Thèses : « Lesions segmentation »

1

Abdullah, Bassem A. « Segmentation of Multiple Sclerosis Lesions in Brain MRI ». Scholarly Repository, 2012. http://scholarlyrepository.miami.edu/oa_dissertations/711.

Texte intégral

Résumé :

Multiple Sclerosis (MS) is an autoimmune disease of central nervous system. It may result in a variety of symptoms from blurred vision to severe muscle weakness and degradation, depending on the affected regions in brain. To better understand this disease and to quantify its evolution, magnetic resonance imaging (MRI) is increasingly used nowadays. Manual delineation of MS lesions in MR images by human expert is time-consuming, subjective, and prone to inter-expert variability. Therefore, automatic segmentation is needed as an alternative to manual segmentation. However, the progression of the MS lesions shows considerable variability and MS lesions present temporal changes in shape, location, and area between patients and even for the same patient, which renders the automatic segmentation of MS lesions a challenging problem. In this dissertation, a set of segmentation pipelines are proposed for automatic segmentation of multiple sclerosis (MS) lesions from brain magnetic resonance imaging (MRI) data. These techniques use a trained support vector machine (SVM) to discriminate between the blocks in regions of MS lesions and the blocks in non-MS lesion regions mainly based on the textural features with aid of the other features. The main contribution of this set of frameworks is the use of textural features to detect MS lesions in a fully automated approach that does not rely on manually delineating the MS lesions. In addition, the technique introduces the concept of the multi-sectional views segmentation to produce verified segmentation. The multi-sectional views pipeline is customized to provide better segmentation performance and to benefit from the properties and the nature of MS lesion in MRI. These customization and enhancement leads to development of the customized MV-T-SVM. The MRI datasets that were used in the evaluation of the proposed pipelines are simulated MRI datasets (3 subjects) generated using the McGill University BrainWeb MRI Simulator, real datasets (51 subjects) publicly available at the workshop of MS Lesion Segmentation Challenge 2008 and real MRI datasets (10 subjects) for MS subjects acquired at the University of Miami. The obtained results indicate that the proposed method would be viable for use in clinical practice for the detection of MS lesions in MRI.

Styles APA, Harvard, Vancouver, ISO, etc.

2

Naeslund, Elin. « Stroke Lesion Segmentation for tDCS ». Thesis, Linköpings universitet, Medicinsk informatik, 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-71472.

Texte intégral

Résumé :

Transcranial direct current stimulation (tDCS), together with speech therapy, is known to relieve the symptoms of aphasia. Knowledge about amount of current to apply and stimulation location is needed to ensure the best result possible. Segmented tissues are used in a finite element method (FEM) simulation and by creating a mesh, information to guide the stimulation is gained. Thus, correct segmentation is crucial. Manual segmentation is known to produce the most accurate result, although it is not useful in the clinical setting since it currently takes weeks to manually segment one image volume. Automatic segmentation is faster, although both acute stroke lesions and nectrotic stroke lesions are known to cause problems. Three automatic segmentation routines are evaluated using default settings and two sets of tissue probability maps (TPMs). Two sets of stroke patients are used; one set with acute stroke lesions (which can only be seen as a change in image intensity) and one set with necrotic stroke lesions (which are cleared out and filled with cerebrospinal fluid (CSF)). The original segmentation routine in SPM8 does not produce correct segmentation result having problems with lesion and paralesional areas. Mohamed Seghier’s ALI, an automatic segmentation routine developed to handle lesions as an own tissue class, does not produce satisfactory result. The new segmentation routine in SPM8 produces the best results, especially if Chris Rorden’s (professor at The Georgia Institute of Technology) improved TPMs are used. Unfortunately, the layer of CSF is not continuous. The segmentation result can still be used in a FEM simulation, although the result from the simulatation will not be ideal. Neither of the automatic segmentation routines evaluated produce an acceptable result (see Figure 5.7) for stroke patients. Necrotic stroke lesions does not affect the segmentation result as much as the acute dito, especially if there is only a small amount of scar tissue present at the lesion site. The new segmentation routine in SPM8 has the brightest future, although changes need to be made to ensure anatomically correct segmentation results. Post-processing algorithms, relying on morphological prior constraints, can improve the segmentation result further.

Styles APA, Harvard, Vancouver, ISO, etc.

3

Wan, Fengkai. « Deep Learning Method used in Skin Lesions Segmentation and Classification ». Thesis, KTH, Medicinsk teknik, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-233467.

Texte intégral

Résumé :

Malignant melanoma (MM) is a type of skin cancer that is associated with a very poor prognosis and can often lead to death. Early detection is crucial in order to administer the right treatment successfully but currently requires the expertise of a dermatologist. In the past years, studies have shown that automatic detection of MM is possible through computer vision and machine learning methods. Skin lesion segmentation and classification are the key methods in supporting automatic detection of different skin lesions. Compared with traditional computer vision as well as other machine learning methods, deep neural networks currently show the greatest promise both in segmentation and classification. In our work, we have implemented several deep neural networks to achieve the goals of skin lesion segmentation and classification. We have also applied different training schemes. Our best segmentation model achieves pixel-wise accuracy of \textbf{0.940}, Dice index of \textbf{0.867} and Jaccard index of \textbf{0.765} on the ISIC 2017 challenge dataset. This surpassed the official state of the art model whose pixel-wise accuracy was 0.934, Dice index 0.849 and Jaccard Index 0.765. We have also trained a segmentation model with the help of adversarial loss which improved the baseline model slightly. Our experiments with several neural network models for skin lesion classification achieved varying results. We also combined both segmentation and classification in one pipeline meaning that we were able to train the most promising classification model on pre-segmented images. This resulted in improved classification performance. The binary (melanoma or not) classification from this single model trained without extra data and clinical information reaches an area under the curve (AUC) of 0.684 on the official ISIC test dataset. Our results suggest that automatic detection of skin cancers through image analysis shows significant promise in early detection of malignant melanoma.

Styles APA, Harvard, Vancouver, ISO, etc.

4

Cabezas, Grebol Mariano. « Atlas-based segmentation of multiple sclerosis lesions in magnetic resonance imaging ». Doctoral thesis, Universitat de Girona, 2013. http://hdl.handle.net/10803/119608.

Texte intégral

Résumé :

This thesis deals with the segmentation of brain magnetic resonance imaging applied to multiple sclerosis patients. This disease is characterised by the presence of white matter lesions in this image modality. After a thorough analysis of the state-of-the-art on this topic, pointing out the importance of prior knowledge, and a subsequent review of atlas-based segmentation of brain imaging, we propose two different multiple sclerosis lesion segmentation pipelines based on the conclusions of these studies. The first one provides an initial tissue classification using a modified expectation-maximisation algorithm, which is later on refined with a lesion segmentation step based on thresholding and a regionwise false positive reduction approach. The second one focuses only on the segmentation of lesions and uses an ensemble classifier alongside a rich feature pool including image intensities, probabilistic atlas maps, an outlier map and contextual information. Both approaches are tested against a novel database comprising imaging data from three different hospitals with a variable lesion load per case. The evaluation, carried out in a quantitative and qualitative manner, includes a comparison and uses several metrics for detection and segmentation. The analysis of the results points out a better performance relative to state-of-the-art approaches, with a clear improvement on the first pipeline in terms of detection, and a clear improvement on the second pipeline in terms of segmentation
Aquesta tesi es centra en la segmentació de imatges de ressonància magnètica del cervell aplicada a pacients d'esclerosi múltiple. Aquesta malaltia es caracteritza per l'aparició de lesions de matèria blanca, visibles en aquesta modalitat d'imatge. Després d'un anàlisi exhaustiu de l'estat de l'art en aquest tòpic, remarcant la importància de la informació prèvia, i també de la segmentació basada en atles del cervell, proposem dues estratègies diferents per a la segmentació de lesions basades en les conclusions d'ambdós estudis. La primera proporciona una classificació inicial dels teixits mitjançant una extensió de l'algorisme d'esperança-maximització, que es refina posteriorment amb un procés de segmentació de les lesions basat en una binarització inicial i una conseqüent estratègia de reducció de falsos positius a nivell de regió. La segona proposta es focalitza bàsicament en la segmentació de lesions i utilitza una combinació de classificadors febles entrenats amb un ric conjunt de característiques que inclou imatges d'intensitat, mapes probabilístics provinents d'un atles, un mapa d'intensitats atípiques i informació contextual. Ambdues estratègies han estat provades amb una nova base de dades formada per imatges de tres hospitals diferents amb diferent càrrega lesional per cas. L'avaluació d'aquestes proves, que s'ha dut a terme de forma quantitativa i qualitativa, inclou una comparativa i utilitza diferents mètriques de detecció i segmentació. L'anàlisi d'aquests resultats apunta a un millor rendiment relatiu a l'estat de l'art actual, amb una millor detecció per part de la primera estratègia i una millor segmentació per part de la segona

Styles APA, Harvard, Vancouver, ISO, etc.

5

Ma, Pu. « Automatic segmentation of multiple sclerosis lesions in magnetic resonance brain images ». Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2001. http://www.collectionscanada.ca/obj/s4/f2/dsk3/ftp05/MQ63536.pdf.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

6

García-Lorenzo, Daniel. « Robust Segmentation of Focal Lesions on Multi-Sequence MRI in Multiple Sclerosis ». Phd thesis, Université Rennes 1, 2010. http://tel.archives-ouvertes.fr/tel-00485645.

Texte intégral

Résumé :

La sclérose en plaques (SEP) atteint autour de 80.000 personnes en France. L'imagerie par résonance magnétique (IRM) est un outil essentiel pour le diagnostic de la SEP. Plusieurs bio-marqueurs sont obtenus à partir des IRM, comme le volume des lésions, et sont utilisés comme mesure dans des études cliniques en SEP, notamment pour le développement des nouveaux traitements. La segmentation manuelle des lésions est une tâche encombrante et dont les variabilités intra- et inter-expert sont grandes. Nous avons développé une chaîne de traitement automatique pour la segmentation des lesions focales en SEP. La méthode de segmentation est basée sur l'estimation robuste d'un modèle paramétrique des intensités du cerveau qui permet de détecter les lésions comme des données aberrantes. Nous avons aussi proposé deux méthodes pour ajouter de l'information spatiale avec les algorithmes mean shift et graph cut. Nous avons validé quantitativement notre approche en utilisant des images synthétiques et cliniques, provenant de deux centres différents pour évaluer la précision et la robustesse.

Styles APA, Harvard, Vancouver, ISO, etc.

7

García, Lorenzo Daniel. « Robust segmentation of focal lesions on multi-sequence MRI in multiple sclerosis ». Rennes 1, 2010. http://www.theses.fr/2010REN1S018.

Texte intégral

Résumé :

La sclérose en plaques (SEP) atteint autour de 80. 000 personnes en France. L'imagerie par résonance magnétique (IRM) est un outil essentiel pour le diagnostic de la SEP. Plusieurs bio-marqueurs sont obtenus à partir des IRM, comme le volume des lésions, et sont utilisés comme mesure dans des études cliniques en SEP, notamment pour le développement des nouveaux traitements. La segmentation manuelle des lésions est une tâche encombrante et dont les variabilités intra- et inter-expert sont grandes. Nous avons développé une chaîne de traitement automatique pour la segmentation des lesions focales en SEP. La méthode de segmentation est basée sur l'estimation robuste d'un modèle paramétrique des intensités du cerveau qui permet de détecter les lésions comme des données aberrantes. Nous avons aussi proposé deux méthodes pour ajouter de l'information spatiale avec les algorithmes mean shift et graph cut. Nous avons validé quantitativement notre approche en utilisant des images synthétiques et cliniques, provenant de deux centres différents pour évaluer la précision et la robustesse
Multiple sclerosis (MS) affects around 80. 000 people in France. Magnetic resonance imaging (MRI) is an essential tool for diagnosis of MS and MRI-derived surrogate markers such as MS lesion volumes are often used as measures in MS clinical trials for the development of new treatments. The manual segmentation of these MS lesions is a time-consuming task that shows high inter- and intra-rater variability. We developed an automatic workflow for the segmentation of focal MS lesions on MRI. The segmentation method is based on the robust estimation of a parametric model of the intensities of the brain; lesions are detected as outliers to the model. We proposed two methods to include spatial information in the segmentation using mean shift and graph cut. We performed a quantitative evaluation of our workflow using synthetic and clinical images of two different centers to verify its accuracy and robustness

Styles APA, Harvard, Vancouver, ISO, etc.

8

ASLANI, SHAHAB. « Deep learning approaches for segmentation of multiple sclerosis lesions on brain MRI ». Doctoral thesis, Università degli studi di Genova, 2020. http://hdl.handle.net/11567/997626.

Texte intégral

Résumé :

Multiple Sclerosis (MS) is a demyelinating disease of the central nervous system which causes lesions in brain tissues, especially visible in white matter with magnetic resonance imaging (MRI). The diagnosis of MS lesions, which is often performed visually with MRI, is an important task as it can help characterizing the progression of the disease and monitoring the efficacy of a candidate treatment. automatic detection and segmentation of MS lesions from MRI images offer the potential for a faster and more cost-effective performance which could also be immune to expert bias segmentation. In this thesis, we study automated approaches to segment MS lesions from MRI images. The thesis begins with a review of the existing literature on MS lesion segmentation and discusses their general limitations. We then propose three novel approaches that rely on Convolutional Neural Networks (CNNs) to segment MS lesions. The first approach demonstrates that the parameters of a CNN learned from natural images, transfer well to the tasks of MS lesion segmentation. In the second approach, we describe a novel multi-branch CNN architecture with end-to-end training that can take advantage of each MRI modalities individually. In that work, we also investigated the combination of MRI modalities leading to the best segmentation performance. In the third approach, we show an effective and novel generalization method for MS lesion segmentation when data are collected from multiple MRI scanning sites and as suffer from (site-)domain shifts. Finally, this thesis concludes with open questions that may benefit from future work. This thesis demonstrates the potential role of CNNs as a common methodological building block to address clinical problems in MS segmentation.

Styles APA, Harvard, Vancouver, ISO, etc.

9

Peruch, Francesco. « (SEMI)-AUTOMATED ANALYSIS OF MELANOCYTIC LESIONS ». Doctoral thesis, Università degli studi di Padova, 2015. http://hdl.handle.net/11577/3424252.

Texte intégral

Résumé :

Melanoma is a very aggressive form of skin cancer whose incidence has constantly grown in the last 50 years. To increase the survival rate, an early diagnosis followed by a prompt excision is crucial and requires an accurate and periodic analysis of the patient's melanocytic lesions. We have developed an hardware and software solution named Mole Mapper to assist the dermatologists during the diagnostic process. The goal is to increase the accuracy of the diagnosis, accelerating the entire process at the same time. This is achieved through an automated analysis of the dermatoscopic images which computes and highlights the proper information to the dermatologist. In this thesis we present the 3 main algorithms that have been implemented into the Mole Mapper: A robust segmentation of the melanocytic lesion, which is the starting point for any other image processing algorithm and which allows the extraction of useful information about the lesion's shape and size. It outperforms the speed and quality of other state-of-the-art methods, with a precision that meets a Senior Dermatologist's standard and an execution time that allows for real-time video processing; A virtual shaving algorithm, which increases the precision and robustness of the other computer vision algorithms and provides the dermatologist with a hair-free image to be used during the evaluation process. It matches the quality of state-of-the-art methods but requires only a fraction of the computational time, allowing for computation on a mobile device in a time-frame compatible with an interactive GUI; A registration algorithm through which to study the evolution of the lesion over time, highlighting any unexpected anomalies and variations. Since a standard approach to this problem has not yet been proposed, we define the scope and constraints of the problem; we analyze the results and issues of standard registration techniques; and finally, we propose an algorithm with a speed compatible with Mole Mapper's constraints and with an accuracy comparable to the registration performed by a human operator.
Il Melanoma è una forma molto aggressiva di cancro alla pelle la cui incidenza è costantemente aumentata negli ultimi 50 anni. Una diagnosi precoce unita ad una rapida asportazione risulta indispensabile per migliorare il tasso di sopravvivenza e richiede una analisi periodica ed accurata della lesioni melanocitiche del paziente. Abbiamo sviluppato una soluzione hardware e software chiamata Mole Mapper per assistere i deramtologi durante l'intero processo di diagnosi. L'obiettivo è permettere un incremento dell'accuratezza della diagnosi velocizzando al contempo l'intero processo. Tali caratteristiche si sono ottenute grazie ad un'analisi automatica delle immagini dermatoscopiche che individua ed evidenza al dermatologo le informazioni più significative. In questa tesi presentiamo 3 principali algoritmi che sono stati implementati in Mole Mapper: Una robusta segmentazione di lesioni melanocitiche, che risulta il punto di partenza di ogni altro algoritmo di elaborazioni di immagini e permette l'estrazione di informazioni utili riguardanti la forma e la dimensione delle lesioni. Tale algoritmo supera in accuratezza e velocità lo stato dell'arte attuale, con una precisione paragonabile ad un dermatologo esperto ed un tempo di esecuzione compatibile con l'elaborazione video realtime; Un algoritmo di depilazione digitale, che garantisce miglior precisione e robustezza agli altri algoritmi di elaborazione di immagini a fornisce al dermatologo un immagine priva di peli da impiegare nel processo di valutazione. La nostra proposta supera l'accuratezza dello stato dell'arte richiedendo solo una frazione del tempo di esecuzione, tanto da poter essere integrata su dispositivi mobili all'interno di una GUI interattiva. Un algoritmo di registrazione, per studiare l'evoluzione delle lesioni nel tempo evidenziando ogni possibile anomalia o variazione. Data la mancanza di un approccio standard al problema, abbiamo caratteriizzato gli obbiettivi ed i vincoli a cui sottostare proponendo quindi un approccio con un tempo di esecuzione compatibile con le necessità del Mole Mapper ed un accuratezza paragonabile a quella di un operatore umano.

Styles APA, Harvard, Vancouver, ISO, etc.

10

Cui, Shenshen. « Fully Automatic Segmentation of White Matter Lesions from Multispectral Magnetic Resonance Imaging Data ». Thesis, Uppsala University, Department of Information Technology, 2010. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-122650.

Texte intégral

Résumé :

A fully automatic white matter lesion segmentation method has been developed and evaluated. The method uses multispectral magnetic resonance imaging (MRI) data (T1,T2 and Proton Density). First fuzzy c means (FCM) was used to segment normal brain tissues (white matter,grey matter, and cerebrospinal fluid). The holes in normal white matter were used to sample the WML intensities in the different images. The segmentation of WML was optimized by a graph cut approach. The method was trained by using 9 manually segmented datasets and evaluated by comparison to 11 other manually segmented, and visually evaluated, datasets. The graph cut part of the automatic segmentation requires, on average, 30 seconds per dataset. The results correlated well (r=0.954) to a manually created reference that was supervised by two neuro radiologists.

Key Words: White matter lesion, automatic segmentation, graph cuts, MRI, PIVUS

Styles APA, Harvard, Vancouver, ISO, etc.

11

Rajab, Maher I. « Neural network edge detection and skin lesions image segmentation methods : analysis and evaluation ». Thesis, University of Nottingham, 2003. http://eprints.nottingham.ac.uk/13681/.

Texte intégral

Résumé :

Similar to a human observer, an automated image vision system is able to recognise most parts of an object if the system could accurately trace and reflect its true shape. This has prompted the development of the many diverse edge detection techniques. Neural networks have been successfully applied to pattern recognition tasks and edge detection. However, there is a great necessity to analyse neural network models so as to achieve close insight into their internal functionality. To this purpose, a new and general training set, consisting of a limited number of prototype edge patterns, is proposed to analyse the problem of neural network edge detection. This thesis also proposes two approaches to the skin lesion image segmentation problem. The first is a mainly thresholding segmentation method where an optimal threshold is determined iteratively by an isodata algorithm. The second method proposed is based on neural network edge detection and a rational Gaussian curve that fits an approximate closed elastic curve between the recognized neural network edge patterns. A quantitative comparison of the techniques is enabled by the use of synthetic lesions to which Gaussian noise is added. The proposed techniques are also compared with an established automatic skin segmentation method. It is demonstrated that for lesions with a range of different border irregularity properties the thresholding segmentation method provides the best performance over a range of signal to noise ratios; the thresholding segmentation method is also demonstrated to have similar performance when tested on real skin lesions.

Styles APA, Harvard, Vancouver, ISO, etc.

12

Mokhomo, Molise. « Automatic detection and segmentation of brain lesions from 3D MR and CT images ». Master's thesis, University of Cape Town, 2014. http://hdl.handle.net/11427/9089.

Texte intégral

Résumé :

Includes bibliographical references.
The detection and segmentation of brain pathologies in medical images is a vital step which helps radiologists to diagnose a variety of brain abnormalities and set up a suitable treatment. A number of institutes such as iThemba LABS still rely on a manual identification of abnormalities. A manual identification is labour intensive and tedious due to the large amount of medical data to be processed and the presence of small lesions. This thesis discusses the possible methods that can be used to address the problem of brain abnormality segmentation in MR and CT images. The methods are general enough to segment different types of abnormalities. The first method is based on the symmetry of the brain while the second method is based on a brain atlas. The symmetry-based method assumes that healthy brain tissues are symmetrical in nature while abnormal tissues are asymmetric with respect to the symmetry plane dividing the brain into similar hemispheres. The three major steps involved in this approach are the symmetry detection, tilt correction and asymmetry quantification. The method used to determine the brain symmetry automatically is discussed and its accuracy has been validated against the ground-truth using mean angular error (MAE) and distance error (DE). Two asymmetric quantification methods are studied and validated on real and simulated patient’s T1- and T2-weighted MR images with low and highgrade gliomas using true positive volume fraction (TPVF), false positive volume fraction (FPVF) and false negative volume fraction (FNVF). The atlas-based method is also presented and relies on the assumption that abnormal brain tissues appear with intensity values different from those of the surrounding healthy tissues. To detect and segment brain lesions the test image is aligned onto the atlas space and voxel by voxel analysis is performed between the atlas and the registered image. This methods is also evaluated on the simulated T1-weighted patient dataset with simulated low and high grade gliomas. The atlas, containing prior knowledge of normal brain tissues, is built from a set of healthy subjects.

Styles APA, Harvard, Vancouver, ISO, etc.

13

Veronese, Elisa. « Methods for segmentation and characterization of multiple sclerosis cortical lesions from MRI data ». Doctoral thesis, Università degli studi di Padova, 2012. http://hdl.handle.net/11577/3422439.

Texte intégral

Résumé :

This thesis deals with the automatic analysis of magnetic resonance images of the brain, acquired from people affected by multiple sclerosis. In particular, the primary aim of the analysis is to obtain a quantitative measure of the cortical lesion burden due to the specific disease. Besides, we propose a technique for the characterization of the different lesion types, based on their inflammatory activity. Multiple sclerosis is a chronic, inflammatory disease of the central nervous system, that causes a progressive demyelination of several areas of the brain and of the spinal cord. As far as diseases’ frequency is concerned, multiple sclerosis represents the second neurologic disease in the young adult, and it is even the first inflammatory chronic disease. Besides, it can also be considered as a social burden, with heavy direct and indirect costs: multiple sclerosis prevents people from working as much as they could without the disease, and can lead to the impossibility to live autonomously. Last but not least, the cost of treatment and care can be very high. Although the causes are still partly unclear, a lot has been achieved in the understanding of the different phases of the inflammatory process characterizing multiple sclerosis. Today it is possible to early diagnose the disease, thus allowing to limit symptoms by early therapies. The lesions caused by multiple sclerosis can be visualized in vivo thanks to magnetic resonance (MR) imaging. In particular in the latest decades several MR sequences have been designed in order to highlight white matter lesions. When studying gray matter lesions, instead, the available MR sequences are less numerous. This is partly due to the fact that the gray matter involvement in multiple sclerosis is a relatively recent finding. It is important to verify both the evolution and the appearance of new lesions: in this way it is possible to monitor the disease progression, which is particularly tricky in the case of multiple sclerosis. This disease is characterized by acute relapses alternated with remitting periods of variable length. For this reason patients are periodically examined acquiring MR images. The subsequent diagnosis made by the physician is based on the MR results. So, it is fundamental for the neurologist to be well trained in order to be able to properly evaluate different magnetic resonance sequences. Besides, he/she has to pay close attention not only to detect new lesions, but also to recognize those lesions that were already present in the previous examinations, and that might have changed their shape, their dimension or they activity. This process requires time and attention, but unfortunately, being human-based, it is strongly error prone. Unquestionably, the diagnose cannot prescind from the neurologist’s evaluation. Nonetheless, the advent of techniques for the automatic analysis of magnetic resonance images and for the detection of multiple sclerosis lesions would represent a valid support for the physicians, who could provide accurate evaluations in faster timing. In this thesis several MR techniques currently used for cortical lesions visualization will be described. Then a segmentation algorithm will be proposed, in order to find the region corresponding to gray matter. On this region a second algorithm will be presented, that detect multiple sclerosis cortical lesions. Finally, a first attempt to characterize cortical lesions based on their inflammatory activity will be described.
Questa tesi tratta l’analisi automatica di immagini di risonanza magnetica cerebrale in soggetti affetti da sclerosi multipla. In particolare, l’analisi è volta sia a una stima quantitativa del carico di lesioni corticali presenti a causa del decorso della malattia, sia a una caratterizzazione del tipo di lesioni presenti basata sul loro grado di infiammazione. La sclerosi multipla è una malattia infiammatoria a decorso cronico che colpisce il sistema nervoso centrale, provocandone una progressiva distruzione della mielina in più aree. Per frequenza, nel giovane adulto è la seconda malattia neurologica e la prima di tipo infiammatorio cronico. Inoltre, la sclerosi multipla può essere considerata anche come malattia sociale, con un’elevata ricaduta economica, sia diretta che indiretta: la diminuzione o la perdita dell’autonomia porta alla progressiva impossibilità di svolgere una qualsiasi attività lavorativa fino all’incapacità di condurre una vita indipendente. A questo si aggiungano il costo delle cure e dell’assistenza necessarie. Benché le cause siano ancora in parte sconosciute, molto è stato fatto nel chiarire le diverse fasi del processo infiammatorio che caratterizza tale patologia, permettendo così di arrivare a una diagnosi e a un trattamento precoce che consentono di ridurre gli effetti della malattia. Le lesioni causate dalla sclerosi multipla risultano visibili grazie a particolari tecniche di acquisizione di immagini basate sulla risonanza magnetica. In particolare negli ultimi decenni si sono studiate e messe a punto diverse sequenze di risonanza ottimizzate per la visualizzazione delle lesioni in materia bianca. Il quadro delle tecniche a disposizione qualora si vogliano studiare lesioni in materia grigia risulta invece meno completo, soprattutto a causa del fatto che la scoperta di un coinvolgimento della materia grigia nella malattia è molto più recente. La verifica dell’evoluzione e della comparsa di nuove lesioni è importante dal momento che consente di monitorare il progredire di una malattia caratterizzata da fasi acute intervallate a periodi di quiescenza più o meno lunghi. Per questo motivo i soggetti affetti da sclerosi multipla vengono periodicamente sottoposti a esami di risonanza magnetica. Ogni successiva valutazione da parte del medico neurologo dipenderà da quanto evidenziato dalle immagini acquisite. In questo senso è fondamentale che il medico sia ben allenato nella valutazione di immagini di risonanza, e che ponga particolare attenzione non solo nell’individuare la comparsa di nuove lesioni, ma anche nel riconoscere la presenza di lesioni già presenti in esami precedenti, che possono essere progredite nella forma, nelle dimensioni e nel grado di attività. La lettura di un esame di risonanza magnetica richiede tempo e attenzione, ed è inevitabilmente soggetta all’errore umano che caratterizza qualsiasi valutazione manuale. Per questo, benché sia impensabile prescindere dalla valutazione del medico, una tecnica di analisi automatica di immagini di risonanza magnetica cerebrale che sia in grado di evidenziare la presenza di lesioni da sclerosi multipla può rappresentare un valido aiuto alla refertazione, sia in termini di tempo che di accuratezza. In questa tesi si descriveranno le tecniche di risonanza magnetica a disposizione per una miglior visualizzazione delle lesioni corticali. Su queste si procederà alla segmentazione del tessuto di interesse, ossia del volume di materia grigia. In seguito verrà descritta la tecnica proposta per il riconoscimento delle regioni patologiche corticali. Infine sarà descritto un primo tentativo di caratterizzazione delle diverse lesioni corticali, basato sulla valutazione del grado di attività di ciascuna lesione.

Styles APA, Harvard, Vancouver, ISO, etc.

14

Militzer, Arne [Verfasser], et Joachim [Akademischer Betreuer] Hornegger. « Boosting Methods for Automatic Segmentation of Focal Liver Lesions / Arne Militzer. Gutachter : Joachim Hornegger ». Erlangen : Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), 2015. http://d-nb.info/1075480299/34.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

15

Bakas, Spyridon. « Computer-aided localisation, segmentation and quantification of focal liver lesions in contrast-enhanced ultrasound ». Thesis, Kingston University, 2014. http://eprints.kingston.ac.uk/30592/.

Texte intégral

Résumé :

The research presented in this thesis focuses on applications of Contrast Enhanced Ultrasound (CEUS) imaging and is coordinated to address current clinical requirements in the assessment, quantification and evaluation of liver cancer and in particular focal liver lesions (FLLs). The main outcomes of this research are methods to assist radiologists with automating these routinely performed manual image interpretation tasks, with the intention of supporting them to make their diagnostic decisions faster, more easily and with greater confidence. Such automatic analysis is challenging mainly because of the relative motion between the ultrasound transducer and the liver, the physiological motion of the patient and the dramatic intensity changes over time caused by the contrast-enhancing agents intravenously injected during a CEUS examination. The work described in this thesis can be divided into three principal themes. These are addressed in turn below. Firstly, a set of methods are proposed to assist in automating initialisation tasks required for the offline assessment of data acquired during CEUS liver scans. These tasks relate to the delineation of the area comprising the ultrasonographic image, the identification of the optimal reference frame for initialising an FLL, as well as the segmentation of the FLL boundaries on this frame. The potential clinical value of the proposed methods is that they can lead to easier and faster assessment of FLLs, whilst producing results less dependent on the human initialisation and hence improving the repeatability and reproducibility of the assessment of the examination and increasing the confidence of radiologists when making a diagnosis. Secondly, a variety of methods are investigated to estimate the motion observed within the ultrasonographic image of CEUS screening recordings and then compensate for this, allowing for an accurate quantification of the perfusion of tissue regions. Obtaining a perfusion curve for an image region, without compensating for the observed motion, may lead to erroneous diagnostic results as the specified image region may correspond to different tissue along the video sequence. Quantitative evaluation of the presented methods demonstrates their potential as reliable real-time motion compensation methods for such recordings. Finally, an alternative fully automatic method for the identification and localisation of potential malignancies is proposed. For such identification, and hence distinction between cases that include potentially malignant and benign lesions, an innovative assessment of the global spatial configuration of local variations of perfusion curves is presented. For the localisation of tissue regions of potential malignancy, a novel feature is proposed that encompasses spatio-temporal information (Le. the combination of both the variation in these local perfusion curves and the location they relate to) to cluster together neighbouring regions with similar dynamic behaviour. The clinical value of the identification part is the early diagnosis of an FLL’s type and the possibility for the discharge of patients with benign FLLs, leading to less distress to the patients and their families, as well as reduced healthcare costs. Additionally, the localisation part assists in enhancing the radiologist’s awareness of tissue regions with potentially malignant behaviour, as well as providing effortless localisation of such regions allowing for an objective initialisation of computer-aided segmentation methods improving the repeatability and reproducibility of the assessment of CEUS data. The key findings of this research indicate that: i) the optimal reference frame can be reliably identified in a fully automatic and deterministic manner, ii) the segmentation of an F LL can be performed in a rapid semi-automatic manner, which produces results that are, at worst, of comparable consistency as different manual annotations, iii) the apparent observed motion can be compensated in real-time, either locally or globally, and a simple translation is sufficient to achieve this, iv) the distinction between benign and malignant lesions can be performed in a fully automatic and deterministic manner, without missing a single malignancy, and v) potential malignancies can be localised reliably in a fully automatic manner. Quantitative analysis of all results on real clinical data, from a multi-centre study, is used to evaluate the level of confidence of the decision of the proposed methods and demonstrates the value of these methods in a diverse dataset acquired using the protocol of current standard care. A system incorporating the proposed methods could improve the current clinical practice for assessing, quantifying and evaluating FLLs in CEUS recordings. Specifically, it would be beneficial to radiologists, for cancer research, providing easier and faster assessment of FLLs whilst producing results less dependent on the human initialisation and therefore increasing the confidence of radiologists in their diagnostic decisions.

Styles APA, Harvard, Vancouver, ISO, etc.

16

Lindemalm, Karlsson Josefin. « Deep Learning-Based Automated Segmentation and Detection of Chondral Lesions on the Distal Femur ». Thesis, KTH, Fysik, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-253077.

Texte intégral

Résumé :

Articular chondral lesions in the knee joint can be diagnosed at an early stage using MRI. Segmenting and visualizing lesions and the overall joint structure allows improved communication between the radiologist and referring physician. It can also be of help when determining diagnosis or conducting surgical planning. Although there are a variety of studies proving good results of segmentation of larger structures such as bone and cartilage in the knee, there are no studies available researching segmentation of articular cartilage lesions. Automating the segmentation will save time and money since manual segmentation is very time-consuming. In this thesis, a U-Net based convolutional neural network is used to perform automatic segmentation of chondral lesions located on the distal part of the femur, in the knee joint. Using two different techniques, batch normalization and dropout, a network was trained and tested using MRI sequences collected from Episurf Medical's database. The network was then evaluated using a segmentation approach and a detection approach. For the segmentation approach, the highest achieved dice coefficient and sensitivity of 0.4059 ± 0.1833 and 0.4591 ± 0.2387, was obtained using batch normalization and 260 training subjects, consisting of MRI sequence and corresponding masks. Using a detection approach, the predicted output could correctly identify 81.8% of the chondral lesions in the MRI sequences. Although there is a need for improvement of technique and datasets used in this thesis, the achieved results show prerequisites for future improvement and possible implementation.
Skador i knäledens brosk kan diagnostiseras i ett tidigt stadie med hjälp av MR. Segmentering och visualisering av skadorna, samt ledens struktur i helhet, bidrar till en förbättrad kommunikation mellan radiolog och remitterande läkare. Det kan också underlätta för att ställa diagnos eller utföra operationsplanering. I dagsläget finns flertalet studier som påvisar goda resultat för segmentering av större strukturer, t.ex. ben och brosk. Det finns dock få studier som studerar segmentering av skador i ledbrosk. Genom att automatisera segmenteringsprocessen kan både tid och pengar sparas. Detta eftersom att manuell segmentering är mycket tidskrävande. I detta arbete kommer ett U-Net baserat convolutional neural network att användas för att utföra automatisk segmentering av skador på distala femur i knäleden. Nätverket kommer att tränas med två olika tekniker, batch normalization och dropout. Nätverket kommer att tränas med data som är hämtad från Episurf Medicals databas och består av MR sekvenser. Nätverket kommer att tränas och utvärderas med hjälp av två metoder, en segmenteringsmetod och detekteringsmetod. Den högsta uppnådda dice koefficienten och sensitiviteten vid utvärderingen av segmenteringsmetoden uppmätte 0,4059 ± 0,1833 och 0,4591 ± 0,2387. Den upnåddes med hjälp av batch normalization och 260 MR sekvenser för träning och testning. För detektionsmetoden kunde programmet identifiera 81,8% av skadorna synliga på MR sekvenserna. Även om tekniken och datan som används behöver optimeras, så visar det uppnådda resultatet på bra förutsättningar för fortsatta studier och i framtiden möjligen även implementering av tekniken.

Styles APA, Harvard, Vancouver, ISO, etc.

17

Geremia, Ezequiel. « Spatial random forests for brain lesions segmentation in MRIs and model-based tumor cell extrapolation ». Phd thesis, Université Nice Sophia Antipolis, 2013. http://tel.archives-ouvertes.fr/tel-00838795.

Texte intégral

Résumé :

The large size of the datasets produced by medical imaging protocols contributes to the success of supervised discriminative methods for semantic labelling of images. Our study makes use of a general and efficient emerging framework, discriminative random forests, for the detection of brain lesions in multi-modal magnetic resonance images (MRIs). The contribution is three-fold. First, we focus on segmentation of brain lesions which is an essential task to diagnosis, prognosis and therapy planning. A context-aware random forest is designed for the automatic multi-class segmentation of MS lesions, low grade and high grade gliomas in MR images. It uses multi-channel MRIs, prior knowledge on tissue classes, symmetrical and long-range spatial context to discriminate lesions from background. Then, we investigate the promising perspective of estimating the brain tumor cell density from MRIs. A generative-discriminative framework is presented to learn the latent and clinically unavailable tumor cell density from model-based estimations associated with synthetic MRIs. The generative model is a validated and publicly available biophysiological tumor growth simulator. The discriminative model builds on multi-variate regression random forests to estimate the voxel-wise distribution of tumor cell density from input MRIs. Finally, we present the "Spatially Adaptive Random Forests" which merge the benefits of multi-scale and random forest methods and apply it to previously cited classification and regression settings. Quantitative evaluation of the proposed methods are carried out on publicly available labeled datasets and demonstrate state of the art performance.

Styles APA, Harvard, Vancouver, ISO, etc.

18

BAIL, LAURENT. « Segmentation automatique en i. R. M. Des lesions de sclerose en plaque : correlation avec l'atrophie du corps calleux ». Lille 2, 1994. http://www.theses.fr/1994LIL2M251.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

19

Bernart, Eliezer Emanuel. « Detecção e qualificação de lesões melanocíticas através de evidências locais e de contexto ». reponame:Biblioteca Digital de Teses e Dissertações da UFRGS, 2016. http://hdl.handle.net/10183/134372.

Texte intégral

Résumé :

Neste trabalho, um novo método não-supervisionado para segmentação de lesões melanocíticas em imagens macroscópicas é proposto levando em consideração regiões suspeitas, e também uma nova abordagem para classificação de lesões que faz uso de evidências locais e de contexto para estimar um índice de probabilidade para malignidade em cada lesão. O método proposto realiza a segmentação das imagens em três tipos de regiões disjuntas: ‘pele saudável’, ‘região de incerteza’ e ‘lesão’. Regiões de incerteza são refinadas através da utilização de feições estocásticas também de forma não-supervisionada, resultando em uma máscara binária que discrimina a pele da lesão. As máscaras obtidas apresentam um erro XOR comparável aos métodos estado da arte. A imagem é segmentada utilizando um algoritmo de superpixels e as sub-regiões que intersectam a máscara obtida são categorizadas como evidências locais. Estas evidências são representadas por uma descrição especializada que explora as características como cor e textura. Estas sub-regiões são então associadas à evidências de contexto definidas pela borda da lesão de onde foram extraídas e classificadas de forma independente através de uma abordagem supervisionada. Com o resultado da classificação destas evidências é possível obter um indicador probabilístico para malignidade associado a cada lesão, e levando em consideração um valor de tolerância é possível identificar lesões malignas em potencial. Os resultados obtidos com o método proposto são promissores e apresentam maior acurácia do que os métodos existentes na literatura apesar do erro XOR da segmentação das lesões ser maior, o que tende a confirmar o potencial do método proposto para discriminar lesões melanocíticas benignas e malignas.
In this work, a novel unsupervised method for melanocytic macroscopic image segmentation is proposed considering suspicious regions, and also a novel approach for lesion classification using local and context evidence to estimate a probabilistic index of malignity or benignity in each lesion. The proposed method segment the macroscopic images in three types of disjoint regions: ‘healthy skin’, ‘suspicious region’ and ‘lesion’. Suspicious areas are refined using stochastic texture features also in an unsupervised approach, resulting in a binary mask discriminating skin and lesion. The resulting masks present an XOR error similar to other state-of-art methods. In the next step, the image is segmented using a superpixels algorithm and subregions that intersect the obtained mask categorized as local evidence. A specialized representation describes color and texture information present in the local evidence region. The border of the segmented skin lesion defines the context evidence and using a supervised approach, local and context evidence are combined and classified independently. With the evidence classification results is possible to obtain a probabilistic index of malignity and benignity associated to each lesion, and considering a tolerance value is possible to identify potential malignant lesions. The results achieved with the proposed method are promissing and present greater accuracy than other techniques in the literature, even with a greater XOR error in segmentation step, confirming the proposed method’s potential to discriminate benignant and malignant melanocytic lesions.

Styles APA, Harvard, Vancouver, ISO, etc.

20

Engström, Messén Matilda, et Elvira Moser. « Pre-planning of Individualized Ankle Implants Based on Computed Tomography - Automated Segmentation and Optimization of Acquisition Parameters ». Thesis, KTH, Fysik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-297674.

Texte intégral

Résumé :

The structure of the ankle joint complex creates an ideal balance between mobility and stability, which enables gait. If a lesion emerges in the ankle joint complex, the anatomical structure is altered, which may disturb mobility and stability and cause intense pain. A lesion in the articular cartilage on the talus bone, or a lesion in the subchondral bone of the talar dome, is referred to as an Osteochondral Lesion of the Talus (OLT). Replacing the damaged cartilage or bone with an implant is one of the methods that can be applied to treat OLTs. Episurf Medical develops and produces patient-specific implants (Episealers) along with the necessary associated surgical instruments by, inter alia, creating a corresponding 3D model of the ankle (talus, tibial, and fibula bones) based on either a Magnetic Resonance Imaging (MRI) scan or a Computed Tomography (CT) scan. Presently, the3D models based on MRI scans can be created automatically, but the 3Dmodels based on CT scans must be created manually, which can be very time-demanding. In this thesis project, a U-net based Convolutional Neural Network (CNN) was trained to automatically segment 3D models of ankles based on CT images. Furthermore, in order to optimize the quality of the incoming CT images, this thesis project also consisted of an evaluation of the specified parameters in the Episurf CT talus protocol that is being sent out to the clinics. The performance of the CNN was evaluated using the Dice Coeﬀicient (DC) with five-fold cross-validation. The CNN achieved a mean DC of 0.978±0.009 for the talus bone, 0.779±0.174 for the tibial bone, and 0.938±0.091 for the fibula bone. The values for the talus and fibula bones were satisfactory and comparable to results presented in previous researches; however, due to background artefacts in the images, the DC achieved by the network for the segmentation of the tibial bone was lower than the results presented in previous researches. To correct this, a noise-reducing filter will be implemented.
Fotledens komplexa anatomi ger upphov till en ideal balans mellan rörlighetoch stabilitet, vilket i sin tur möjliggör gång. Fotledens anatomi förändras när en skada uppstår, vilket kan påverka rörligheten och stabiliteten samt orsaka intensiv smärta. En skada i talusbenets ledbrosk eller i det subkondrala benet på talusdomen benämns som en Osteochondral Lesion of the Talus(OLT). En metod att behandla OLTs är att ersätta den del brosk eller bensom är skadat med ett implantat. Episurf Medical utvecklar och producerar individanpassade implantat (Episealers) och tillhörande nödvändiga kirurgiska instrument genom att, bland annat, skapa en motsvarande 3D-modell av fotleden (talus-, tibia- och fibula-benen) baserat på en skanning med antingen magnetisk resonanstomografi (MRI) eller datortomografi (CT). I dagsläget kan de 3D-modeller som baseras på MRI-skanningar skapas automatiskt, medan de 3D-modeller som baseras på CT-skanningar måste skapas manuellt - det senare ofta tidskrävande. I detta examensarbete har ett U-net-baserat Convolutional Neuralt Nätverk (CNN) tränats för att automatiskt kunna segmentera 3D-modeller av fotleder baserat på CT-bilder. Vidare har de speciferade parametrarna i Episurfs CT-protokoll för fotleden som skickas ut till klinikerna utvärderats, detta för att optimera bildkvaliteten på de CT-bilder som används för implantatspositionering och design. Det tränade nätverkets prestanda utvärderades med hjälp av Dicekoeﬀicienten (DC) med en fem-delad korsvalidering. Nätverket åstadkom engenomsnittlig DC på 0.978±0.009 för talusbenet, 0.779±0.174 för tibiabenet, och 0.938±0.091 för fibulabenet. Värdena för talus och fibula var adekvata och jämförbara med resultaten presenterade i tidigare forskning. På grund av bakgrundsartefakter i bilderna blev den DC som nätverket åstadkom för sin segmentering av tibiabenet lägre än tidigiare forskningsresultat. För att korrigera för bakgrundsartefakterna kommer ett brusreduceringsfilter implementeras

Styles APA, Harvard, Vancouver, ISO, etc.

21

Flores, Eliezer Soares. « Segmentação de lesões melanocíticas usando uma abordagem baseada no aprendizado de dicionários ». reponame:Biblioteca Digital de Teses e Dissertações da UFRGS, 2015. http://hdl.handle.net/10183/115219.

Texte intégral

Résumé :

Segmentação é uma etapa essencial para sistemas de pré-triagem de lesões melanocíticas. Neste trabalho, um novo método para segmentar lesões melanocíticas em imagens de câmera padrão (i.e., imagens macroscópicas) é apresentado. Inicialmente, para reduzir artefatos indesejáveis, os efeitos de sombra são atenuados na imagem macroscópica e uma présegmentação é obtida usando um esquema que combina a transformada wavelet com a transformada watershed. Em seguida, uma imagem de variação textural projetada para melhorar a discriminabilidade da lesão em relação ao fundo é obtida e a região présegmentada é usada para o aprendizado de um dicionário inicial e de uma representação inicial via um método de fatoração de matrizes não-negativas. Uma versão nãosupervisionada e não-paramétrica do método de aprendizado de dicionário baseado em teoria da informação é proposta para otimizar esta representação, selecionando o subconjunto de átomos que maximiza a compactividade e a representatividade do dicionário aprendido. Por fim, a imagem da lesão de pele é representada usando o dicionário aprendido e segmentada com o método de corte normalizado em grafos. Nossos resultados experimentais baseados em uma base de imagens bastante utilizada sugerem que o método proposto tende a fornecer melhores resultados do que os métodos estado-da-arte analisados (em termos do erro XOR).
Segmentation is an essential step for the automated pre-screening of melanocytic lesions. In this work, a new method for segmenting melanocytic lesions in standard camera images (i.e., macroscopic images) is presented. Initially, to reduce unwanted artifacts, shading effects are attenuated in the macroscopic image and a pre-segmentation is obtained using a scheme that combines the wavelet transform and the watershed transform. Afterwards, a textural variation image designed to enhance the skin lesion against the background is obtained, and the presegmented skin lesion region is used to learn an initial dictionary and an initial representation via a nonnegative matrix factorization method. An unsupervised and non-parametric version of the information-theoretic dictionary learning method is proposed to optimize this representation by selecting the subset of atoms that maximizes the learned dictionary compactness and representation. Finally, the skin lesion image is represented using the learned dictionary and segmented with the normalized graph cuts method. Our experimental results based on a widely used image dataset suggest that the proposed method tends to provide more accurate skin lesion segmentations than comparable state-of-the-art methods (in terms of the XOR error).

Styles APA, Harvard, Vancouver, ISO, etc.

22

Roura, Pérez Eloy. « Automated methods on magnetic resonance brain imaging in multiple sclerosis ». Doctoral thesis, Universitat de Girona, 2016. http://hdl.handle.net/10803/394030.

Texte intégral

Résumé :

In this thesis, we have focused on the image pre-processing in order to enhance the image information. The main aspects of this enhancement rely on removing any image noise and correcting any intensity bias induced by the scanner. Besides, we also contributed with a new technique based on a multispectral, adaptive, region growing algorithm in order to segment the brain from the rest of the head. We include, as a pre-processing step, the image registration process, in which we proposed a novel pipeline by using information from multiple modalities to improve the results of this process. Furthermore, we have also studied the current techniques for the detection and segmentation of WML, proposing a new method based on a previous proposal. Therefore, we presented a tool able to automatically detect and segment WML of Multiple sclerosis and Lupus patients.
En aquesta tesi ens centrem, per una part, en el pre-processat de la imatge per tal d'eliminar el soroll i corregir les inhomogeneïtats en les intensitats, ambdós errors introduïts per l'escàner. A més hem contribuït també amb una nova tècnica basada en un algoritme de “región growing” per tal de segmentar el cervell de dins de tota la imatge del cap. Incloem com a pre-processat el registre d'imatges, on hem proposat una “pipeline" mitjançant la informació de múltiples modalitats per tal de millorar els resultats d'aquest procés. Per altra banda, hem estudiat també les tècniques actuals de detecció i segmentació de lesions en la matèria blanca, proposant un mètode nou basat en anteriors propostes. Així doncs, presentem una eina automàtica capaç de detectar i segmentar lesions en la matèria blanca de pacients d'Esclerosi Múltiple i Lupus.

Styles APA, Harvard, Vancouver, ISO, etc.

23

Demel, Jan. « Segmentace 3D obrazových dat s využitím grafové reprezentace ». Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2014. http://www.nusl.cz/ntk/nusl-220863.

Texte intégral

Résumé :

This thesis deals with the application of graph theory in image segmentation. There are specifically presented method utilizing graph cuts and extensions of this method. In the first chapter thera are initially explained basics of graph theory that are essential for understanding of the presented method. It is described in the second chapter, including its extensions that use shape priors. In the third chapter there is presented solution which is used for vertebrae lesion segmentation in the CT data sets. Final function is implemented into the program but it can be used also separately. Success rate is described using sensitivity and specificity in the last chapter, there are also examples of results.

Styles APA, Harvard, Vancouver, ISO, etc.

24

Martin, Matthieu. « Reconstruction 3D de données échographiques du cerveau du prématuré et segmentation des ventricules cérébraux et thalami par apprentissage supervisé ». Thesis, Lyon, 2019. http://www.theses.fr/2019LYSEI118.

Texte intégral

Résumé :

Environ 15 millions d’enfants naissent prématurément chaque année dans le monde. Ces patients peuvent présenter des anomalies du développement cérébral qui peuvent causer des troubles du neuro-développement : paralysie cérébrale, surdité, cécité, retard du développement intellectuel, … Des études ont montrées que la quantification du volume des structures cérébrales est un bon indicateur qui permet de réduire ces risques et de les pronostiquer pour orienter les patients dans des parcours de soins adaptés pendant l’enfance. Cette thèse a pour objectif de montrer que l’échographie 3D pourrait être une alternative à l’IRM qui permettrait de quantifier le volume des structures cérébrales chez 100 % des prématurés. Ce travail se focalise plus particulièrement sur la segmentation des ventricules latéraux (VL) et des Thalami, il apporte trois contributions principales : le développement d’un algorithme de création de données échographiques 3D à partir d’échographie transfontanellaire 2D du cerveau du prématuré, la segmentation des ventricules latéraux et des thalami dans un temps clinique et l’apprentissage par des réseaux de neurones convolutionnels (CNN) de la position anatomique des ventricules latéraux. En outre, nous avons créé plusieurs bases de données annotées en partenariat avec le CH d’Avignon. L’algorithme de création de données échographiques 3D a été validé in-vivo où une précision de 0.69 ± 0.14 mm a été obtenue sur le corps calleux. Les VL et les thalami ont été segmentés par apprentissage profond avec l’architecture V-net. Les segmentations ont été réalisées en quelques secondes par ce CNN et des Dice respectifs de 0.828 ± 0.044 et de 0.891 ± 0.016 ont été obtenus. L’apprentissage de la position anatomique des VL a été réalisée via un CPPN (Compositional Pattern Producing Network), elle a permis d’améliorer significativement la précision de V-net lorsqu’il était composé de peu de couches, faisant passer le Dice de 0.524 ± 0.076 à 0.724 ± 0.107 dans le cas d’un réseau V-net à 7 couches. Cette thèse montre qu’il est possible de segmenter automatiquement, avec précision et dans un temps clinique, des structures cérébrales de l’enfant prématuré dans des données échographiques 3D. Cela montre qu’une échographie 3D de haute qualité pourrait être utilisée en routine clinique pour quantifier le volume des structures cérébrales et ouvre la voie aux études d’évaluation de son bénéfice pour les patients
About 15 million children are born prematurely each year worldwide. These patients are likely to suffer from brain abnormalities that can cause neurodevelopmental disorders: cerebral palsy, deafness, blindness, intellectual development delay, … Studies have shown that the volume of brain structures is a good indicator which enables to reduce and predict these risks in order to guide patients through appropriate care pathways during childhood. This thesis aims to show that 3D ultrasound could be an alternative to MRI that would enable to quantify the volume of brain structures in all premature infants. This work focuses more particularly on the segmentation of the lateral ventricles (VL) and thalami. Its four main contributions are: the development of an algorithm which enables to create 3D ultrasound data from 2D transfontanellar ultrasound of the premature brain, the segmentation of thigh quality he lateral ventricles and thalami in clinical time and the learning by a convolutional neural networks (CNN) of the anatomical position of the lateral ventricles. In addition, we have created several annotated databases in partnership with the CH of Avignon. Our reconstruction algorithm was used to reconstruct 25 high-quality ultrasound volumes. It was validated in-vivo where an accuracy 0.69 ± 0.14 mm was obtained on the corpus callosum. The best segmentation results were obtained with the V-net, a 3D CNN, which segmented the CVS and the thalami with respective Dice of 0.828± 0.044 and 0.891±0.016 in a few seconds. Learning the anatomical position of the CVS was achieved by integrating a CPPN (Compositional Pattern Producing Network) into the CNNs. It significantly improved the accuracy of CNNs when they had few layers. For example, in the case of the 7-layer V-net network, the Dice has increased from 0.524± 0.076 to 0.724±0.107. This thesis shows that it is possible to automatically segment brain structures of the premature infant into 3D ultrasound data with precision and in a clinical time. This proves that high quality 3D ultrasound could be used in clinical routine to quantify the volume of brain structures and paves the way for studies to evaluate its benefit to patients

Styles APA, Harvard, Vancouver, ISO, etc.

25

Eltayef, Khalid Ahmad A. « Segmentation and lesion detection in dermoscopic images ». Thesis, Brunel University, 2017. http://bura.brunel.ac.uk/handle/2438/16211.

Texte intégral

Résumé :

Malignant melanoma is one of the most fatal forms of skin cancer. It has also become increasingly common, especially among white-skinned people exposed to the sun. Early detection of melanoma is essential to raise survival rates, since its detection at an early stage can be helpful and curable. Working out the dermoscopic clinical features (pigment network and lesion borders) of melanoma is a vital step for dermatologists, who require an accurate method of reaching the correct clinical diagnosis, and ensure the right area receives the correct treatment. These structures are considered one of the main keys that refer to melanoma or non-melanoma disease. However, determining these clinical features can be a time-consuming, subjective (even for trained clinicians) and challenging task for several reasons: lesions vary considerably in size and colour, low contrast between an affected area and the surrounding healthy skin, especially in early stages, and the presence of several elements such as hair, reflections, oils and air bubbles on almost all images. This thesis aims to provide an accurate, robust and reliable automated dermoscopy image analysis technique, to facilitate the early detection of malignant melanoma disease. In particular, four innovative methods are proposed for region segmentation and classification, including two for pigmented region segmentation, one for pigment network detection, and one for lesion classification. In terms of boundary delineation, four pre-processing operations, including Gabor filter, image sharpening, Sobel filter and image inpainting methods are integrated in the segmentation approach to delete unwanted objects (noise), and enhance the appearance of the lesion boundaries in the image. The lesion border segmentation is performed using two alternative approaches. The Fuzzy C-means and the Markov Random Field approaches detect the lesion boundary by repeating the labeling of pixels in all clusters, as a first method. Whereas, the Particle Swarm Optimization with the Markov Random Field method achieves greater accuracy for the same aim by combining them in the second method to perform a local search and reassign all image pixels to its cluster properly. With respect to the pigment network detection, the aforementioned pre-processing method is applied, in order to remove most of the hair while keeping the image information and increase the visibility of the pigment network structures. Therefore, a Gabor filter with connected component analysis are used to detect the pigment network lines, before several features are extracted and fed to the Artificial Neural Network as a classifier algorithm. In the lesion classification approach, the K-means is applied to the segmented lesion to separate it into homogeneous clusters, where important features are extracted; then, an Artificial Neural Network with Radial Basis Functions is trained by representative features to classify the given lesion as melanoma or not. The strong experimental results of the lesion border segmentation methods including Fuzzy C-means with Markov Random Field and the combination between the Particle Swarm Optimization and Markov Random Field, achieved an average accuracy of 94.00% , 94.74% respectively. Whereas, the lesion classification stage by using extracted features form pigment network structures and segmented lesions achieved an average accuracy of 90.1% , 95.97% respectively. The results for the entire experiment were obtained using a public database PH2 comprising 200 images. The results were then compared with existing methods in the literature, which have demonstrated that our proposed approach is accurate, robust, and efficient in the segmentation of the lesion boundary, in addition to its classification.

Styles APA, Harvard, Vancouver, ISO, etc.

26

Pons, Rodríguez Gerard. « Computer-aided lesion detection and segmentation on breast ultrasound ». Doctoral thesis, Universitat de Girona, 2014. http://hdl.handle.net/10803/129453.

Texte intégral

Résumé :

This thesis deals with the detection, segmentation and classification of lesions on sonography. The contribution of the thesis is the development of a new Computer-Aided Diagnosis (CAD) framework capable of detecting, segmenting, and classifying breast abnormalities on sonography automatically. Firstly, an adaption of a generic object detection method, Deformable Part Models (DPM), to detect lesions in sonography is proposed. The method uses a machine learning technique to learn a model based on Histogram of Oriented Gradients (HOG). This method is also used to detect cancer lesions directly, simplifying the traditional cancer detection pipeline. Secondly, different initialization proposals by means of reducing the human interaction in a lesion segmentation algorithm based on Markov Random Field (MRF)-Maximum A Posteriori (MAP) framework is presented. Furthermore, an analysis of the influence of lesion type in the segmentation results is performed. Finally, the inclusion of elastography information in this segmentation framework is proposed, by means of modifying the algorithm to incorporate a bivariant formulation. The proposed methods in the different stages of the CAD framework are assessed using different datasets, and comparing the results with the most relevant methods in the state-of-the-art
Aquesta tesi es centra en la detecció, segmentació i classificació de lesions en imatges d'ecografia. La contribució d'aquesta tesi és el desenvolupament d'una nova eina de Diagnòstic Assistit per Ordinador (DAO) capaç de detectar, segmentar i classificar automàticament lesions en imatges d'ecografia de mama. Inicialment, s'ha proposat l'adaptació del mètode genèric de detecció d'objectes Deformable Part Models (DPM) per detectar lesions en imatges d'ecografia. Aquest mètode utilitza tècniques d'aprenentatge automàtic per generar un model basat en l'Histograma de Gradients Orientats. Aquest mètode també és utilitzat per detectar lesions malignes directament, simplificant així l'estratègia tradicional. A continuació, s'han realitzat diferents propostes d'inicialització en un mètode de segmentació basat en Markov Random Field (MRF)-Maximum A Posteriori (MAP) per tal de reduir la interacció amb l'usuari. Per avaluar aquesta proposta, s'ha realitzat un estudi sobre la influència del tipus de lesió en els resultats aconseguits. Finalment, s'ha proposat la inclusió d'elastografia en aquesta estratègia de segmentació. Els mètodes proposats per a cada etapa de l'eina DAO han estat avaluats fent servir bases de dades diferents, comparant els resultats obtinguts amb els resultats dels mètodes més importants de l'estat de l'art

Styles APA, Harvard, Vancouver, ISO, etc.

27

Maier, Oskar [Verfasser]. « Decision forest variants for brain lesion segmentation / Oskar Maier ». Lübeck : Zentrale Hochschulbibliothek Lübeck, 2017. http://d-nb.info/1137396520/34.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

28

Freire, Paulo Guilherme de Lima. « Segmentação de placas de esclerose múltipla em imagens de ressonância magnética usando modelos de mistura de distribuições t-Student e detecção de outliers ». Universidade Federal de São Carlos, 2016. https://repositorio.ufscar.br/handle/ufscar/7736.

Texte intégral

Résumé :

Submitted by Livia Mello (liviacmello@yahoo.com.br) on 2016-09-22T11:50:45Z No. of bitstreams: 1 DissPGLF.pdf: 2510277 bytes, checksum: ac0bc495fe911118e100ddeeaea3b4d9 (MD5)
Approved for entry into archive by Marina Freitas (marinapf@ufscar.br) on 2016-10-10T14:47:09Z (GMT) No. of bitstreams: 1 DissPGLF.pdf: 2510277 bytes, checksum: ac0bc495fe911118e100ddeeaea3b4d9 (MD5)
Approved for entry into archive by Marina Freitas (marinapf@ufscar.br) on 2016-10-10T14:47:16Z (GMT) No. of bitstreams: 1 DissPGLF.pdf: 2510277 bytes, checksum: ac0bc495fe911118e100ddeeaea3b4d9 (MD5)
Made available in DSpace on 2016-10-10T14:47:24Z (GMT). No. of bitstreams: 1 DissPGLF.pdf: 2510277 bytes, checksum: ac0bc495fe911118e100ddeeaea3b4d9 (MD5) Previous issue date: 2016-02-15
Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
Multiple Sclerosis (MS) is an inflammatory demyelinating (that is, with myelin loss) disease of the Central Nervous System (CNS). It is considered an autoimmune disease in which the immune system wrongly recognizes the myelin sheath of the CNS as an external element and attacks it, resulting in inflammation and scarring (sclerosis) of multiple areas of CNS’s white matter. Multi-contrast magnetic resonance imaging (MRI) has been successfully used in diagnosing and monitoring MS due to its excellent properties such as high resolution and good differentiation between soft tissues. Nowadays, the preferred method to segment MS lesions is the manual segmentation, which is done by specialists with limited help of a computer. However, this approach is tiresome, expensive and prone to error due to inter- and intra-variability between observers caused by low contrast on lesion edges. The challenge in automatic detection and segmentation of MS lesions in MR images is related to the variability of size and location of lesions, low contrast due to partial volume effect and the high range of forms that lesions can take depending on the stage of the disease. Recently, many researchers have turned their efforts into developing techniques that aim to accurately measure volumes of brain tissues and MS lesions, and also to reduce the amount of time spent on image analysis. In this context, this project proposes the study and development of an automatic computational technique based on an outlier detection approach, Student’s t-distribution finite mixture models and probabilistic atlases to segment and measure MS lesions volumes in MR images.
Esclerose Múltipla (EM) é uma doença inflamatória e desmielinizante (isto é, com perda de mielina) do sistema nervoso central (SNC). É considerada uma doença autoimune a qual o sistema imunológico reconhece erroneamente a bainha de mielina do SNC como um elemento externo e então a ataca, resultando em inflamação e formação de cicatrizes gliais (escleroses) em múltiplas áreas da substância branca do SNC. O imageamento multi- contraste por ressonância magnética (RM) tem sido usado clinicamente com muito sucesso para o diagnóstico e monitoramento da EM devido às suas excelentes propriedades como alta resolução e boa diferenciação de tecidos moles. Atualmente, o método utilizado para a segmentação de lesões de EM é o delineamento manual em imagens 3D de RM, o qual é realizado por especialistas com ajuda limitada do computador. Entretanto, tal procedimento é custoso e propenso à variabilidade inter e intraobservadores devido ao baixo contraste das bordas das lesões. A grande dificuldade na detecção e segmentação automáticas das le- sões de EM em imagens de RM está associada às suas variações no tamanho e localização, baixo contraste decorrente do efeito de volume parcial e o amplo espectro de aparências (realçadas, não-realçadas, black-holes) que elas podem ter, dependendo do estado evolutivo da doença. Atualmente, vários pesquisadores têm voltado seus esforços para o desenvol- vimento de técnicas que visam diminuir o tempo gasto na análise das imagens e medir, de maneira mais precisa, o volume dos tecidos cerebrais e das lesões de EM. Nesse contexto, este projeto propõe o estudo e o desenvolvimento de uma técnica computacional automá- tica, baseada na abordagem de detecção de outliers e usando modelos de misturas finitas de distribuições t-Student e atlas probabilísticos para a segmentação e medição do volume de lesões de EM em imagens de RM.
FAPESP: 2014/00019-6

Styles APA, Harvard, Vancouver, ISO, etc.

29

Li, Xiang. « Depth data improves non-melanoma skin lesion segmentation and diagnosis ». Thesis, University of Edinburgh, 2012. http://hdl.handle.net/1842/5867.

Texte intégral

Résumé :

Examining surface shape appearance by touching and observing a lesion from different points of view is a part of the clinical process for skin lesion diagnosis. Motivated by this, we hypothesise that surface shape embodies important information that serves to represent lesion identity and status. A new sensor, Dense Stereo Imaging System (DSIS) allows us to capture 1:1 aligned 3D surface data and 2D colour images simultaneously. This thesis investigates whether the extra surface shape appearance information, represented by features derived from the captured 3D data benefits skin lesion analysis, particularly on the tasks of segmentation and classification. In order to validate the contribution of 3D data to lesion identification, we compare the segmentations resulting from various combinations of images cues (e.g., colour, depth and texture) embedded in a region-based level set segmentation method. The experiments indicate that depth is complementary to colour. Adding the 3D information reduces the error rate from 7:8% to 6:6%. For the purpose of evaluating the segmentation results, we propose a novel ground truth estimation approach that incorporates a prior pattern analysis of a set of manual segmentations. The experiments on both synthetic and real data show that this method performs favourably compared to the state of the art approach STAPLE [1] on ground truth estimation. Finally, we explore the usefulness of 3D information to non-melanoma lesion diagnosis by tests on both human and computer based classifications of five lesion types. The results provide evidence for the benefit of the additional 3D information, i.e., adding the 3D-based features gives a significantly improved classification rate of 80:7% compared to only using colour features (75:3%). The three main contributions of the thesis are improved methods for lesion segmentation, non-melanoma lesion classification and lesion boundary ground-truth estimation.

Styles APA, Harvard, Vancouver, ISO, etc.

30

Kobold, Jonathan. « Deep Learning for lesion and thrombus segmentation from cerebral MRI ». Thesis, Université Paris-Saclay (ComUE), 2019. http://www.theses.fr/2019SACLE044.

Texte intégral

Résumé :

L'apprentissage profond est le meilleur ensemble de méthodes aumonde pour identifier des objets sur des images. L'accident vascu-laire cérébral est une maladie mortelle dont le traitement nécessitel'identification d'objets par imagerie médicale. Cela semble être unecombinaison évidente, mais il n'est pas anodin de joindre les deux.La segmentation de la lésion de l'IRM cérébrale a retenu l'attentiondes chercheurs, mais la segmentation du thrombus est encore inex-plorée. Ce travail montre que les architectures de réseau de neur-ones convolutionnels contemporaines ne peuvent pas identifier demanière fiable le thrombus sur l'IRM. En outre, il est démontrépourquoi ces modèles ne fonctionnent pas sur ce problème. Fort decette connaissance, une architecture de réseau neuronal récurrente aété développée, appelée logic-LSTM, capable de prendre en comptela manière dont les médecins identifient le thrombus. Cette ar-chitecture fournit non seulement la première identification fiablede thrombus, mais elle fournit également de nouvelles informationssur la conception des réseaux neuronaux. En particulier, les méthodesd'augmentation du champ récepteur sont enrichies d'une nouvelleoption sans paramètre. Enfin, le logic-LSTM améliore également lesrésultats de la segmentation des lésions en fournissant une segment-ation des lésions avec un niveau de performance humaine
Deep learning, the world's best set of methods for identifying ob-jects on images. Stroke, a deadly disease whose treatment requiresidentifying objects on medical imaging. Sounds like an obvious com-bination yet it is not trivial to marry the two. Segmenting the lesionfrom stroke MRI has had some attention in literature but thrombussegmentation is still uncharted area. This work shows that contem-porary convolutional neural network architectures cannot reliablyidentify the thrombus on stroke MRI. Also it is demonstrated whythese models don't work on this problem. With this knowledge arecurrent neural network architecture, the logic LSTM, is developedthat takes into account the way medical doctors identify the throm-bus. Not only this architecture provides the first reliable thrombusidentification, it also provides new insights to neural network design.Especially the methods for increasing the receptive field are enrichedwith a new parameter free option. And last but not least the logicLSTM also improves the results of lesion segmentation by providinga lesion segmentation with human level performance

Styles APA, Harvard, Vancouver, ISO, etc.

31

Kaur, Ravneet. « THRESHOLDING METHODS FOR LESION SEGMENTATION OF BASAL CELL CARCINOMA IN DERMOSCOPY IMAGES ». OpenSIUC, 2017. https://opensiuc.lib.siu.edu/dissertations/1367.

Texte intégral

Résumé :

Purpose: Automatic border detection is the first and most crucial step for lesion segmentation and can be very challenging, due to several lesion characteristics. There are many melanoma border-detecting algorithms that perform poorly on dermoscopy images of basal cell carcinoma (BCC), which is the most common skin cancer. One of the reasons for poor lesion detection performance is that there are very few algorithms that detect BCC borders, because they are difficult to segment, even for dermatologists. This difficulty is due to low contrast, variation in lesion color and artifacts inside/outside the lesion. Segmentation that has adequate lesion-feature capture, with acceptable tolerance, will facilitate accurate feature segmentation, thereby maximizing classification accuracy. Methods: The main objective of this research was to develop an effective BCC border detecting algorithm whose accuracy is better than the existing melanoma border detectors that have been applied to BCCs. Fifteen auto-thresholding techniques were implemented for BCC lesion segmentation; but, only five were selected for use in algorithm development. A novel technique was developed to automatically expand BCC lesion borders, to completely circumscribe the lesion. Two error metrics were used that better measure Type II (false-negative) errors: Relative XOR error and Lesion Capture Ratio (a novel error metric). Results: On training and test sets of 1023 and 119 images, respectively, based on two error metrics, five thresholding-based algorithms outperformed two state-of-the-art melanoma segmentation techniques, in segmenting BCCs. Five algorithms generated borders that appreciably better matched dermatologists’ hand-drawn borders which were used as the “gold standard.” Conclusion: The five developed algorithms, which included solutions for image-vignetting correction and border expansion, to achieve dermatologist-like borders, provided more inclusive and therefore, feature-preserving border detection, favoring better BCC classification accuracy, for future work.

Styles APA, Harvard, Vancouver, ISO, etc.

32

Dong, Xu. « Segmenting Skin Lesion Attributes in Dermoscopic Images Using Deep Learing Algorithm for Melanoma Detection ». Thesis, Virginia Tech, 2018. http://hdl.handle.net/10919/86883.

Texte intégral

Résumé :

Melanoma is the most deadly form of skin cancer worldwide, which causes the 75% of deaths related to skin cancer. National Cancer Institute estimated that 91,270 new case and 9,320 deaths are expected in 2018 caused by melanoma. Early detection of melanoma is the key for the treatment. The image technique to diagnose skin cancer is dermoscopy, which leads to improved diagnose accuracy compared to traditional ABCD criteria. But reading and examining dermoscopic images is a time-consuming and complex process. Therefore, computerized analysis methods of dermoscopic images have been developed to assist the visual interpretation of dermoscopic images. The automatic segmentation of skin lesion attributes is a key step in computerized analysis of dermoscopic images. The International Skin Imaging Collaboration (ISIC) hosted the 2018 Challenges to help the diagnosis of melanoma based on dermoscopic images. In this thesis, I develop a deep learning based approach to automatically segment the attributes from dermoscopic skin lesion images. The approach described in the thesis achieved the Jaccard index of 0.477 on the official test dataset, which ranked 5th place in the challenge.
Master of Science
Melanoma is the most deadly form of skin cancer worldwide, which causes the 75% of deaths related to skin cancer. Early detection of melanoma is the key for the treatment. The image technique to diagnose skin cancer is called dermoscopy. It has become increasingly conveniently to use dermoscopic device to image the skin in recent years. Dermoscopic lens are available in the market for individual customer. When coupling the dermoscopic lens with smartphones, people are be able to take dermoscopic images of their skin even at home. However, reading and examining dermoscopic images is a time-consuming and complex process. It requires specialists to examine the image, extract the features, and compare with criteria to make clinical diagnosis. The time-consuming image examination process becomes the bottleneck of fast diagnosis of melanoma. Therefore, computerized analysis methods of dermoscopic images have been developed to promote the melanoma diagnosis and to increase the survival rate and save lives eventually. The automatic segmentation of skin lesion attributes is a key step in computerized analysis of dermoscopic images. In this thesis, I developed a deep learning based approach to automatically segment the attributes from dermoscopic skin lesion images. The segmentation result from this approach won 5th place in a public competition. It has the potential to be utilized in clinic application in the future.

Styles APA, Harvard, Vancouver, ISO, etc.

33

Thieu, Quang Tung. « Segmentation by convex active contour models : application to skin lesion and medical images ». Paris 13, 2013. http://www.theses.fr/2013PA132063.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

34

Gonzalez, Ana Guadalupe Salazar. « Structure analysis and lesion detection from retinal fundus images ». Thesis, Brunel University, 2011. http://bura.brunel.ac.uk/handle/2438/6456.

Texte intégral

Résumé :

Ocular pathology is one of the main health problems worldwide. The number of people with retinopathy symptoms has increased considerably in recent years. Early adequate treatment has demonstrated to be effective to avoid the loss of the vision. The analysis of fundus images is a non intrusive option for periodical retinal screening. Different models designed for the analysis of retinal images are based on supervised methods, which require of hand labelled images and processing time as part of the training stage. On the other hand most of the methods have been designed under the basis of specific characteristics of the retinal images (e.g. field of view, resolution). This compromises its performance to a reduce group of retinal image with similar features. For these reasons an unsupervised model for the analysis of retinal image is required, a model that can work without human supervision or interaction. And that is able to perform on retinal images with different characteristics. In this research, we have worked on the development of this type of model. The system locates the eye structures (e.g. optic disc and blood vessels) as first step. Later, these structures are masked out from the retinal image in order to create a clear field to perform the lesion detection. We have selected the Graph Cut technique as a base to design the retinal structures segmentation methods. This selection allows incorporating prior knowledge to constraint the searching for the optimal segmentation. Different link weight assignments were formulated in order to attend the specific needs of the retinal structures (e.g. shape). This research project has put to work together the fields of image processing and ophthalmology to create a novel system that contribute significantly to the state of the art in medical image analysis. This new knowledge provides a new alternative to address the analysis of medical images and opens a new panorama for researchers exploring this research area.

Styles APA, Harvard, Vancouver, ISO, etc.

35

Raina, Kevin. « Machine Learning Methods for Brain Lesion Delineation ». Thesis, Université d'Ottawa / University of Ottawa, 2020. http://hdl.handle.net/10393/41156.

Texte intégral

Résumé :

Brain lesions are regions of abnormal or damaged tissue in the brain, commonly due to stroke, cancer or other disease. They are diagnosed primarily using neuroimaging, the most common modalities being Magnetic Resonance Imaging (MRI) or Computed Tomography (CT). Brain lesions have a high degree of variability in terms of location, size, intensity and form, which makes diagnosis challenging. Traditionally, radiologists diagnose lesions by inspecting neuroimages directly by eye; however, this is time-consuming and subjective. For these reasons, many automated methods have been developed for lesion delineation (segmentation), lesion identification and diagnosis. The goal of this thesis is to improve and develop automated methods for delineating brain lesions from multimodal MRI scans. First, we propose an improvement to existing segmentation methods by exploiting the bilateral quasi-symmetry of healthy brains, which breaks down when lesions are present. We augment our data using nonlinear registration of a neuroimage to a reflected version of itself, leading to an improvement in Dice coefficient of 13 percent. Second, we model lesion volume in brain image patches with a modified Poisson regression method. The model accurately identified the lesion image with the larger lesion volume for 86 percent of paired sample patches. Both of these projects were published in the proceedings of the BIOSTEC 2020 conference. In the last two chapters, we propose a confidence-based approach to measure segmentation uncertainty, and apply an unsupervised segmentation method based on mutual information.

Styles APA, Harvard, Vancouver, ISO, etc.

36

Gong, Hao. « Segmentation d'images couleurs et multispectrales de la peau ». Phd thesis, Université de Grenoble, 2013. http://tel.archives-ouvertes.fr/tel-00934789.

Texte intégral

Résumé :

La délimitation précise du contour des lésions pigmentées sur des images est une première étape importante pour le diagnostic assisté par ordinateur du mélanome. Cette thèse présente une nouvelle approche de la détection automatique du contour des lésions pigmentaires sur des images couleurs ou multispectrales de la peau. Nous présentons d'abord la notion de minimisation d'énergie par coupes de graphes en terme de Maxima A-Posteriori d'un champ de Markov. Après un rapide état de l'art, nous étudions l'influence des paramètres de l'algorithme sur les contours d'images couleurs. Dans ce cadre, nous proposons une fonction d'énergie basée sur des classifieurs performants (Machines à support de vecteurs et Forêts aléatoires) et sur un vecteur de caractéristiques calculé sur un voisinage local. Pour la segmentation de mélanomes, nous estimons une carte de concentration des chromophores de la peau, indices discriminants du mélanomes, à partir d'images couleurs ou multispectrales, et intégrons ces caractéristiques au vecteur. Enfin, nous détaillons le schéma global de la segmentation automatique de mélanomes, comportant une étape de sélection automatique des "graines" utiles à la coupure de graphes ainsi que la sélection des caractéristiques discriminantes. Cet outil est comparé favorablement aux méthodes classiques à base de coupure de graphes en terme de précision et de robustesse.

Styles APA, Harvard, Vancouver, ISO, etc.

37

Brosch, Tom. « Efficient deep learning of 3D structural brain MRIs for manifold learning and lesion segmentation with application to multiple sclerosis ». Thesis, University of British Columbia, 2016. http://hdl.handle.net/2429/58427.

Texte intégral

Résumé :

Deep learning methods have shown great success in many research areas such as object recognition, speech recognition, and natural language understanding, due to their ability to automatically learn a hierarchical set of features that is tuned to a given domain and robust to large variability. This motivates the use of deep learning for neurological applications, because the large variability in brain morphology and varying contrasts produced by different MRI scanners makes the automatic analysis of brain images challenging. However, 3D brain images pose unique challenges due to their complex content and high dimensionality relative to the typical number of images available, making optimization of deep networks and evaluation of extracted features difficult. In order to facilitate the training on large 3D volumes, we have developed a novel training method for deep networks that is optimized for speed and memory. Our method performs training of convolutional deep belief networks and convolutional neural networks in the frequency domain, which replaces the time-consuming calculation of convolutions with element-wise multiplications, while adding only a small number of Fourier transforms. We demonstrate the potential of deep learning for neurological image analysis using two applications. One is the development of a fully automatic multiple sclerosis (MS) lesion segmentation method based on a new type of convolutional neural network that consists of two interconnected pathways for feature extraction and lesion prediction. This allows for the automatic learning of features at different scales that are optimized for accuracy for any given combination of image types and segmentation task. Our network also uses a novel objective function that works well for segmenting underrepresented classes, such as MS lesions. The other application is the development of a statistical model of brain images that can automatically discover patterns of variability in brain morphology and lesion distribution. We propose building such a model using a deep belief network, a layered network whose parameters can be learned from training images. Our results show that this model can automatically discover the classic patterns of MS pathology, as well as more subtle ones, and that the parameters computed have strong relationships to MS clinical scores.
Applied Science, Faculty of
Electrical and Computer Engineering, Department of
Graduate

Styles APA, Harvard, Vancouver, ISO, etc.

38

Pescia, Daniel. « Segmentation des tumeurs du foie sur des images CT ». Phd thesis, Ecole Centrale Paris, 2011. http://tel.archives-ouvertes.fr/tel-00649030.

Texte intégral

Résumé :

Cette thèse porte sur la segmentation des tumeurs du foie sur des images tomodensitométriques. Ce sujet présente un intérêt certain pour le domaine médical puisque les médecins pourraient ainsi bénéficier d'une méthode reproductible et fiable pour segmenter de telles lésions. Une segmentation précise des tumeurs du foie permettrait en effet d'aider les médecins lors de l'évaluation des lésions (détection, localisation, quantification), du choix d'un traitement, et de sa planification. Les méthodes développées dans ce cadre doivent faire face à trois principales difficultés scientifiques: (i) la grande variabilité de l'apparence et de la forme des structures recherchées, (ii) leur ressemblance avec les régions environnantes et finalement (iii) la faiblesse du rapport signal sur bruit observé dans les images dans lesquelles on travaille. Ce problème est abordé dans une optique d'application clinique et est résolu en suivant une approche en deux temps commençant par le calcul d'une enveloppe du foie, avant de segmenter les tumeurs présentes à l'intérieur de cette enveloppe. Nous commençons par proposer une approche basée sur des atlas pour le calcul d'une enveloppe des foies pathologiques. Tout d'abord, un outil de traitement d'image a été développé pour calculer une enveloppe autour d'un masque binaire, afin d'essayer d'obtenir une enveloppe du foie à partir d'une estimation du parenchyme sain. Un nouvel atlas statistique a ensuite été introduit, puis utilise pour la segmentation à travers son recalage difféomorphique avec une image. La segmentation est finalement réalisée en combinant les coûts d'appariement des images avec des a priori spatiaux et d'apparence, le tout en suivant une approche multi échelle basée sur des MRFs. La deuxième étape de notre approche porte sur la segmentation des lésions continues dans ces enveloppes en combinant des techniques d'apprentissage par ordinateur avec de méthodes basées sur des graphes. Un espace d'attributs approprié est tout d'abord défini en considérant des descripteurs de textures déterminés à travers des filtres de diverses tailles et orientations. Des méthodes avancées d'apprentissage automatique sont ensuite utilisées pour déterminer les attributs pertinents, ainsi que l'hyperplan qui sépare les voxels tumoraux des voxels correspondant à des tissus sains dans cet espace d'attributs. Pour finir, la segmentation est réalisée en minimisant une énergie sous forme de MRF, laquelle combine les probabilités d'appartenance de chaque voxel à une classe, avec celles de ses voisins. Des résultats prometteurs montrent les potentiels de notre méthode.

Styles APA, Harvard, Vancouver, ISO, etc.

39

Moltz, Jan Hendrik [Verfasser], Horst Karl [Akademischer Betreuer] Hahn, Andreas [Akademischer Betreuer] Nüchter et Ginneken Bram [Akademischer Betreuer] van. « Lesion segmentation and tracking for CT-based chemotherapy monitoring / Jan Hendrik Moltz. Betreuer : Horst Karl Hahn. Gutachter : Horst Karl Hahn ; Andreas Nüchter ; Bram van Ginneken ». Bremen : IRC-Library, Information Resource Center der Jacobs University Bremen, 2013. http://d-nb.info/1087285054/34.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

40

Daviller, Clément. « Quantification de la perfusion myocardique en imagerie de perfusion par résonance magnétique : modèles et classification non-supervisée ». Thesis, Lyon, 2019. http://www.theses.fr/2019LYSE1208/document.

Texte intégral

Résumé :

Les maladies cardiovasculaires et en particulier les maladies coronariennes représentent la principale cause de mortalité mondiale avec 17,9 millions de décès en 2012. L’IRM cardiaque est un outil particulièrement intéressant pour la compréhension et l’évaluation des cardiopathies, notamment ischémiques. Son apport diagnostique est souvent majeur et elle apporte des informations non accessibles par d’autres modalités d’imagerie. Les travaux menés pendant cette thèse portent plus particulièrement sur l’examen dit de perfusion myocardique qui consiste à étudier la distribution d’un agent de contraste au sein du muscle cardiaque lors de son premier passage. En pratique clinique cet examen est souvent limité à la seule analyse visuelle du clinicien qui recherche un hyposignal lui permettant d’identifier l’artère coupable et d’en déduire le territoire impacté. Cependant, cette technique est relative et ne permet pas de quantifier le flux sanguin myocardique. Au cours de ces dernières années, un nombre croissant de techniques sont apparues pour permettre cette quantification et ce à toutes les étapes de traitement, depuis l’acquisition jusqu’à la mesure elle-même. Nous avons dans un premier temps établi un pipeline de traitement afin de combiner ces approches et de les évaluer à l’aide d’un fantôme numérique et à partir de données cliniques. Nous avons pu démontrer que l’approche Bayésienne permettait de quantifier la perfusion cardiaque et sa supériorité à évaluer le délai d’arrivé du bolus d’indicateur par rapport au modèle de Fermi. De plus l’approche Bayésienne apporte en supplément des informations intéressantes telles que la fonction de densité de probabilité de la mesure et l’incertitude sur la fonction résidu qui permettent de connaitre la fiabilité de la mesure effectuée notamment en observant la répartition de la fonction de densité de probabilité de la mesure. Enfin, nous avons proposé un algorithme de segmentation des lésions myocardiques, exploitant les dimensions spatiotemporelles des données de perfusion. Cette technique permet une segmentation objective et précise de la région hypoperfusée permettant une mesure du flux sanguin myocardique sur une zone de tissu dont le comportement est homogène et dont la mesure du signal moyen permet une augmentation du rapport contraste à bruit. Sur la cohorte de 30 patients, la variabilité des mesures du flux sanguin myocardique effectuées sur les voxels détectés par cette technique était significativement inférieure à celle des mesures effectuées sur les voxels des zones définies manuellement (différence moyenne=0.14, 95% CI [0.07, 0.2]) et de celles effectuées sur les voxels des zones définies à partir de la méthode bullseye (différence moyenne =0.25, 95% CI [0.17, 0.36])
Cardiovascular diseases and in particular coronary heart disease are the main cause of death worldwide with 17.9 million deaths in 2012. Cardiac MRI is a particularly interesting tool for understanding and evaluating heart disease, including ischemic heart disease. Its diagnostic contribution is often major and it provides information that is not accessible by other imaging modalities. The work carried out during this thesis focuses more specifically on the so-called myocardium perfusion test, which consists in studying the distribution of a contrast agent within the heart muscle during its first passage. In clinical practice, this examination is often limited to the clinician's visual analysis, allowing him to identify the culprit artery and deduce the impacted territory. However, this technique is relative and does not quantify myocardial blood flow. In recent years, an increasing number of techniques have emerged to enable this quantification at all stages of processing, from acquisition to the measurement itself. We first established a treatment pipeline to combine these approaches and evaluate them using a digital phantom and clinical data. We demonstrated that the Bayesian approach is able to quantify myocardium perfusion and its superiority in evaluating the arrival time of the indicator bolus compared to the Fermi model. In addition, the Bayesian approach provides additional interesting information such as the probability density function of the measurement and the uncertainty of the residual function, which makes it possible to know the reliability of the measurement carried out, in particular by observing the distribution of the probability density function of the measurement. Finally, we proposed an algorithm for segmentation of myocardial lesions, using the spatial and temporal dimensions of infusion data. This technique allows an objective and precise segmentation of the hypoperfused region allowing a measurement of myocardial blood flow over an area of tissue which behavior is homogeneous and which average signal measurement allows an increase in the contrast-to-noise ratio. In the cohort of 30 patients, the variability of myocardial blood flow measurements performed on voxels detected by this technique was significantly lower than that of measurements performed on voxels in manually defined areas (mean difference=0.14, 95% CI[0.07, 0.2]) and those performed on voxels in areas defined using the bullseye method (mean difference=0.25, 95% CI[0.17, 0.36])

Styles APA, Harvard, Vancouver, ISO, etc.

41

Moussallem, Mazen. « Optimisation de la délimitation automatique des tumeurs pulmonaires à partir de l'imagerie TEP/TDM pour les planifications dosimétriques des traitements par radiothérapie ». Phd thesis, Université Claude Bernard - Lyon I, 2011. http://tel.archives-ouvertes.fr/tel-00864905.

Texte intégral

Résumé :

L'un des aspects les plus critiques dans les planifications dosimétriques des traitements par radiothérapie est la délinéation des limites de la tumeur. Cette délinéation se fait généralement sur les images anatomiques de tomodensitométrie (TDM). Mais récemment, il est recommandé de faire cette délinéation pour les cancers broncho-pulmonaires non à petites cellules (CBNPC) sur les images fonctionnelles de Tomographie par Émission de Positon (TEP) pour prendre en compte les caractéristiques biologiques de la cible. Jusqu'à ce jour, aucune technique de segmentation ne s'est révélée satisfaisante pour les images TEP en application clinique. Une solution pour ce problème est proposée dans cette étude. Méthodes : Les optimisations de notre méthode ont consisté principalement à faire l'ajustement des seuils directement à partir des corps des patients au lieu de le faire à partir du fantôme. Résultats : Pour les lésions de grands axes supérieurs à 20 mm, notre technique de segmentation a montré une bonne estimation des mesures histologiques (la moyenne de différence de diamètre entre données mesurées et déterminées avec notre technique = +1,5 ± 8,4 %) et une estimation acceptable des mesures TDM. Pour les lésions de grands axes inférieurs ou égaux à 20 mm, cette méthode a montré un écart avec les mesures dérivées des données histologiques ou bien des données TDM. Conclusion : Cette nouvelle méthode d'ajustement montre une bonne précision pour la délimitation des lésions de grands axes compris entre 2 et 4,5 cm. Néanmoins, elle n'évalue pas correctement les lésions les plus petites, cela peut être dû à l'effet du volume partiel

Styles APA, Harvard, Vancouver, ISO, etc.

42

Chmelík, Jiří. « Metody detekce, segmentace a klasifikace obtížně definovatelných kostních nádorových lézí ve 3D CT datech ». Doctoral thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2020. http://www.nusl.cz/ntk/nusl-433066.

Texte intégral

Résumé :

The aim of this work was the development of algorithms for detection segmentation and classification of difficult to define bone metastatic cancerous lesions from spinal CT image data. For this purpose, the patient database was created and annotated by medical experts. Successively, three methods were proposed and developed; the first of them is based on the reworking and combination of methods developed during the preceding project phase, the second method is a fast variant based on the fuzzy k-means cluster analysis, the third method uses modern machine learning algorithms, specifically deep learning of convolutional neural networks. Further, an approach that elaborates the results by a subsequent random forest based meta-analysis of detected lesion candidates was proposed. The achieved results were objectively evaluated and compared with results achieved by algorithms published by other authors. The evaluation was done by two objective methodologies, technical voxel-based and clinical object-based ones. The achieved results were subsequently evaluated and discussed.

Styles APA, Harvard, Vancouver, ISO, etc.

43

Glaister, Jeffrey Luc. « Automatic segmentation of skin lesions from dermatological photographs ». Thesis, 2013. http://hdl.handle.net/10012/7718.

Texte intégral

Résumé :

Melanoma is the deadliest form of skin cancer if left untreated. Incidence rates of melanoma have been increasing, especially among young adults, but survival rates are high if detected early. Unfortunately, the time and costs required for dermatologists to screen all patients for melanoma are prohibitively expensive. There is a need for an automated system to assess a patient's risk of melanoma using photographs of their skin lesions. Dermatologists could use the system to aid their diagnosis without the need for special or expensive equipment. One challenge in implementing such a system is locating the skin lesion in the digital image. Most existing skin lesion segmentation algorithms are designed for images taken using a special instrument called the dermatoscope. The presence of illumination variation in digital images such as shadows complicates the task of finding the lesion. The goal of this research is to develop a framework to automatically correct and segment the skin lesion from an input photograph. The first part of the research is to model illumination variation using a proposed multi-stage illumination modeling algorithm and then using that model to correct the original photograph. Second, a set of representative texture distributions are learned from the corrected photograph and a texture distinctiveness metric is calculated for each distribution. Finally, a texture-based segmentation algorithm classifies regions in the photograph as normal skin or lesion based on the occurrence of representative texture distributions. The resulting segmentation can be used as an input to separate feature extraction and melanoma classification algorithms. The proposed segmentation framework is tested by comparing lesion segmentation results and melanoma classification results to results using other state-of-the-art algorithms. The proposed framework has better segmentation accuracy compared to all other tested algorithms. The segmentation results produced by the tested algorithms are used to train an existing classification algorithm to identify lesions as melanoma or non-melanoma. Using the proposed framework produces the highest classification accuracy and is tied for the highest sensitivity and specificity.

Styles APA, Harvard, Vancouver, ISO, etc.

44

Hsu, Yu-ting, et 徐于婷. « Image Segmentation of Lesions in Brain Magnetic Resonance Imaging ». Thesis, 2013. http://ndltd.ncl.edu.tw/handle/41786073121372140182.

Texte intégral

Résumé :

碩士
國立雲林科技大學
工業工程與管理研究所碩士班
101
MRI can provide information on pathological changes in brain tissue to the doctors for diagnosis and treatment. With the advancement of technology, clinical practice has integrated computer-aided measurement and diagnosis, and the cutting algorithm can be used to cut out the required focal area accurately, in order to effectively diagnose the focal area. This study used Active Contours using Level Sets (ACLS) to cut out the boundary of tumor and edema. Before the segmentation, the image preprocessing technique N3 was used for image non-homogeneity removal, and the influence of non-homogeneity removal on segmentation performance was discussed. The segmentation effect of ACLS algorithm was influenced by the parameter combinations in the algorithm. In this study, Grid Search was used to search for the optimum parameter combination, so as to discuss the influence of parameter optimization of ACLS on the segmentation performance. Therefore, there were four experimental combinations in this study: (1) without non-homogeneity removal without parameter optimization, (2) without non-homogeneity removal with parameter optimization, (3) with non-homogeneity removal without parameter optimization and (4) with non-homogeneity removal with parameter optimization. The four combinations were processed by ACLS algorithm, and then the Jaccard Similarity was used to measure the segmentation performance of the four combinations. The Analysis of Variance (ANOVA) was used to calculate whether various factors resulted in significance difference in image segmentation, and then the paired-samples t test was conducted to test the significance difference among various combinations. The result of ANOVA showed that in the tumor segmentation performance, the non-homogeneity removal results in significance difference in segmentation performance. There was no significance difference in the segmentation performance without parameter optimization, and the interaction between two factors did not reached significance difference. In the edema segmentation performance, there was no significance difference whether or not there were non-homogeneity removal and parameter optimization, and the interaction between two factors had not reached significance difference. The result of paired-sample t test found that for the segmentation of tumor area, the Jaccard Similarity average value of non-homogeneity removal and parameter optimization in test data set was 0.7899. The segmentation performance was the best and was significantly better than the other combinations. For the segmentation of edema, the Jaccard Similarity average value of non-homogeneity removal and parameter optimization in test data set was 0.7604. The segmentation performance was also the best and was significantly better than the other combinations.

Styles APA, Harvard, Vancouver, ISO, etc.

45

Vieira, Pedro Miguel. « Hierarchical classification of lesions in wireless capsule endoscopy exams ». Doctoral thesis, 2021. http://hdl.handle.net/1822/75508.

Texte intégral

Résumé :

Programa doutoral em Engenharia Biomédica
A cápsula endoscópica é um dispositivo médico que tem como como principal vantagem a possibilidade de visualizar todo o trato gastrointestinal. Este exame não invasivo é especialmente usado e vantajoso para o diagnóstico de patologias do intestino delgado, já que a endoscopia convencional é um exame invasivo que não possibilita a visualização deste órgão. Para analisar os exames de cápsula endoscópica o pessoal médico necessita de treino especializado, tendo sido provado que a quantidade massiva de imagens de cada exame pode levar à existência de erros médicos e uma propensão a que exista um subdiagnóstico de algumas patologias. Esta tese teve como objetivo o desenvolvimento de sistemas de deteção automática de diferentes tipos de lesões presentes no intestino delgado. Estes métodos envolveram o uso de algoritmos de segmentação baseados em métodos probabilísticos (nomeadamente o Expectation- Maximization), com a apresentação de um método de aceleração da convergência do algoritmo e do desenvolvimento de um novo método para melhorar as fronteiras de segmentação, baseado em Campos Aleatórios de Markov. Além disso, foram estudadas diferentes metodologias de classificação supervisionada, desde classificadores mais simples e classificadores ensemble para deteção de lesões individuais, e redes neuronais convolucionais e segmentação de instâncias para deteção e segmentação de multi-patologias. Com o apoio do Hospital de Braga, foi efetuado um estudo clínico com o método desenvolvido para deteção automática de angioectasias. Este trabalho teve como principal objetivo comparar a eficiência e performance deste método com a performance de diferentes médicos a analisar exames de cápsula endoscópica. Os diferentes métodos desenvolvidos demonstraram resultados superiores aos encontrados na bibliografia mais recente. É importante referir que o trabalho desenvolvido nesta tese permitiu uma melhor análise à necessidade de uma maior implantação de métodos de deteção de lesões em sistemas de cápsula endoscópica, tal como a necessidade de maiores e melhores estudos clínicos, tal como a disponibilização de melhores bases de dados públicas.
The wireless capsule endoscopy is a medical device with the main advantage of being able to visualize the whole gastrointestinal tract. This non-invasive exam is specially used for the diagnosis of small bowel pathologies, since the conventional endoscopy is not able to visualize this organ. To analyze these exams the medical staff need specialized training and it was recently proven that the massive quantity of images that are generated lead to medical errors and consequently the sub diagnosis of certain pathologies. In this thesis the main objective was to develop systems for automatic detection of different lesions present in the small bowel. These developments included the use of segmentation algorithms based on probabilistic methods (namely the Expectation-Maximization), with the presentation of an acceleration method and a new approach for improving the borders of the segmentation based on Markov Random Fields. Beyond that, several supervised classification strategies were studied, with the use of single-based classifiers and ensemble-based classifiers for detection of single lesions and convolutional neural networks, and instance segmentation for multipathology detection and segmentation. With the support of Hospital of Braga, a clinical studied was performed with the developed method for angioectasia detection. This work had the main purpose of comparing the efficiency and performance of the method with the performance of different physicians when analyzing wireless capsule endoscopy exams. The developed methods were tested in different applications and it was found that the performance was improved when compared to the most recent bibliography. It is important to state that all this work allowed to conclude that these systems need to have a greater implantation in the clinical practice. While there is a lot of advances in computer vision methods for lesion detection, there are still lacking better clinical studies and better and bigger public databases to improve the testing of the methodologies.
The author was funded by the grant SFRH/BD/92143/2013 from the Portuguese Foundation for Science and Technology (FCT), with funds from the European Social Fund (FSE), under the Human Capital Operational Programme (POCH) from Portugal 2020 Programme.

Styles APA, Harvard, Vancouver, ISO, etc.

46

Gentile, Giordano. « Facing the current challenges in multiple sclerosis lesions : from automated segmentation to assessing the role of inflammation in neurodegeneration ». Doctoral thesis, 2022. http://hdl.handle.net/2158/1265556.

Texte intégral

Résumé :

Multiple sclerosis (MS) is characterized by the concomitant presence of focal areas of inflammation (lesions) and diffuse damage and neurodegeneration (atrophy). Lesions identification on magnetic resonance imaging is a key biomarker in MS diagnosis. Further, lesions and brain atrophy quantification is an important step in monitoring disease progression and evaluating treatment efficacy. However, several challenges need to be faced when dealing with these two biomarkers. For what concerns lesions, although several tools have been developed during the last years, automated segmentation is still an open challenge and no satisfactory solution has yet been found. Nextly, recent evidences suggested the presence of inflammation and neurodegeneration from the early phase of MS. However, the dynamics of accumulation of lesions and brain atrophy is not completely understood. Here, we have faced the two MS challenges strictly related to lesions. We first dealt with the technical difficulties of MS automated lesion segmentation by developing a novel artificial intelligence pipeline, named BIANCA-MS. Afterwards, by using whole brain and voxel-wise analyses, we have investigated whether inflammation and neurodegeneration were two causally related processes or two separate pathological mechanisms. Our experiments highlighted how BIANCA-MS achieved significantly higher degree of similarity to the manual segmentation compared to other widely used tools. Further, the consistency and reproducibility of performances achieved across different datasets proved BIANCA-MS robustness and flexibility. These findings suggested that BIANCA-MS is a promising tool for accurate and robust MS automated lesions segmentation. When investigating the spatio-temporal relationship between inflammation and neurodegeneration, our analyses were indicative of a not causal relationship where lesion changes and brain atrophy developed simultaneously over time, thus suggesting that these are two partially independent mechanisms. Further, our results suggested also the presence of a causal relationship where lesion volume changes were related to subsequent faster atrophy. These findings highlighted how the relationship between inflammation and neurodegeneration is not restricted to a single direction but is more probably the sum of different models that are not mutually exclusive and could coexist at the same time. The results achieved here provided crucial insights on the inter-role between inflammation and neurodegeneration, which in turn will broaden our understandings of underlying disease mechanisms and will allow the development of more targeted therapeutic strategies.

Styles APA, Harvard, Vancouver, ISO, etc.

47

Zhang, Shu-Wei, et 張書瑋. « Level Set Method with Cell Structure and Graph Partition Prior for Segmentation of Sonographic Breast Lesions ». Thesis, 2007. http://ndltd.ncl.edu.tw/handle/69445629325251191059.

Texte intégral

Résumé :

碩士
國立臺灣大學
醫學工程學研究所
95
Automatic boundary extraction of multiple targets of interest in an ultrasound image can not only help clinicians find out most perceptible objects, but also save sonologists’ time for boundary delineation. Moreover, it is potentially helpful for the novice instruction and medical research. In this paper we propose a new method combining the level set method with the cell competition structure information and graph partition prior in ultrasound image segmentation. Because of the intrinsic properties in ultrasound images, such as low contrast, high noises, speckle, artifacts, tissue related textures and so on, it is difficult to identify the blurred boundaries or weak edges in ultrasound images. Since the cell competition algorithm can divide the ROI (Region of Interest) into several prominent components, which can be parts of the desired target, tissue structures, artifacts, and so on, we first apply it to capture the most likely visually perceived boundaries in ultrasound images. Then we regard the boundaries of the prominent components as shape prior knowledge and integrate it into the level set energy function. Next, we adjust the importance of the boundary information by a spatially variant band constructed from the second smallest eigenvector via the constrained normalized-Cut. The proposed method unifies the region-based, and boundary-based information as well as the shape prior in the level set energy function. The active contours are attracted by the visually perceived boundaries defined by the cell structures and the broken edges and weak edges of the cell structure are overcome by incorporating the second smallest eigenvector computed by the constrained normalized cut. The proposed algorithm has been validated on 472 breast sonograms which comprise 221 malignant and 251 benign cases. The result shows the proposed method can detect weak edges successfully in ultrasound images. Moreover, the boundaries derived by the proposed method are comparable to the manually delineated boundaries and robust in reproducibility.

Styles APA, Harvard, Vancouver, ISO, etc.

48

Weng, Ching-Jung, et 翁靖容. « Segmentation of white matter lesions in multispectral MR image using Independent Component Analysis and Support Vector Machine ». Thesis, 2016. http://ndltd.ncl.edu.tw/handle/w86qf4.

Texte intégral

Résumé :

碩士
國立陽明大學
生物醫學影像暨放射科學系
104
Magnetic resonance images (MRI) are used to quantify brain volume because of its excellent soft-tissue contrast and high spatial resolution. Volume changes in whole brain, gray/white matter and lesion can provide information for diagnosis or prognosis of various brain diseases. Currently, most software for brain MRI analysis only use T1 weighted image (T1WI). But when there are white matter lesions in Multiple sclerosis (MS) patients, it can’t be properly distinguished because of the similar signal intensity between lesion and white matter on TIWI. Compared to using single weighted image, multispectral MRI contain different image contrast which is useful for segmentation. The purpose of this study is to use Independent component analysis (ICA) and Support vector machine (SVM) to identify white matter lesion correctly using multispectral MRI. At first, synthetic MS images were analyzed including: registration, noise correction, uniformity correction and skull stripping. Secondly, SVM and ICA+SVM methods were used to analyze three groups of multispectral MR image. Thirdly, using sensitivity, positive predictive value (PPV) and Tanimoto index (TI) to evaluate the accuracy. Lastly, clinical MR images were analyzed. For synthetic MS images, the result of lesion classification by applying ICA+SVM method to analyze T1WI, T2WI and FLAIR images had the highest PPV. The sensitivity, PPV and TI for this technique were over 0.75/0.7/0.6. As for clinical MS data experiments, ICA+SVM method can identify more lesion than freesurfer which only use T1WI in the analysis.

Styles APA, Harvard, Vancouver, ISO, etc.

49

Jodas, Danilo Samuel. « Segmentation and classification of structures of the carotid and coronary arteries for image-based evaluation of atherosclerotic lesions ». Doctoral thesis, 2017. https://hdl.handle.net/10216/108560.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

50

Jodas, Danilo Samuel. « Segmentation and classification of structures of the carotid and coronary arteries for image-based evaluation of atherosclerotic lesions ». Tese, 2017. https://hdl.handle.net/10216/108560.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Thèses sur le sujet « Lesions segmentation »

Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres