Dissertations / Theses on the topic 'Biomedical images'
To see the other types of publications on this topic, follow the link: Biomedical images.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Biomedical images.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Pham, Hong Nhung. "Graph-based registration for biomedical images." Thesis, Poitiers, 2019. http://www.theses.fr/2019POIT2258/document.
Full textAbstract:
Le contexte de cette thèse est le recalage d'images endomicroscopiques. Le microendoscope multiphotonique fournit différentes trajectoires de balayage que nous considérons dans ce travail. Nous proposons d'abord une méthode de recalage non rigide dont l'estimation du mouvement est transformée en un problème d'appariement d'attributs dans le cadre des Log-Demons et d'ondelettes sur graphes. Nous étudions les ondelettes de graphe spectral (SGW) pour capturer les formes des images, en effet, la représentation des données sur les graphes est plus adaptée aux données avec des structures complexes. Nos expériences sur des images endomicroscopiques montrent que cette méthode est supérieure aux techniques de recalage d'images non rigides existantes. Nous proposons ensuite une nouvelle stratégie de recalage d'images pour les images endomicroscopiques acquises sur des grilles irrégulières. La transformée en ondelettes sur graphe est flexible et peut être appliquée à différents types de données, quelles que soient la densité de points et la complexité de la structure de données. Nous montrons également comment le cadre des Log-Demons peut être adapté à l'optimisation de la fonction objective définie pour les images acquises avec un échantillonnage irrégulierThe context of this thesis is the image registration for endomicroscopic images. Multiphoton microendoscope provides different scanning trajectories which are considered in this work. First we propose a nonrigid registration method whose motion estimation is cast into a feature matching problem under the Log-Demons framework using Graph Wavelets. We investigate the Spectral Graph Wavelets (SGWs) to capture the shape feature of the images. The data representation on graphs is more adapted to data with complex structures. Our experiments on endomicroscopic images show that this method outperforms the existing nonrigid image registration techniques. We then propose a novel image registration strategy for endomicroscopic images acquired on irregular grids. The Graph Wavelet transform is flexible to apply on different types of data regardless of the data point densities and how complex the data structure is. We also show how the Log-Demons framework can be adapted to the optimization of the objective function defined for images with an irregular sampling
2
RUNDO, LEONARDO. "Computer-Assisted Analysis of Biomedical Images." Doctoral thesis, Università degli Studi di Milano-Bicocca, 2019. http://hdl.handle.net/10281/241343.
Full textAbstract:
Oggigiorno, la mole di dati biomedicali eterogenei è in continua crescita grazie alle nuove tecniche di sensing e alle tecnologie ad high-throughput. Relativamente all'analisi di immagini biomedicali, i progressi relativi alle modalità di acquisizione di immagini agli esperimenti di imaging ad high-throughput stanno creando nuove sfide. Questo ingente complesso di informazioni può spesso sopraffare le capacità analitiche sia dei medici nei loro processi decisionali sia dei biologi nell'investigazione di sistemi biochimici complessi. In particolare, i metodi di imaging quantitativo forniscono informazioni scientificamente rilevanti per la predizione, la prognosi o la valutazione della risposta al trattamento, prendendo in considerazione anche approcci di radiomica. Pertanto, l'analisi computazionale di immagini medicali e biologiche svolge un ruolo chiave in applicazioni di radiologia e di laboratorio. A tal proposito, framework basati su tecniche avanzate di Machine Learning e Computational Intelligence permettono di migliorare significativamente i tradizionali approcci tradizionali di Image Processing e Pattern Recognition. Tuttavia, le tecniche convenzionali di Intelligenza Artificiale devono essere propriamente adattate alle sfide uniche imposte dai dati di imaging biomedicale.
La presente tesi mira a proporre innovativi metodi assistiti da calcolatore per l'analisi di immagini biomedicali, da utilizzare anche come strumento per lo sviluppo di Sistemi di Supporto alle Decisioni Cliniche, tenendo sempre in considerazione la fattibilità delle soluzioni sviluppate. In primo luogo, sono descritti gli algoritmi classici di Image Processing realizzati, focalizzandosi sugli approcci basati su regioni e sulla morfologia matematica. Dopodiché, si introducono le tecniche di Pattern Recognition, applicando il clustering fuzzy non supervisionato e i modelli basati su grafi (i.e., Random Walker e Automi Cellulari) per l'elaborazione di dati multispettrali e multimodali di imaging medicale. In riferimento ai metodi di Computational Intelligence, viene presentato un innovativo framework evolutivo basato sugli Algoritmi Genetici per il miglioramento e la segmentazione di immagini medicali. Inoltre, è discussa la co-registrazione di immagini multimodali utilizzando Particle Swarm Optimization. Infine, si investigano le Deep Neural Network: (i) le capacità di generalizzazione delle Convolutional Neural Network nell'ambito della segmentazione di immagini medicali provenienti da studi multi-istituzionali vengono affrontate mediante la progettazione di un'architettura che integra blocchi di ricalibrazione delle feature, e (ii) la generazione di immagini medicali realistiche basata sulle Generative Adversarial Network è applicata per scopi di data augmentation.
In conclusione, il fine ultimo di tali studi è quello di ottenere conoscenza clinicamente e biologicamente utile che possa guidare le diagnosi e le terapie differenziali, conducendo verso l'integrazione di dati biomedicali per la medicina personalizzata. Difatti, i metodi assistiti da calcolatore per l'analisi delle immagini biomedicali sono vantaggiosi sia per la definizione di biomarcatori basati sull'imaging sia per la medicina e biologia quantitativa.Nowadays, the amount of heterogeneous biomedical data is increasing more and more thanks to novel sensing techniques and high-throughput technologies. In reference to biomedical image analysis, the advances in image acquisition modalities and high-throughput imaging experiments are creating new challenges. This huge information ensemble could overwhelm the analytic capabilities needed by physicians in their daily decision-making tasks as well as by biologists investigating complex biochemical systems. In particular, quantitative imaging methods convey scientifically and clinically relevant information in prediction, prognosis or treatment response assessment, by also considering radiomics approaches. Therefore, the computational analysis of medical and biological images plays a key role in radiology and laboratory applications. In this regard, frameworks based on advanced Machine Learning and Computational Intelligence can significantly improve traditional Image Processing and Pattern Recognition approaches. However, conventional Artificial Intelligence techniques must be tailored to address the unique challenges concerning biomedical imaging data. This thesis aims at proposing novel and advanced computer-assisted methods for biomedical image analysis, also as an instrument in the development of Clinical Decision Support Systems, by always keeping in mind the clinical feasibility of the developed solutions. The devised classical Image Processing algorithms, with particular interest to region-based and morphological approaches in biomedical image segmentation, are first described. Afterwards, Pattern Recognition techniques are introduced, applying unsupervised fuzzy clustering and graph-based models (i.e., Random Walker and Cellular Automata) to multispectral and multimodal medical imaging data processing. Taking into account Computational Intelligence, an evolutionary framework based on Genetic Algorithms for medical image enhancement and segmentation is presented. Moreover, multimodal image co-registration using Particle Swarm Optimization is discussed. Finally, Deep Neural Networks are investigated: (i) the generalization abilities of Convolutional Neural Networks in medical image segmentation for multi-institutional datasets are addressed by conceiving an architecture that integrates adaptive feature recalibration blocks, and (ii) the generation of realistic medical images based on Generative Adversarial Networks is applied to data augmentation purposes. In conclusion, the ultimate goal of these research studies is to gain clinically and biologically useful insights that can guide differential diagnosis and therapies, leading towards biomedical data integration for personalized medicine. As a matter of fact, the proposed computer-assisted bioimage analysis methods can be beneficial for the definition of imaging biomarkers, as well as for quantitative medicine and biology.
3
Cai, Hongmin. "Quality enhancement and segmentation for biomedical images." Click to view the E-thesis via HKUTO, 2007. http://sunzi.lib.hku.hk/hkuto/record/B39380130.
Full text
4
Cai, Hongmin, and 蔡宏民. "Quality enhancement and segmentation for biomedical images." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 2007. http://hub.hku.hk/bib/B39380130.
Full text
5
Lashin, Nabil Aly Mohamed Aly. "Restoration methods for biomedical images in confocal microscopy." [S.l.] : [s.n.], 2005. http://deposit.ddb.de/cgi-bin/dokserv?idn=975678167.
Full text
6
Aguilar, Chongtay María del Rocío. "Model based system for automated analysis of biomedical images." Thesis, University of Edinburgh, 1997. http://hdl.handle.net/1842/30059.
Full textAbstract:
This thesis is concerned with developing a probabilistic formulation of model-based vision using generalised flexible template models. It includes the design and implementation of a system which extends flexible template models to include grey level information in the object representation for image interpretation. This system was designed to deal with microscope images where the different stain and illumination conditions during the image acquisition process produce a strong correlation between density profile and geometric shape. This approach is based on statistical knowledge from a training set of examples. The variability of the shape-grey level relationships is characterised by applying principal component analysis to the shape-grey level vector extracted from the training set. The main modes of variation of each object class are encoded with a generic object formulation constrained by the training set limits. This formulation adapts to the diversity and irregularities of shape and view during the object recognition process. The modes of variation are used to generate new object instances for the matching process of new image data. A genetic algorithm method is used to find the best possible explanation for a candidate of a given model, based on the probability distribution of all possible matches. This approach is demonstrated by its application to microscope images of brain cells. It provides the means to obtain information such as brain cells density and distribution. This information could be useful in the understanding of the development and properties of some Central Nervous System (CNS) related diseases, such as in studies on the effects of HIV in CNS where neuronal loss is expected. The performance of the SGmodel system was compared with manual neuron counts from domain experts. The results show no significant difference between SGmodel and manual neuron estimates. The observation of bigger differences between the counts of the domain experts underlines the automated approach importance to perform an objective analysis.
7
Stanier, Jeffrey. "Segmentation and editing of 3-dimensional medical images." Thesis, University of Ottawa (Canada), 1994. http://hdl.handle.net/10393/10031.
Full textAbstract:
Neuroradiologists rely on scanned images of the human brain to diagnose many pathologies. The images, even those collected in 3-dimensions, are typically displayed as a 2-dimensional collage of slices and much of the intrinsic 3-D structure of the data is lost. Image Atlases are commonly used to delineate and label Volumes Of Interest (VOIs) in 3-dimensional, slice-type, medical data sets. They can serve many purposes: to highlight important regions, to quantify the size and shape of structures in the images, to define a surface for 3-D rendering and to help in navigation through a series of images. To perform these functions, an individual atlas is required for each data set. The purpose of this thesis is to develop a link between the volume data and the individual atlas associated with each set of images. An automatic method of building an individual atlas from the volume data is proposed. The method uses a data-driven, bottom-up segmentation to produce a primitive atlas followed by a knowledge-driven, top-down merging and labelling stage to refine the primitive atlas into an individual atlas. The system was implemented in software using an object-oriented approach which allowed for a high quality user interface and a flexible and efficient implementation of the concepts of an atlas and a VOI. Tests were performed to judge the quality of the segmentations and of the atlas labellings. The results prove that the individual atlases created using the proposed method are sufficiently accurate to aid in visualizing 3-D structures in medical data sets and to quantify the sizes of these structures.
8
Stinson, Eric. "Distortion correction for diffusion weighted magnetic resonance images." Thesis, McGill University, 2009. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=32587.
Full textAbstract:
Diffusion magnetic resonance imaging (MRI) is useful for studying the diseased, dysfunctional, and healthy human brain. Unfortunately, this technique is susceptible to geometric distortions that decrease the accuracy and value of the data. A distortion correction algorithm must be used to remedy these issues during post-processing. The purpose of this thesis is to develop, implement, and test a distortion correction method for diffusion weighted MRI. A distortion correction algorithm was designed and implemented and then tested on simulated and real human brain datasets. The algorithm was found to work well for simulated datasets with b-values up to and including b=2000 s/(mm*mm). Furthermore, the cause of distortion correction failures were investigated. Failures are believed to be due to a combination of reduced signal to noise ratio (SNR) and increased contrast differences in datasets with higher b-values.L'imagerie par résonance magnétique (IRM) de diffusion est utile dans l'étude du cerveau humain, tant en santé que dysfonctionnel ou atteint de maladie. Malheureusement, cette technique est susceptible à des distortions géometriques qui diminuent la précision et la valeur des données. Un algorithme de correction de ces distortions doit être utilisé pendant le traitement des données. Le but de ce mémoire est de développer, d'implementer et de tester une méthode de correction des distortions pour l'IRM de diffusion. Un algorithme de correction des distortions fut developé et implémenté, puis évalué sur des ensembles de données cérébrales humaines simulées et réelles. L'algorithme fonctionne bien pour des données simulées avec des valeurs b jusqu'à b=2000 s/(mm*mm). La cause des échecs de la correction de distortion fut également étudiée. Les échecs sont attribués à une combinaison de la réduction du rapport signal sur bruit (SNR, pour signal-to-noise ratio) et de l'augmentation des différences de contraste, dans les ensembles de données avec des valeurs-b plus élevées.
9
Chen, Pei. "Volumetric reconstruction and real-time deformation modeling of biomedical images." Access to citation, abstract and download form provided by ProQuest Information and Learning Company; downloadable PDF file 6.09 Mb., p, 2006. http://gateway.proquest.com/openurl?url_ver=Z39.88-2004&res_dat=xri:pqdiss&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&rft_dat=xri:pqdiss:3220796.
Full textAbstract:
Thesis (Ph.D.)--University of Delaware, 2006.Principal faculty advisors: Kenneth E. Barner, Dept. of Electrical and Computer Engineering; and Karl V. Steiner, Delaware Biotechnology Institute. Includes bibliographical references.
10
Selagamsetty, Srinivasa Siddhartha. "Exploring a Methodology for Segmenting Biomedical Images using Deep Learning." University of Cincinnati / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1573812579683504.
Full text
11
Wang, Xiuying. "Automatic and elastic registration for biomedical images / Xiu Ying Wang." Thesis, The University of Sydney, 2005. https://hdl.handle.net/2123/28018.
Full text
12
Hatamzadeh-Tabrizi, Joubin. "Using active contours for segmentation of middle-ear images." Thesis, McGill University, 2003. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=79231.
Full textAbstract:
Image segmentation, or the extraction of the boundaries of objects, is one of the most important problems in computer vision and image processing. As a high-level technique for boundary identification, active contours are used extensively for segmentation purposes.Two different active contour approaches, i.e., parametric active contours and discrete dynamic contours, were used and compared for the segmentation of middle-ear images. We used histological and Magnetic Resonance Microscopy (MRM) image datasets for our experiments.
Parametric and discrete dynamic contours show similar boundary identification results for the histological and MRM datasets. Gradient, Gradient Vector Flow (GVF), and the gradient plus pressure were used as the external force. The gradient has the disadvantage of having a restricted capture range. Two solutions for improving the capture range, gradient vector flow and pressure force, were compared. Although GVF provides a good capture range, it sometimes wrongly identifies the low-contrast boundaries. It was also found that GVF may wrongly identify the boundaries of close neighbouring structures. As an alternative, pressure forces have shown promising results for histological and MRM middle-ear images. For the same initial contours, a larger number of iterations is required for the parametric contours to converge to the boundary than with the discrete dynamic contours, when the gradient is used as the external force. However, when using GVF and gradient plus pressure, parametric active contours require a smaller number of iterations for active contour convergence, compared with the discrete dynamic approach.
The use of open contours was demonstrated for shared boundaries and thin structures, in addition to the usual closed contours.
13
Goldenstein, Janet Helene. "Registration of musculoskeletal images for the analysis of bone structure." Diss., Search in ProQuest Dissertations & Theses. UC Only, 2009. http://gateway.proquest.com/openurl?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&res_dat=xri:pqdiss&rft_dat=xri:pqdiss:3390045.
Full textAbstract:
Thesis (Ph.D.)--University of California, San Francisco with the University of California, Berkeley, 2009.Source: Dissertation Abstracts International, Volume: 71-02, Section: B, page: . Advisers: Sharmila Majumdar; Thomas Link.
14
Srinivasan, Nirmala. "Cross-Correlation Of Biomedical Images Using Two Dimensional Discrete Hermite Functions." University of Akron / OhioLINK, 2012. http://rave.ohiolink.edu/etdc/view?acc_num=akron1341866987.
Full text
15
Eslava, Rios Javier. "Automatic melanoma detection in dermatological images." Thesis, California State University, Long Beach, 2015. http://pqdtopen.proquest.com/#viewpdf?dispub=1582857.
Full textAbstract:
Malignant melanoma is one of the most dangerous types of skin cancer. A very important aspect of this type of cancer is that, if detected early, it can be completely removed from the body. These characteristics make the research on automated melanoma detection systems a field with high potential. In this thesis, a system for automatic detection of melanoma is designed, developed and studied. The system is composed of five stages; image acquisition, illumination correction, lesion segmentation, feature extraction and classification. The techniques implemented in illumination correction are based in morphological operators and the Retinex algorithm. The four proposed methods for lesion segmentation include Otsu's method thresholding, GVF Snakes, and two novel methods based in Mean Shift clustering using color and texture information. The classification stage makes use of linear discriminant analysis and SVMs. In addition, a GUI tool that takes advantage of the mentioned techniques is created and presented.
16
Veeraragoo, Mahalingam. "Pattern recognition to detect fetal alchohol syndrome using stereo facial images." Master's thesis, University of Cape Town, 2010. http://hdl.handle.net/11427/3212.
Full textAbstract:
Fetal alcohol syndrome (FAS) is a condition which is caused by excessive consumption of alcohol by the mother during pregnancy. A FAS diagnosis depends on the presence of growth retardation, central nervous system and neurodevelopment abnormalities together with facial malformations. The main facial features which best distinguish children with and without FAS are smooth philtrum, thin upper lip and short palpebral fissures. Diagnosis of the facial phenotype associated with FAS can be done using methods such as direct facial anthropometry and photogrammetry. The project described here used information obtained from stereo facial images and applied facial shape analysis and pattern recognition to distinguish between children with FAS and control children. Other researches have reported on identifying FAS through the classification of 2D landmark coordinates and 3D landmark information in the form of Procrustes residuals. This project built on this previous work with the use of 3D information combined with texture as features for facial classification. Stereo facial images of children were used to obtain the 3D coordinates of those facial landmarks which play a role in defining the FAS facial phenotype. Two datasets were used: the first consisted of facial images of 34 children whose facial shapes had previously been analysed with respect to FAS. The second dataset consisted of a new set of images from 40 subjects. Elastic bunch graph matching was used on the frontal facial images of the study populaiii tion to obtain texture information, in the form of jets, around selected landmarks. Their 2D coordinates were also extracted during the process. Faces were classified using knearest neighbor (kNN), linear discriminant analysis (LDA) and support vector machine (SVM) classifiers. Principal component analysis was used for dimensionality reduction while classification accuracy was assessed using leave-one-out cross-validation. For dataset 1, using 2D coordinates together with texture information as features during classification produced a best classification accuracy of 72.7% with kNN, 75.8% with LDA and 78.8% with SVM. When the 2D coordinates were replaced by Procrustes residuals (which encode 3D facial shape information), the best classification accuracies were 69.7% with kNN, 81.8% with LDA and 78.6% with SVM. LDA produced the most consistent classification results. The classification accuracies for dataset 2 were lower than for dataset 1. The different conditions during data collection and the possible differences in the ethnic composition of the datasets were identified as likely causes for this decrease in classification accuracy.
17
Golding, Dan. "A comparison of methods for the registration of tractographic fibre images." Master's thesis, University of Cape Town, 2011. http://hdl.handle.net/11427/10536.
Full text
18
Chen, Ye. "Fuzzy Cognitive Maps: Learning Algorithms and Biomedical Applications." University of Cincinnati / OhioLINK, 2015. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1423581705.
Full text
19
Gauvin, Alain. "Geometrical distortion of magnetic resonance images." Thesis, McGill University, 1992. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=60675.
Full textAbstract:
The problem of geometrical distortion in MR images is addressed in the context of the applicability of stereotactic techniques. For this purpose, the distortion of phantom images is measured at various readout bandwidths and the spatial linearity is evaluated in view of the use of a stereotactic frame. The presence of a contribution to the overall distortion of non-linear magnetic gradients is shown from the data, although the distortion observed seems to be mostly attributable to the main field inhomogeneity. The specific problems of distortion of the fiducial markers due to bulk magnetic susceptibility effects is addressed. The occurrence of such effects is characterized with the help of imaging, and the role of the phenomenon on proper target localization is demonstrated. In addition, a method of bypassing the detrimental aspect of these effects is presented.Various distortion correction approaches are discussed, and their benefits and drawbacks are evaluated. In the light of this discussion, a recently reported correction method is then presented. This method allows the calculation of an image free from geometrical and intensity distortion from the combined effect of main field inhomogeneity, susceptibility effects and chemical shift.
20
Munechika, Stacy Mark 1961. "Applying multiresolution and graph-searching techniques for boundary detection in biomedical images." Thesis, The University of Arizona, 1989. http://hdl.handle.net/10150/277091.
Full textAbstract:
An edge-based segmentation scheme (i.e. boundary detector) for nuclear medicine images has been developed and consists of a multiresolutional Gaussian-based edge detector working in conjunction with a modified version of Nilsson's A* graph-search algorithm. A multiresolution technique of analyzing the edge-signature plot (edge gradient versus resolution scale) allows the edge detector to match an appropriately sized edge operator to the edge structure in order to measure the full extent of the edge and thus gain the best compromise between noise suppression and edge localization. The graph-search algorithm uses the output from the multiresolution edge detector as the primary component in a cost function which is then minimized to obtain the boundary path. The cost function can be adapted to include global information such as boundary curvature, shape, and similarity to prototype to help guide the boundary detection process in the absence of good edge information.
21
IACOMI, Marius Mihail. "Application of the chaotic map algorithm in the analysis of biomedical images." Doctoral thesis, Università degli Studi di Palermo, 2014. http://hdl.handle.net/10447/91293.
Full text
22
Tziraki, Maria. "The development of photorefractive holography through turbid media for application to biomedical imaging." Thesis, Imperial College London, 2000. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.341934.
Full text
23
Ozturk, Caglar. "METHOD FOR DETERMINATION OF KINEMATIC SENSOR POSITION AND ORIENTATION FROM MAGNETIC RESONANCE IMAGES." Cleveland State University / OhioLINK, 2013. http://rave.ohiolink.edu/etdc/view?acc_num=csu1377015511.
Full text
24
Majola, Khwezi. "Three-Dimensional Body Volume Measurement From Two-Dimensional Images: Towards A Smartphone Application." Master's thesis, Faculty of Health Sciences, 2021. http://hdl.handle.net/11427/32797.
Full textAbstract:
Obesity poses a public health threat worldwide and is associated with a higher mortality, increased likelihood of diabetes, and an increased risk of cancer. When treating obesity, regular monitoring of metrics such as body mass index (BMI) and waist circumference has been found to result in improved health outcomes for patients. Three-dimensional (3D) scanners provide a useful tool to provide body measurements based on 3D images in obesity management. However, such scanners are often inaccessible due to cost. A smartphone image-based method able to produce 3D images may provide a more accessible measuring tool. As a step towards developing such a smartphone application, this project developed a method for 3D reconstruction of body images from two-dimensional (2D) images, using a full body 3D Gaussian process morphable model (GPMM). Separate GPMMs were trained to learn the shape of female and male human bodies. Gaussian process regression of the three-dimensional (3D) GPMM models onto two-dimensional (2D) images is performed. Corresponding landmarks on the 3D shapes and in the 2D images are employed in reconstruction. Measurements of body volume, waist circumference and height are then performed to extract information that is useful in obesity management. Different model configurations (shape model with arms; modified shape model with arms; shape model without arms; marginalised shape model without arms; shape model with different landmarks) were used to ascertain the most promising approach for the reconstruction. Each reconstructed body was tested for accuracy using the surface-tosurface distance per vertex, modified Hausdorff distance, and assessment of the measurements. Tests were performed using data from the same dataset used to build the model and generalised data from a different dataset. In all test cases, the best performing approach used shape models without arms when considering surface distances. However, the surface-to-surface distances errors were larger than those seen in literature. For body measurements, the best performing models varied with different models performing best for different measurements. For the measurements, the errors were larger than the allowable errors and larger than those found in literature. Landmark positions were evaluated separately and found to be imprecise. There are a few sources that contribute towards the reconstruction errors. Possible sources of error include an inability to interpret pose and landmark position errors. The major recommendations for future work are to use a model that incorporates both shape and pose and to use automatic landmarking methods. Regarding a pathway to a smartphone app, camera parameter information should be considered to improve processing of the images and smartphone orientation information should be considered to correct for distortions due to a tilted phone.
25
Bolton, Frank. "Automated 3D reconstruction of Lodox Statscan images for forensic application." Master's thesis, University of Cape Town, 2011. http://hdl.handle.net/11427/10128.
Full textAbstract:
The main objectives of this project are to perform tomographic reconstruction with manually scanned projection data from a Lodox Statscan full body digital radiography system, and to produce tools to allow automated generation of information required to perform the tomographic reconstruction.
26
Lu, Hong. "Machine Learning Based Analysis of Coronary Stent Images in Intravascular Optical Coherence Tomography Pullbacks." Case Western Reserve University School of Graduate Studies / OhioLINK, 2015. http://rave.ohiolink.edu/etdc/view?acc_num=case1415548044.
Full text
27
Xie, Zhongliu. "Machine learning for efficient recognition of anatomical structures and abnormalities in biomedical images." Thesis, Imperial College London, 2016. http://hdl.handle.net/10044/1/44567.
Full textAbstract:
Three studies have been carried out to investigate new approaches to efficient image segmentation and anomaly detection. The first study investigates the use of deep learning in patch based segmentation. Current approaches to patch based segmentation use low level features such as the sum of squared differences between patches. We argue that better segmentation can be achieved by harnessing the power of deep neural networks. Currently these networks make extensive use of convolutional layers. However, we argue that in the context of patch based segmentation, convolutional layers have little advantage over the canonical artificial neural network architecture. This is because a patch is small, and does not need decomposition and thus will not benefit from convolution. Instead, we make use of the canonical architecture in which neurons only compute dot products, but also incorporate modern techniques of deep learning. The resulting classifier is much faster and less memory-hungry than convolution based networks. In a test application to the segmentation of hippocampus in human brain MR images, we significantly outperformed prior art with a median Dice score up to 90.98% at a near real-time speed (< 1s). The second study is an investigation into mouse phenotyping, and develops a high-throughput framework to detect morphological abnormality in mouse embryo micro-CT images. Existing work in this line is centred on, either the detection of phenotype-specific features or comparative analytics. The former approach lacks generality and the latter can often fail, for example, when the abnormality is not associated with severe volume variation. Both these approaches often require image segmentation as a pre-requisite, which is very challenging when applied to embryo phenotyping. A new approach to this problem in which non-rigid registration is combined with robust principal component analysis (RPCA), is proposed. The new framework is able to efficiently perform abnormality detection in a batch of images. It is sensitive to both volumetric and non-volumetric variations, and does not require image segmentation. In a validation study, it successfully distinguished the abnormal VSD and polydactyly phenotypes from the normal, respectively, at 85.19% and 88.89% specificities, with 100% sensitivity in both cases. The third study investigates the RPCA technique in more depth. RPCA is an extension of PCA that tolerates certain levels of data distortion during feature extraction, and is able to decompose images into regular and singular components. It has previously been applied to many computer vision problems (e.g. video surveillance), attaining excellent performance. However these applications commonly rest on a critical condition: in the majority of images being processed, there is a background with very little variation. By contrast in biomedical imaging there is significant natural variation across different images, resulting from inter-subject variability and physiological movements. Non-rigid registration can go some way towards reducing this variance, but cannot eliminate it entirely. To address this problem we propose a modified framework (RPCA-P) that is able to incorporate natural variation priors and adjust outlier tolerance locally, so that voxels associated with structures of higher variability are compensated with a higher tolerance in regularity estimation. An experimental study was applied to the same mouse embryo micro-CT data, and notably improved the detection specificity to 94.12% for the VSD and 90.97% for the polydactyly, while maintaining the sensitivity at 100%.
28
Li, Guannan. "Locality sensitive modelling approach for object detection, tracking and segmentation in biomedical images." Thesis, University of Warwick, 2016. http://wrap.warwick.ac.uk/81399/.
Full textAbstract:
Biomedical imaging techniques play an important role in visualisation of e.g., biological structures, tissues, diseases and medical conditions in cellular level. The techniques bring us enormous image datasets for studying biological processes, clinical diagnosis and medical analysis. Thanks to recent advances in computer technology and hardware, automatic analysis of biomedical images becomes more feasible and popular. Although computer scientists have made a great effort in developing advanced imaging processing algorithms, many problems regarding object analysis still remain unsolved due to the diversity of biomedical imaging. In this thesis, we focus on developing object analysis solutions for two entirely different biomedical image types: uorescence microscopy sequences and endometrial histology images. In uorescence microscopy, our task is to track massive uorescent spots with similar appearances and complicated motion pattern in noisy environments over hundreds of frames. In endometrial histology, we are challenged by detecting different types of cells with similar appearance and in terms of colour and morphology. The proposed solutions utilise several novel locality sensitive models which can extract spatial or/and temporal relational features of the objects, i.e., local neighbouring objects exhibiting certain structures or patterns, for overcoming the difficulties of object analysis in uorescence microscopy and endometrial histology.
29
Feilke, Martina [Verfasser], and Volker [Akademischer Betreuer] Schmid. "Estimation and model selection for dynamic biomedical images / Martina Feilke. Betreuer: Volker Schmid." München : Universitätsbibliothek der Ludwig-Maximilians-Universität, 2015. http://d-nb.info/1076243274/34.
Full text
30
Feilke, Martina Verfasser], and Volker [Akademischer Betreuer] [Schmid. "Estimation and model selection for dynamic biomedical images / Martina Feilke. Betreuer: Volker Schmid." München : Universitätsbibliothek der Ludwig-Maximilians-Universität, 2015. http://d-nb.info/1076243274/34.
Full text
31
Madaris, Aaron T. "Characterization of Peripheral Lung Lesions by Statistical Image Processing of Endobronchial Ultrasound Images." Wright State University / OhioLINK, 2016. http://rave.ohiolink.edu/etdc/view?acc_num=wright1485517151147533.
Full text
32
Narayanan, Priya Lakshmi. "Development of a tool for automatic segmentation of the cerebellum in MR images of children." Doctoral thesis, University of Cape Town, 2015. http://hdl.handle.net/11427/20262.
Full textAbstract:
The human cerebellar cortex is a highly foliated structure that supports both motor and complex cognitive functions in humans. Magnetic Resonance Imaging (MRI) is commonly used to explore structural alterations in patients with psychiatric and neurological diseases. The ability to detect regional structural differences in cerebellar lobules may provide valuable insights into disease biology, progression and response to treatment, but has been hampered by the lack of appropriate tools for performing automated structural cerebellar segmentation and morphometry. In this thesis, time intensive manual tracings by an expert neuroanatomist of 16 cerebellar regions on high-resolution T1-weighted MR images of 18 children aged 9-13 years were used to generate the Cape Town Pediatric Cerebellar Atlas (CAPCA18) in the age-appropriate National Institute of Health Pediatric Database (NIHPD) asymmetric template space. An automated pipeline was developed to process the MR images and generate lobule-wise segmentations, as well as a measure of the uncertainty of the label assignments. Validation in an independent group of children with ages similar to those of the children used in the construction of the atlas, yielded spatial overlaps with manual segmentations greater than 70% in all lobules, except lobules VIIb and X. Average spatial overlap of the whole cerebellar cortex was 86%, compared to 78% using the alternative Spatially Unbiased Infra-tentorial Template (SUIT), which was developed using adult images.
33
Dendere, Ronald. "Segmentation of candidate bacillus objects in images of Ziehl-Neelsen-stained sputum smears using deformable models." Master's thesis, University of Cape Town, 2009. http://hdl.handle.net/11427/3232.
Full textAbstract:
Includes abstract.Includes bibliographical references (leaves 83-88).
Automated microscopy for the detection of tuberculosis (TB) in sputum smears seeks to address the strain on technicians and to achieve faster diagnosis in order to cope with the rising number of TB cases. Image processing techniques provide a useful alternative to the conventional, manual analysis of sputum smears for diagnosis. In the project described here, the use of parametric and geometric deformable models was explored for segmentation of TB bacilli in images of Ziehl-Neelsen-stained sputum smears for automated TB diagnosis. The goal of segmentation is to produce candidate bacillus objects for input into a classifier.
34
Marcotte, Hope Ann 1964. "Expectation maximization methods for processing SPECT images." Thesis, The University of Arizona, 1993. http://hdl.handle.net/10150/278351.
Full textAbstract:
A method is developed for pre-processing projection images for a SPECT brain imaging system. The projection images are recorded by modular gamma cameras that exhibit noisy response before processing. The image acquisition process is modeled so that the mean of the detected gamma-ray emissions is a linear transformation of the actual flux. Two models for detection are examined, one based on independent Poisson distributions and the other based on a multivariate distribution. The Expectation Maximization (EM) algorithm is used to invert the forward model to obtain a Maximum Likelihood estimate of the flux. Simulations using uniform, Gaussian and point flux patterns demonstrated that EM processing recovered improved estimates of these patterns. Processing measured images yielded improved estimates, but also revealed that both forward models are incomplete.
35
Bakar, Majd. "An environment for the objective comparison of MRA and DSA images /." Thesis, McGill University, 1996. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=27484.
Full textAbstract:
This thesis describes an environment in which two angiographic methods, Digital Subtraction Angiography (DSA) and Magnetic Resonance Angiography (MRA), can be objectively compared and analyzed.Such an environment requires that both angiographic projections be displayed from the same view-point and with the same projection geometry. The two angiograms are displayed side by side and several points on the vascular structure are identified in both modalities. These points are used to estimate, using a Least Squares Minimization, the Homogeneous Transformation Matrix (HTM) characterizing the projection of the DSA image. The resulting HTM is used to generate a corresponding Maximum Intensity Projection (MIP) of the MRA dataset. The number and location of the required homologous point-pairs are determined empirically.
Other alternatives to MIP are presented as well, and their performance relative to DSA is discussed. Images from each modality are displayed stereoscopically to reflect the three dimensional nature of the vascular tree.
36
Lancashire, Martin John Richard. "The assessment of ureteric function using compressed images from fast-frame renography." Thesis, Imperial College London, 1996. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.321804.
Full text
37
Gedamu, Elias. "Automated quality control procedures for brain magnetic resonance images acquired in multi-centre clinical trials for multiple sclerosis." Thesis, McGill University, 2011. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=103558.
Full textAbstract:
Automated quality control procedures are critical for efficiently obtaining precise quantitative brain imaging-based metrics of in vivo brain pathology. This is especially important for multi-centre clinical trials of therapeutics for multiple sclerosis, in which MRI-derived brain pathology metrics may be used to quantify therapeutic efficacy. Currently, a large number of QC procedures have been developed for scanner maintenance with the idea that optimal scanner performance should produce MRIs with acceptable image quality and, thus, limit the effect of brain pathology measurement errors on quantitative analyses like therapeutic efficacy. Unfortunately these procedures may not be applicable to real subject MRI scans where non-ideal conditions like subject motion during an acquisition exist. The goal of this thesis is to provide an automated QC procedure for brain MRIs acquired in multi-centre clinical trials for multiple sclerosis where image quality is evaluated directly from the acquired MRI itself.Les procédures automatisées de contrôle de qualité (CQ) sont essentielles afin d'obtenir de manière efficace des mesures précises d'imagerie cérébrale fondées sur la pathologie du cerveau in vivo. Ceci est particulièrement important pour les essais cliniques multicentriques de produits thérapeutiques destinés aux maladies neurologiques, dont les mesures de pathologie cérébrale dérivées des IRMs peuvent être utilisées pour quantifier l'efficacité thérapeutique. Présentement, la littérature met l'accent sur les procédures de CQ pour l'entretien des scanners, en supposant que ce bon entretien du scanner d'IRM produirait une qualité d'image acceptable et, par conséquent, limiterait les erreurs de mesures sur les analyses quantitatives, comme l'efficacité thérapeutique. Malheureusement, ces procédures peuvent ne pas être applicables sur des scans de sujets réels où des conditions non-idéals seraient présents, comme le mouvement du sujet lors d'une prise. L'objectif de cette thèse est de fournir une procédure automatisée de CQ pour les IRM cérébrales acquises lors de plusieurs essais cliniques sur la sclérose en plaques, où la qualité de l'image est évaluée directement à partir de l'IRM elle-même. Cette procédure a été testée, validée et appliquée dans l'industrie.
38
Wasswa, William. "3D approximation of scapula bone shape from 2D X-ray images using landmark-constrained statistical shape model fitting." Master's thesis, University of Cape Town, 2016. http://hdl.handle.net/11427/23777.
Full textAbstract:
Two-dimensional X-ray imaging is the dominant imaging modality in low-resource countries despite the existence of three-dimensional (3D) imaging modalities. This is because fewer hospitals in low-resource countries can afford the 3D imaging systems as their acquisition and operation costs are higher. However, 3D images are desirable in a range of clinical applications, for example surgical planning. The aim of this research was to develop a tool for 3D approximation of scapula bone from 2D X-ray images using landmark-constrained statistical shape model fitting. First, X-ray stereophotogrammetry was used to reconstruct the 3D coordinates of points located on 2D X-ray images of the scapula, acquired from two perspectives. A suitable calibration frame was used to map the image coordinates to their corresponding 3D realworld coordinates. The 3D point localization yielded average errors of (0.14, 0.07, 0.04) mm in the X, Y and Z coordinates respectively, and an absolute reconstruction error of 0.19 mm. The second phase assessed the reproducibility of the scapula landmarks reported by Ohl et al. (2010) and Borotikar et al. (2015). Only three (the inferior angle, acromion and the coracoid process) of the eight reproducible landmarks considered were selected as these were identifiable from the two different perspectives required for X-ray stereophotogrammetry in this project. For the last phase, an approximation of a scapula was produced with the aid of a statistical shape model (SSM) built from a training dataset of 84 CT scapulae. This involved constraining an SSM to the 3D reconstructed coordinates of the selected reproducible landmarks from 2D X-ray images. Comparison of the approximate model with a CT-derived ground truth 3D segmented volume resulted in surface-to-surface average distances of 4.28 mm and 3.20 mm, using three and sixteen landmarks respectively. Hence, increasing the number of landmarks produces a posterior model that makes better predictions of patientspecific reconstructions. An average Euclidean distance of 1.35 mm was obtained between the three selected landmarks on the approximation and the corresponding landmarks on the CT image. Conversely, a Euclidean distance of 5.99 mm was obtained between the three selected landmarks on the original SSM and corresponding landmarks on the CT image. The Euclidean distances confirm that a posterior model moves closer to the CT image, hence it reduces the search space for a more exact patient-specific 3D reconstruction by other fitting algorithms.
39
Szilágyi, Anna Tünde. "Structural characterization of liver fibrosis in magnetic resonance images." Thesis, University of Oxford, 2014. http://ora.ox.ac.uk/objects/uuid:1860b1d9-2b10-409f-9220-e12b002a9e32.
Full textAbstract:
The overall clinical motivation of this thesis is to differentiate between the different stages of liver disease stratifying into: no disease, mild disease, and severe fibrosis using Magnetic Resonance Imaging (MRI). As a related aim, we seek to differentiate as much as possible pericellular and nonpericellular fibrosis. This latter is clinically important, but currently no method exists that is able to perform this. Quickly, we realised that these aims push low level image analysis beyond their current bounds and so a great deal of the thesis is dedicated to extending such techniques before they can be applied. To work on the most fundamental low level image analysis concepts and algorithms we choose one of the most recent developments, namely continuous intrinsic dimensionality (ciD), which allows the continuous classification of homogeneous patches from 1D structures to intrinsically 2D structures. We show that the current formalism has several fundamental limitations and we propose a number of developments to improve on these. We re-evaluated feature energy statistics that were originally proposed in ciD, and additionally we examined the confidence one may have in stateof- the-art methods to estimate the orientation of features. We show that new statistical methods are required for feature energy, and that orientation predictability is more important than correctness of the estimation. This evaluation led us to the monogenic signal local orientation. Analysis of feature or texture energy is also a main contribution of this thesis. Within this framework we propose the Riesz-weighted phase congruency model. This is able to detect internal texture structures but it is not capable of delineating boundaries. Nevertheless, it proves an appropriate basis for texture quantification. Finally, we show that in contrast to using the standard established Kovesi approach, the developed texture measure leads to good results on the suboptimal T1w MRI liver image staging images. We show that we are able to differentiate automatically between the separate disease scores and between pericellular and non-pericellular fibrosis.
40
Petre, Valentina. "Generating synthetic 3-D images of objects lit by speckle light, providing a test for 3-D reconstruction algorithms." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1997. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape11/PQDD_0002/MQ44033.pdf.
Full text
41
Watson, Jennifer Marie. "Examination of Diagnostic Features in Multiphoton Microscopy and Optical Coherence Tomography Images of Ovarian Tumorigenesis in a Mouse Model." Diss., The University of Arizona, 2013. http://hdl.handle.net/10150/293473.
Full textAbstract:
Ovarian cancer is a deadly disease owing to the non-specific symptoms and suspected rapid progression, leading to frequent late stage detection and poor prognosis. Medical imaging methods such as CT, MRI and ultrasound as well as serum testing for cancer markers have had extremely poor performance for early disease detection. Due to the poor performance of available screening methods, and the impracticality and ineffectiveness of taking tissue biopsies from the ovary, women at high risk for developing ovarian cancer are often advised to undergo prophylactic salpingo-oophorectomy. This surgery results in many side effects and is most often unnecessary since only a fraction of high risk women go on to develop ovarian cancer. Better understanding of the early development of ovarian cancer and characterization of morphological changes associated with early disease could lead to the development of an effective screening test for women at high risk. Optical imaging methods including optical coherence tomography (OCT) and multiphoton microscopy (MPM) are excellent tools for studying disease progression owing to the high resolution and depth sectioning capabilities. Further, these techniques are excellent for optical biopsy because they can image in situ non-destructively. In the studies described in this dissertation OCT and MPM are used to identify cellular and tissue morphological changes associated with early tumor development in a mouse model of ovarian cancer. This work is organized into three specific aims. The first aim is to use the images from the MPM phenomenon of second harmonic generation to quantitatively examine the morphological differences in collagen structure in normal mouse ovarian tissue and mouse ovarian tumors. The second aim is to examine the differences in endogenous two-photon excited fluorescence in normal mouse ovarian tissue and mouse ovarian tumors. The third and final aim is to identify changes in ovarian microstructure resulting from early disease development by imaging animals in vivo at three time points during a long-term survival study.
42
Evanoff, Michael Geoffrey 1964. "Automatic identification of chest orientation in digital radiographic images." Diss., The University of Arizona, 1998. http://hdl.handle.net/10150/282811.
Full textAbstract:
Radiology departments are implementing conversion from the use of hard copy film in favor of digital imaging. New digital acquisitions are increasing the efficacy of radiological imaging. The outputs of new modalities such as magnetic resonance (MR) and computed tomography (CT) are digital. They both involve gathering information that allows reconstructing cross sectional projections of internal structures and displaying them as digital images. Other technologies, e.g., computed radiography (CR), can provide digital radiographic data that replaces analog projection radiography. To date, the processed digital data is still transferred to film to provide a typical radiographic film in appearance. The film is presented to the doctor for diagnostic review. The research in this dissertation is concerned with making a film-less department. It specifically addresses problems in presenting CR images to the physician. The goal of this research is to create a computer recognition algorithm that will automatically recognize the orientation and discriminate between the lateral and posteroanterior view of digital chest radiographs image. The algorithm maintains 91.9% accuracy rate. The recognition takes .15 second per image.
43
Perring, Steve. "Clinical applications of the three dimensional (3D) analysis and visualisation of medical slice images." Thesis, University of Southampton, 1992. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.387074.
Full text
44
Su, Hai. "Nuclei/Cell Detection in Microscopic Skeletal Muscle Fiber Images and Histopathological Brain Tumor Images Using Sparse Optimizations." UKnowledge, 2014. http://uknowledge.uky.edu/cs_etds/24.
Full textAbstract:
Nuclei/Cell detection is usually a prerequisite procedure in many computer-aided biomedical image analysis tasks. In this thesis we propose two automatic nuclei/cell detection frameworks. One is for nuclei detection in skeletal muscle fiber images and the other is for brain tumor histopathological images.
For skeletal muscle fiber images, the major challenges include: i) shape and size variations of the nuclei, ii) overlapping nuclear clumps, and iii) a series of z-stack images with out-of-focus regions. We propose a novel automatic detection algorithm consisting of the following components: 1) The original z-stack images are first converted into one all-in-focus image. 2) A sufficient number of hypothetical ellipses are then generated for each nuclei contour. 3) Next, a set of representative training samples and discriminative features are selected by a two-stage sparse model. 4) A classifier is trained using the refined training data. 5) Final nuclei detection is obtained by mean-shift clustering based on inner distance. The proposed method was tested on a set of images containing over 1500 nuclei. The results outperform the current state-of-the-art approaches.
For brain tumor histopathological images, the major challenges are to handle significant variations in cell appearance and to split touching cells. The proposed novel automatic cell detection consists of: 1) Sparse reconstruction for splitting touching cells. 2) Adaptive dictionary learning for handling cell appearance variations. The proposed method was extensively tested on a data set with over 2000 cells. The result outperforms other state-of-the-art algorithms with F1 score = 0.96.
45
Prabhu, David. "Automated Plaque Characterization of Intravascular Optical Coherence Tomography (IVOCT) Images Using 3D Cryo-image/Histology Validation." Case Western Reserve University School of Graduate Studies / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=case1556293860943414.
Full text
46
Youmaran, Richard. "Automatic measurement of features in ultrasound images of the eye." Thesis, University of Ottawa (Canada), 2005. http://hdl.handle.net/10393/27092.
Full textAbstract:
In closed angled Glaucoma, fluid pressure in the eye increases because of inadequate fluid flow between the iris and the cornea. One important technique to assess patients at risk of glaucoma is to analyze ultrasound images of the eye to detect abnormal structural changes. Currently, these images are analyzed manually. This thesis presents an algorithm to automatically identify and measure clinically important features in ultrasound images of the eye. The main challenge is stable detection of features in the presence of ultrasound speckle noise; an algorithm is developed to address this using multiscale analysis and template matching. Tests were performed by comparison of results with eighty images of glaucoma patients and normals against the feature locations identified by a trained technologist. In 5% of cases, the algorithm could not analyze the images; in the remaining cases, features were correctly identified (within 97.5 mum) in 97% of images. This work shows promise as a technique to improve the efficiency of clinical interpretation of ultrasound images of the eye.
47
Tkachenko, Evgeniy. "Measures of Individual Resorption Cavities in Three-Dimensional Images in Cancellous Bone." Case Western Reserve University School of Graduate Studies / OhioLINK, 2011. http://rave.ohiolink.edu/etdc/view?acc_num=case1301413780.
Full text
48
Rahmatullah, Bahbibi. "Assessment of obstetric ultrasound images using machine learning." Thesis, University of Oxford, 2012. http://ora.ox.ac.uk/objects/uuid:8f8f1796-7c25-43b9-bb14-d8cdc28f6ca2.
Full textAbstract:
Ultrasound-based fetal biometry is used to derive important clinical information for identifying IUGR (intra-uterine growth restriction) and managing risk in pregnancy. Accurate and reproducible biometric measurement relies heavily on a good standard image plane. However, qualitative visual assessment, which includes the visual identification of certain anatomical landmarks in the image is prone to inter- and intra-reviewer variability and is also time-consuming to perform. Automated anatomical structure detection is the first step towards the development of a fast and reproducible quality assessment of fetal biometry images. This thesis deals specifically with abdominal scans in the development and evaluation of methods to automatically detect the stomach and the umbilical vein within them. First, an original method for detecting the stomach and the umbilical vein in fetal abdominal scans was developed using a machine learning framework. A classifier solution was designed with AdaBoost learning algorithm with Haar features extracted from the intensity image. The performance of the new method was compared on different clinically relevant gestational age groups. Speckle and the low contrast nature of ultrasound images motivated the idea of introducing features extracted from local phase images. Local phase is contrast invariant and has proven to be useful in other ultrasound image analysis application compared with intensity. Nevertheless, it has never been implemented in a machine learning environment before. In our second experiment, local phase features were proven to have higher discriminative power than intensity features which enabled them to be selected as the first weak classifiers with large classifier weight. Third, a novel approach to improving the speed of the detection was developed using a global feature symmetry map based on local phase to select the candidate locations for the stomach and the umbilical vein. It was coupled with a local intensity-based classifier to form a “hybrid” detector. A nine-fold increase in the average computational speed was recorded along with higher accuracy in the detection of both the anatomical structures. Quantitative and qualitative evaluations of all the algorithms were presented using 2384 fetal abdominal images retrieved from the image database study of the Oxford Ultrasound Quality Control Unit of the INTERGROWTH-21st project. Finally, the “hybrid” detection method was evaluated in two potential application scenarios. The first application was clinical scoring in which both the computer algorithm and four experts were asked to record presence or absence of the stomach and the umbilical vein in 400 ultrasound images. The computer-experts agreement was found to be comparable with the inter-expert agreement. The second application concerned selecting the standard image plane from 3D abdominal ultrasound volume. The algorithm was successful in selecting 93.36% of the images plane defined by the expert in 30 ultrasound volumes.
49
Victora, Ceres. "Images of the body : lay and biomedical views of the reproductive system in Britain and Brazil." Thesis, Brunel University, 1996. http://bura.brunel.ac.uk/handle/2438/7299.
Full textAbstract:
This thesis presents an anthropological study of ordinary people's views about the body in general and the reproductive system in particular, based on two case studies carried out in Britain and in Brazil. I discuss the meanings of lay and biomedical images of the body and identify the ways the researched groups reinterpret the biomedical view of the body anatomy and physiology. Through the analysis of ethnographic material on time, space and domestic organisation in four shantytown groups in Porto Alegre, Brazil and in three different groups in London, UK, I point out the dwelling peculiarities of the different groups and suggest there is a relationship between embodied experiences of time/space and knowledge of the reproductive system. These arguments lead to a more general phenomenologically theorised view of gendered and status-framed bodies, consequently situating this work in the interface of Medical Anthropology and a more general socio-cultural Anthropology.
50
Namayega, Catherine. "A deep learning algorithm for contour detection in synthetic 2D biplanar X-ray images of the scapula: towards improved 3D reconstruction of the scapula." Master's thesis, University of Cape Town, 2020. http://hdl.handle.net/11427/32542.
Full textAbstract:
Three-dimensional (3D) reconstruction from X-ray images using statistical shape models (SSM) provides a cost-effective way of increasing the diagnostic utility of two-dimensional (2D) X-ray images, especially in low-resource settings. The landmark-constrained model fitting approach is one way to obtain patient-specific models from a statistical model. This approach requires an accurate selection of corresponding features, usually landmarks, from the bi-planar X-ray images. However, X-ray images are 2D representations of 3D anatomy with super-positioned structures, which confounds this approach. The literature shows that detection and use of contours to locate corresponding landmarks within biplanar X-ray images can address this limitation. The aim of this research project was to train and validate a deep learning algorithm for detection the contour of a scapula in synthetic 2D bi-planar Xray images. Synthetic bi-planar X-ray images were obtained from scapula mesh samples with annotated landmarks generated from a validated SSM obtained from the Division of Biomedical Engineering, University of Cape Town. This was followed by the training of two convolutional neural network models as the first objective of the project; the first model was trained to predict the lateral (LAT) scapula image given the anterior-posterior (AP) image. The second model was trained to predict the AP image given the LAT image. The trained models had an average Dice coefficient value of 0.926 and 0.964 for the predicted LAT and AP images, respectively. However, the trained models did not generalise to the segmented real X-ray images of the scapula. The second objective was to perform landmark-constrained model fitting using the corresponding landmarks embedded in the predicted images. To achieve this objective, the 2D landmark locations were transformed into 3D coordinates using the direct linear transformation. The 3D point localization yielded average errors of (0.35, 0.64, 0.72) mm in the X, Y and Z directions, respectively, and a combined coordinate error of 1.16 mm. The reconstructed landmarks were used to reconstruct meshes that had average surface-to-surface distances of 3.22 mm and 1.72 mm for 3 and 6 landmarks, respectively. The third objective was to reconstruct the scapula mesh using matching points on the scapula contour in the bi-planar images. The average surface-to-surface distances of the reconstructed meshes with 8 matching contour points and 6 corresponding landmarks of the same meshes were 1.40 and 1.91 mm, respectively. In summary, the deep learning models were able to learn the mapping between the bi-planar images of the scapula. Increasing the number of corresponding landmarks from the bi-planar images resulted into better 3D reconstructions. However, obtaining these corresponding landmarks was non-trivial, necessitating the use of matching points selected from the scapulae contours. The results from the latter approach signal a need to explore contour matching methods to obtain more corresponding points in order to improve the scapula 3D reconstruction using landmark-constrained model fitting.