Щоб переглянути інші типи публікацій з цієї теми, перейдіть за посиланням: Segmentation.
Статті в журналах з теми "Segmentation"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 статей у журналах для дослідження на тему "Segmentation".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте статті в журналах для різних дисциплін та оформлюйте правильно вашу бібліографію.
1
Saker, Halima, Rainer Machné, Jörg Fallmann, Douglas B. Murray, Ahmad M. Shahin, and Peter F. Stadler. "Weighted Consensus Segmentations." Computation 9, no. 2 (February 5, 2021): 17. http://dx.doi.org/10.3390/computation9020017.
Повний текст джерелаАнотація:
The problem of segmenting linearly ordered data is frequently encountered in time-series analysis, computational biology, and natural language processing. Segmentations obtained independently from replicate data sets or from the same data with different methods or parameter settings pose the problem of computing an aggregate or consensus segmentation. This Segmentation Aggregation problem amounts to finding a segmentation that minimizes the sum of distances to the input segmentations. It is again a segmentation problem and can be solved by dynamic programming. The aim of this contribution is (1) to gain a better mathematical understanding of the Segmentation Aggregation problem and its solutions and (2) to demonstrate that consensus segmentations have useful applications. Extending previously known results we show that for a large class of distance functions only breakpoints present in at least one input segmentation appear in the consensus segmentation. Furthermore, we derive a bound on the size of consensus segments. As show-case applications, we investigate a yeast transcriptome and show that consensus segments provide a robust means of identifying transcriptomic units. This approach is particularly suited for dense transcriptomes with polycistronic transcripts, operons, or a lack of separation between transcripts. As a second application, we demonstrate that consensus segmentations can be used to robustly identify growth regimes from sets of replicate growth curves.
2
Buser, Myrthe A. D., Alida F. W. van der Steeg, Marc H. W. A. Wijnen, Matthijs Fitski, Harm van Tinteren, Marry M. van den Heuvel-Eibrink, Annemieke S. Littooij, and Bas H. M. van der Velden. "Radiologic versus Segmentation Measurements to Quantify Wilms Tumor Volume on MRI in Pediatric Patients." Cancers 15, no. 7 (April 1, 2023): 2115. http://dx.doi.org/10.3390/cancers15072115.
Повний текст джерелаАнотація:
Wilms tumor is a common pediatric solid tumor. To evaluate tumor response to chemotherapy and decide whether nephron-sparing surgery is possible, tumor volume measurements based on magnetic resonance imaging (MRI) are important. Currently, radiological volume measurements are based on measuring tumor dimensions in three directions. Manual segmentation-based volume measurements might be more accurate, but this process is time-consuming and user-dependent. The aim of this study was to investigate whether manual segmentation-based volume measurements are more accurate and to explore whether these segmentations can be automated using deep learning. We included the MRI images of 45 Wilms tumor patients (age 0–18 years). First, we compared radiological tumor volumes with manual segmentation-based tumor volume measurements. Next, we created an automated segmentation method by training a nnU-Net in a five-fold cross-validation. Segmentation quality was validated by comparing the automated segmentation with the manually created ground truth segmentations, using Dice scores and the 95th percentile of the Hausdorff distances (HD95). On average, manual tumor segmentations result in larger tumor volumes. For automated segmentation, the median dice was 0.90. The median HD95 was 7.2 mm. We showed that radiological volume measurements underestimated tumor volume by about 10% when compared to manual segmentation-based volume measurements. Deep learning can potentially be used to replace manual segmentation to benefit from accurate volume measurements without time and observer constraints.
3
Nanni, Loris, Daniel Fusaro, Carlo Fantozzi, and Alberto Pretto. "Improving Existing Segmentators Performance with Zero-Shot Segmentators." Entropy 25, no. 11 (October 30, 2023): 1502. http://dx.doi.org/10.3390/e25111502.
Повний текст джерелаАнотація:
This paper explores the potential of using the SAM (Segment-Anything Model) segmentator to enhance the segmentation capability of known methods. SAM is a promptable segmentation system that offers zero-shot generalization to unfamiliar objects and images, eliminating the need for additional training. The open-source nature of SAM allows for easy access and implementation. In our experiments, we aim to improve the segmentation performance by providing SAM with checkpoints extracted from the masks produced by mainstream segmentators, and then merging the segmentation masks provided by these two networks. We examine the “oracle” method (as upper bound baseline performance), where segmentation masks are inferred only by SAM with checkpoints extracted from the ground truth. One of the main contributions of this work is the combination (fusion) of the logit segmentation masks produced by the SAM model with the ones provided by specialized segmentation models such as DeepLabv3+ and PVTv2. This combination allows for a consistent improvement in segmentation performance in most of the tested datasets. We exhaustively tested our approach on seven heterogeneous public datasets, obtaining state-of-the-art results in two of them (CAMO and Butterfly) with respect to the current best-performing method with a combination of an ensemble of mainstream segmentator transformers and the SAM segmentator. The results of our study provide valuable insights into the potential of incorporating the SAM segmentator into existing segmentation techniques. We release with this paper the open-source implementation of our method.
4
Liu, Qiming, Qifan Lu, Yezi Chai, Zhengyu Tao, Qizhen Wu, Meng Jiang, and Jun Pu. "Radiomics-Based Quality Control System for Automatic Cardiac Segmentation: A Feasibility Study." Bioengineering 10, no. 7 (July 1, 2023): 791. http://dx.doi.org/10.3390/bioengineering10070791.
Повний текст джерелаАнотація:
Purpose: In the past decade, there has been a rapid increase in the development of automatic cardiac segmentation methods. However, the automatic quality control (QC) of these segmentation methods has received less attention. This study aims to address this gap by developing an automatic pipeline that incorporates DL-based cardiac segmentation and radiomics-based quality control. Methods: In the DL-based localization and segmentation part, the entire heart was first located and cropped. Then, the cropped images were further utilized for the segmentation of the right ventricle cavity (RVC), myocardium (MYO), and left ventricle cavity (LVC). As for the radiomics-based QC part, a training radiomics dataset was created with segmentation tasks of various quality. This dataset was used for feature extraction, selection, and QC model development. The model performance was then evaluated using both internal and external testing datasets. Results: In the internal testing dataset, the segmentation model demonstrated a great performance with a dice similarity coefficient (DSC) of 0.954 for whole heart segmentations. Images were then appropriately cropped to 160 × 160 pixels. The models also performed well for cardiac substructure segmentations. The DSC values were 0.863, 0.872, and 0.940 for RVC, MYO, and LVC for 2D masks and 0.928, 0.886, and 0.962 for RVC, MYO, and LVC for 3D masks with an attention-UNet. After feature selection with the radiomics dataset, we developed a series of models to predict the automatic segmentation quality and its DSC value for the RVC, MYO, and LVC structures. The mean absolute values for our best prediction models were 0.060, 0.032, and 0.021 for 2D segmentations and 0.027, 0.017, and 0.011 for 3D segmentations, respectively. Additionally, the radiomics-based classification models demonstrated a high negative detection rate of >0.85 in all 2D groups. In the external dataset, models showed similar results. Conclusions: We developed a pipeline including cardiac substructure segmentation and QC at both the slice (2D) and subject (3D) levels. Our results demonstrate that the radiomics method possesses great potential for the automatic QC of cardiac segmentation.
5
Sithole, G., and L. Majola. "FRAMEWORK FOR COMPARING SEGMENTATION ALGORITHMS." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XL-4/W5 (May 11, 2015): 131–36. http://dx.doi.org/10.5194/isprsarchives-xl-4-w5-131-2015.
Повний текст джерелаАнотація:
The notion of a ‘Best’ segmentation does not exist. A segmentation algorithm is chosen based on the features it yields, the properties of the segments (point sets) it generates, and the complexity of its algorithm. The segmentation is then assessed based on a variety of metrics such as homogeneity, heterogeneity, fragmentation, etc. Even after an algorithm is chosen its performance is still uncertain because the landscape/scenarios represented in a point cloud have a strong influence on the eventual segmentation. Thus selecting an appropriate segmentation algorithm is a process of trial and error. <br><br> Automating the selection of segmentation algorithms and their parameters first requires methods to evaluate segmentations. Three common approaches for evaluating segmentation algorithms are ‘goodness methods’, ‘discrepancy methods’ and ‘benchmarks’. Benchmarks are considered the most comprehensive method of evaluation. This paper shortcomings in current benchmark methods are identified and a framework is proposed that permits both a visual and numerical evaluation of segmentations for different algorithms, algorithm parameters and evaluation metrics. The concept of the framework is demonstrated on a real point cloud. Current results are promising and suggest that it can be used to predict the performance of segmentation algorithms.
6
Stevens, Michiel, Afroditi Nanou, Leon W. M. M. Terstappen, Christiane Driemel, Nikolas H. Stoecklein, and Frank A. W. Coumans. "StarDist Image Segmentation Improves Circulating Tumor Cell Detection." Cancers 14, no. 12 (June 13, 2022): 2916. http://dx.doi.org/10.3390/cancers14122916.
Повний текст джерелаАнотація:
After a CellSearch-processed circulating tumor cell (CTC) sample is imaged, a segmentation algorithm selects nucleic acid positive (DAPI+), cytokeratin-phycoerythrin expressing (CK-PE+) events for further review by an operator. Failures in this segmentation can result in missed CTCs. The CellSearch segmentation algorithm was not designed to handle samples with high cell density, such as diagnostic leukapheresis (DLA) samples. Here, we evaluate deep-learning-based segmentation method StarDist as an alternative to the CellSearch segmentation. CellSearch image archives from 533 whole blood samples and 601 DLA samples were segmented using CellSearch and StarDist and inspected visually. In 442 blood samples from cancer patients, StarDist segmented 99.95% of CTC segmented by CellSearch, produced good outlines for 98.3% of these CTC, and segmented 10% more CTC than CellSearch. Visual inspection of the segmentations of DLA images showed that StarDist continues to perform well when the cell density is very high, whereas CellSearch failed and generated extremely large segmentations (up to 52% of the sample surface). Moreover, in a detailed examination of seven DLA samples, StarDist segmented 20% more CTC than CellSearch. Segmentation is a critical first step for CTC enumeration in dense samples and StarDist segmentation convincingly outperformed CellSearch segmentation.
7
Harkey, Matthew S., Nicholas Michel, Christopher Kuenze, Ryan Fajardo, Matt Salzler, Jeffrey B. Driban, and Ilker Hacihaliloglu. "Validating a Semi-Automated Technique for Segmenting Femoral Articular Cartilage on Ultrasound Images." CARTILAGE 13, no. 2 (April 2022): 194760352210930. http://dx.doi.org/10.1177/19476035221093069.
Повний текст джерелаАнотація:
Objective To validate a semi-automated technique to segment ultrasound-assessed femoral cartilage without compromising segmentation accuracy to a traditional manual segmentation technique in participants with an anterior cruciate ligament injury (ACL). Design We recruited 27 participants with a primary unilateral ACL injury at a pre-operative clinic visit. One investigator performed a transverse suprapatellar ultrasound scan with the participant’s ACL injured knee in maximum flexion. Three femoral cartilage ultrasound images were recorded. A single expert reader manually segmented the femoral cartilage cross-sectional area in each image. In addition, we created a semi-automatic program to segment the cartilage using a random walker-based method. We quantified the average cartilage thickness and echo-intensity for the manual and semi-automated segmentations. Intraclass correlation coefficients (ICC2,k) and Bland-Altman plots were used to validate the semi-automated technique to the manual segmentation for assessing average cartilage thickness and echo-intensity. A dice correlation coefficient was used to quantify the overlap between the segmentations created with the semi-automated and manual techniques. Results For average cartilage thickness, there was excellent reliability (ICC2,k = 0.99) and a small mean difference (+0.8%) between the manual and semi-automated segmentations. For average echo-intensity, there was excellent reliability (ICC2,k = 0.97) and a small mean difference (−2.5%) between the manual and semi-automated segmentations. The average dice correlation coefficient between the manual segmentation and semi-automated segmentation was 0.90, indicating high overlap between techniques. Conclusions Our novel semi-automated segmentation technique is a valid method that requires less technical expertise and time than manual segmentation in patients after ACL injury.
8
Mendoza Garay, Juan Ignacio. "Segmentation boundaries in accelerometer data of arm motion induced by music: Online computation and perceptual assessment." Human Technology 18, no. 3 (December 28, 2022): 250–66. http://dx.doi.org/10.14254/1795-6889.2022.18-3.4.
Повний текст джерелаАнотація:
Segmentation is a cognitive process involved in the understanding of information perceived through the senses. Likewise, the automatic segmentation of data captured by sensors may be used for the identification of patterns. This study is concerned with the segmentation of dancing motion captured by accelerometry and its possible applications, such as pattern learning and recognition, or gestural control of devices. To that effect, an automatic segmentation system was formulated and tested. Two participants were asked to ‘dance with one arm’ while their motion was measured by an accelerometer. The performances were recorded on video, and manually segmented by six annotators later. The annotations were used to optimize the automatic segmentation system, maximizing a novel similarity score between computed and annotated segmentations. The computed segmentations with highest similarity to each annotation were then manually assessed by the annotators, resulting in Precision between 0.71 and 0.89, and Recall between 0.82 to 1.
9
Schmidt-Richberg, A., J. Fiehler, T. Illies, D. Möller, H. Handels, D. Säring, and N. D. Forkert. "Automatic Correction of Gaps in Cerebrovascular Segmentations Extracted from 3D Time-of-Flight MRA Datasets." Methods of Information in Medicine 51, no. 05 (2012): 415–22. http://dx.doi.org/10.3414/me11-02-0037.
Повний текст джерелаАнотація:
Summary Objectives: Exact cerebrovascular segmentations are required for several applications in today’s clinical routine. A major drawback of typical automatic segmentation methods is the occurrence of gaps within the segmentation. These gaps are typically located at small vessel structures exhibiting low intensities. Manual correction is very time-consuming and not suitable in clinical practice. This work presents a post-processing method for the automatic detection and closing of gaps in cerebrovascular segmentations. Methods: In this approach, the 3D centerline is calculated from an available vessel segmentation, which enables the detection of corresponding vessel endpoints. These endpoints are then used to detect possible connections to other 3D centerline voxels with a graph-based approach. After consistency check, reasonable detected paths are expanded to the vessel boundaries using a level set approach and combined with the initial segmentation. Results: For evaluation purposes, 100 gaps were artificially inserted at non-branching vessels and bifurcations in manual cerebrovascular segmentations derived from ten Time-of-Flight magnetic resonance angiography datasets. The results show that the presented method is capable of detecting 82% of the non-branching vessel gaps and 84% of the bifurcation gaps. The level set segmentation expands the detected connections with 0.42 mm accuracy compared to the initial segmentations. A further evaluation based on 10 real automatic segmentations from the same datasets shows that the proposed method detects 35 additional connections in average per dataset, whereas 92.7% were rated as correct by a medical expert. Conclusion: The presented approach can considerably improve the accuracy of cerebrovascular segmentations and of following analysis outcomes.
10
van der Putten, Joost, Fons van der Sommen, Jeroen de Groof, Maarten Struyvenberg, Svitlana Zinger, Wouter Curvers, Erik Schoon, Jacques Bergman, and Peter H. N. de With. "Modeling clinical assessor intervariability using deep hypersphere encoder–decoder networks." Neural Computing and Applications 32, no. 14 (November 21, 2019): 10705–17. http://dx.doi.org/10.1007/s00521-019-04607-w.
Повний текст джерелаАнотація:
AbstractIn medical imaging, a proper gold-standard ground truth as, e.g., annotated segmentations by assessors or experts is lacking or only scarcely available and suffers from large intervariability in those segmentations. Most state-of-the-art segmentation models do not take inter-observer variability into account and are fully deterministic in nature. In this work, we propose hypersphere encoder–decoder networks in combination with dynamic leaky ReLUs, as a new method to explicitly incorporate inter-observer variability into a segmentation model. With this model, we can then generate multiple proposals based on the inter-observer agreement. As a result, the output segmentations of the proposed model can be tuned to typical margins inherent to the ambiguity in the data. For experimental validation, we provide a proof of concept on a toy data set as well as show improved segmentation results on two medical data sets. The proposed method has several advantages over current state-of-the-art segmentation models such as interpretability in the uncertainty of segmentation borders. Experiments with a medical localization problem show that it offers improved biopsy localizations, which are on average 12% closer to the optimal biopsy location.
11
Halawa, Abdelrahman, Shehab Gamalel-Din, and Abdurrahman Nasr. "EXPLOITING BERT FOR MALFORMED SEGMENTATION DETECTION TO IMPROVE SCIENTIFIC WRITINGS." Applied Computer Science 19, no. 2 (June 30, 2023): 126–41. http://dx.doi.org/10.35784/acs-2023-20.
Повний текст джерелаАнотація:
Writing a well-structured scientific documents, such as articles and theses, is vital for comprehending the document's argumentation and understanding its messages. Furthermore, it has an impact on the efficiency and time required for studying the document. Proper document segmentation also yields better results when employing automated Natural Language Processing (NLP) manipulation algorithms, including summarization and other information retrieval and analysis functions. Unfortunately, inexperienced writers, such as young researchers and graduate students, often struggle to produce well-structured professional documents. Their writing frequently exhibits improper segmentations or lacks semantically coherent segments, a phenomenon referred to as "mal-segmentation." Examples of mal-segmentation include improper paragraph or section divisions and unsmooth transitions between sentences and paragraphs. This research addresses the issue of mal-segmentation in scientific writing by introducing an automated method for detecting mal-segmentations, and utilizing Sentence Bidirectional Encoder Representations from Transformers (sBERT) as an encoding mechanism. The experimental results section shows a promising results for the detection of mal-segmentation using the sBERT technique.
12
Zhao, Yuan, Mingjie Jiang, Wai Sum Chan, and Bernard Chiu. "Development of a Three-Dimensional Carotid Ultrasound Image Segmentation Workflow for Improved Efficiency, Reproducibility and Accuracy in Measuring Vessel Wall and Plaque Volume and Thickness." Bioengineering 10, no. 10 (October 18, 2023): 1217. http://dx.doi.org/10.3390/bioengineering10101217.
Повний текст джерелаАнотація:
Automated segmentation of carotid lumen-intima boundary (LIB) and media-adventitia boundary (MAB) by deep convolutional neural networks (CNN) from three-dimensional ultrasound (3DUS) images has made assessment and monitoring of carotid atherosclerosis more efficient than manual segmentation. However, training of CNN still requires manual segmentation of LIB and MAB. Therefore, there is a need to improve the efficiency of manual segmentation and develop strategies to improve segmentation accuracy by the CNN for serial monitoring of carotid atherosclerosis. One strategy to reduce segmentation time is to increase the interslice distance (ISD) between segmented axial slices of a 3DUS image while maintaining the segmentation reliability. We, for the first time, investigated the effect of ISD on the reproducibility of MAB and LIB segmentations. The intra-observer reproducibility of LIB and MAB segmentations at ISDs of 1 mm and 2 mm was not statistically significantly different, whereas the reproducibility at ISD = 3 mm was statistically lower. Therefore, we conclude that segmentation with an ISD of 2 mm provides sufficient reliability for CNN training. We further proposed training the CNN by the baseline images of the entire cohort of patients for automatic segmentation of the follow-up images acquired for the same cohort. We validated that segmentation with this time-based partitioning approach is more accurate than that produced by patient-based partitioning, especially at the carotid bifurcation. This study forms the basis for an efficient, reproducible, and accurate 3DUS workflow for serial monitoring of carotid atherosclerosis useful in risk stratification of cardiovascular events and in evaluating the efficacy of new treatments.
13
Yang, Zi, Mingli Chen, Mahdieh Kazemimoghadam, Lin Ma, Strahinja Stojadinovic, Robert Timmerman, Tu Dan, Zabi Wardak, Weiguo Lu, and Xuejun Gu. "Deep-learning and radiomics ensemble classifier for false positive reduction in brain metastases segmentation." Physics in Medicine & Biology 67, no. 2 (January 19, 2022): 025004. http://dx.doi.org/10.1088/1361-6560/ac4667.
Повний текст джерелаАнотація:
Abstract Stereotactic radiosurgery (SRS) is now the standard of care for brain metastases (BMs) patients. The SRS treatment planning process requires precise target delineation, which in clinical workflow for patients with multiple (>4) BMs (mBMs) could become a pronounced time bottleneck. Our group has developed an automated BMs segmentation platform to assist in this process. The accuracy of the auto-segmentation, however, is influenced by the presence of false-positive segmentations, mainly caused by the injected contrast during MRI acquisition. To address this problem and further improve the segmentation performance, a deep-learning and radiomics ensemble classifier was developed to reduce the false-positive rate in segmentations. The proposed model consists of a Siamese network and a radiomic-based support vector machine (SVM) classifier. The 2D-based Siamese network contains a pair of parallel feature extractors with shared weights followed by a single classifier. This architecture is designed to identify the inter-class difference. On the other hand, the SVM model takes the radiomic features extracted from 3D segmentation volumes as the input for twofold classification, either a false-positive segmentation or a true BM. Lastly, the outputs from both models create an ensemble to generate the final label. The performance of the proposed model in the segmented mBMs testing dataset reached the accuracy (ACC), sensitivity (SEN), specificity (SPE) and area under the curve of 0.91, 0.96, 0.90 and 0.93, respectively. After integrating the proposed model into the original segmentation platform, the average segmentation false negative rate (FNR) and the false positive over the union (FPoU) were 0.13 and 0.09, respectively, which preserved the initial FNR (0.07) and significantly improved the FPoU (0.55). The proposed method effectively reduced the false-positive rate in the BMs raw segmentations indicating that the integration of the proposed ensemble classifier into the BMs segmentation platform provides a beneficial tool for mBMs SRS management.
14
Zhang, Jin Xi, Hong Zhi Yu, Ning Ma, and Zhao Yao Li. "The Phoneme Automatic Segmentation Algorithms Study of Tibetan Lhasa Words Continuous Speech Stream." Advanced Materials Research 765-767 (September 2013): 2051–54. http://dx.doi.org/10.4028/www.scientific.net/amr.765-767.2051.
Повний текст джерелаАнотація:
In this paper, we adopt two methods to voice phoneme segmentation when building Tibetan corpus: One is the traditional artificial segmentation method, one is the automatic segmentation method based on the Mono prime HMM model. And experiments are performed to analyze the accuracy of both methods of segmentations. The results showed: Automatic segmentation method based tone prime HMM model helps to shorten the cycle of building Tibetan corpus, especially in building a large corpus segmentation and labeling a lot of time and manpower cost savings, and have greatly improved the accuracy and consistency of speech corpus annotation information.
15
Shah, Nilima, Dhanesh Patel, and Pasi Fränti. "Fast Mumford-Shah Two-Phase Image Segmentation Using Proximal Splitting Scheme." Journal of Applied Mathematics 2021 (April 13, 2021): 1–13. http://dx.doi.org/10.1155/2021/6618505.
Повний текст джерелаАнотація:
The Mumford-Shah model is extensively used in image segmentation. Its energy functional causes the content of the segments to remain homogeneous and the segment boundaries to become short. However, the problem is that optimization of the functional can be very slow. To attack this problem, we propose a reduced two-phase Mumford-Shah model to segment images having one prominent object. First, initial segmentation is obtained by the k-means clustering technique, further minimizing the Mumford-Shah functional by the Douglas-Rachford algorithm. Evaluation of segmentations with various error metrics shows that 70 percent of the segmentations keep the error values below 50%. Compared to the level set method to solve the Chan-Vese model, our algorithm is significantly faster. At the same time, it gives almost the same or better segmentation results. When compared to the recent k-means variant, it also gives much better segmentation with convex boundaries. The proposed algorithm balances well between time and quality of the segmentation. A crucial step in the design of machine vision systems is the extraction of discriminant features from the images, which is based on low-level segmentation which can be obtained by our approach.
16
Chen, Fuhua, Yunmei Chen, and Hemant D. Tagare. "A New Framework of Multiphase Segmentation and Its Application to Partial Volume Segmentation." Applied Computational Intelligence and Soft Computing 2011 (2011): 1–11. http://dx.doi.org/10.1155/2011/786369.
Повний текст джерелаАнотація:
We proposed a novel framework of multiphase segmentation based on stochastic theory and phase transition theory. Our main contribution lies in the introduction of a constructed function so that its composition with phase function forms membership functions. In this way, it saves memory space and also avoids the general simplex constraint problem for soft segmentations. The framework is then applied to partial volume segmentation. Although the partial volume segmentation in this paper is focused on brain MR image, the proposed framework can be applied to any segmentation containing partial volume caused by limited resolution and overlapping.
17
Akcay, Ozgun, Emin Avsar, Melis Inalpulat, Levent Genc, and Ahmet Cam. "Assessment of Segmentation Parameters for Object-Based Land Cover Classification Using Color-Infrared Imagery." ISPRS International Journal of Geo-Information 7, no. 11 (October 31, 2018): 424. http://dx.doi.org/10.3390/ijgi7110424.
Повний текст джерелаАнотація:
Using object-based image analysis (OBIA) techniques for land use-land cover classification (LULC) has become an area of interest due to the availability of high-resolution data and segmentation methods. Multi-resolution segmentation in particular, statistically seen as the most used algorithm, is able to produce non-identical segmentations depending on the required parameters. The total effect of segmentation parameters on the classification accuracy of high-resolution imagery is still an open question, though some studies were implemented to define the optimum segmentation parameters. However, recent studies have not properly considered the parameters and their consequences on LULC accuracy. The main objective of this study is to assess OBIA segmentation and classification accuracy according to the segmentation parameters using different overlap ratios during image object sampling for a predetermined scale. With this aim, we analyzed and compared (a) high-resolution color-infrared aerial images of a newly-developed urban area including different land use types; (b) combinations of multi-resolution segmentation with different shape, color, compactness, bands, and band-weights; and (c) accuracies of classifications based on varied segmentations. The results of various parameters in the study showed an explicit correlation between segmentation accuracies and classification accuracies. The effect of changes in segmentation parameters using different sample selection methods for five main LULC types was studied. Specifically, moderate shape and compactness values provided more consistency than lower and higher values; also, band weighting demonstrated substantial results due to the chosen bands. Differences in the variable importance of the classifications and changes in LULC maps were also explained.
18
Li, Yuan, Fu Cang Jia, Xiao Dong Zhang, Cheng Huang, and Huo Ling Luo. "Local Patch Similarity Ranked Voxelwise STAPLE on Magnetic Resonance Image Hippocampus Segmentation." Applied Mechanics and Materials 333-335 (July 2013): 1065–70. http://dx.doi.org/10.4028/www.scientific.net/amm.333-335.1065.
Повний текст джерелаАнотація:
The segmentation and labeling of sub-cortical structures of interest are important tasks for the assessment of morphometric features in quantitative magnetic resonance (MR) image analysis. Recently, multi-atlas segmentation methods with statistical fusion strategy have demonstrated high accuracy in hippocampus segmentation. While, most of the segmentations rarely consider spatially variant model and reserve all segmentations. In this study, we propose a novel local patch-based and ranking strategy for voxelwise atlas selection to extend the original Simultaneous Truth and Performance Level Estimation (STAPLE) algorithm. The local ranking strategy is based on the metric of normalized cross correlation (NCC). Unlike its predecessors, this method estimates the fusion of each voxel patch-by-patch and makes use of gray image features as a prior. Validation results on 33 pairs of hippocampus MR images show good performance on the segmentation of hippocampus.
19
Matin-Mann, Farnaz, Ziwen Gao, Chunjiang Wei, Felix Repp, Eralp-Niyazi Artukarslan, Samuel John, Dorian Alcacer Labrador, Thomas Lenarz, and Verena Scheper. "Development and In-Silico and Ex-Vivo Validation of a Software for a Semi-Automated Segmentation of the Round Window Niche to Design a Patient Specific Implant to Treat Inner Ear Disorders." Journal of Imaging 9, no. 2 (February 20, 2023): 51. http://dx.doi.org/10.3390/jimaging9020051.
Повний текст джерелаАнотація:
The aim of this study was to develop and validate a semi-automated segmentation approach that identifies the round window niche (RWN) and round window membrane (RWM) for use in the development of patient individualized round window niche implants (RNI) to treat inner ear disorders. Twenty cone beam computed tomography (CBCT) datasets of unilateral temporal bones of patients were included in the study. Defined anatomical landmarks such as the RWM were used to develop a customized 3D Slicer™ plugin for semi-automated segmentation of the RWN. Two otolaryngologists (User 1 and User 2) segmented the datasets manually and semi-automatically using the developed software. Both methods were compared in-silico regarding the resulting RWM area and RWN volume. Finally, the developed software was validated ex-vivo in N = 3 body donor implantation tests with additively manufactured RNI. The independently segmented temporal bones of the different Users showed a strong consistency in the volume of the RWN and the area of the RWM. The volume of the semi-automated RWN segmentations were 48 ± 11% smaller on average than the manual segmentations and the area of the RWM of the semi-automated segmentations was 21 ± 17% smaller on average than the manual segmentation. All additively manufactured implants, based on the semi-automated segmentation method could be implanted successfully in a pressure-tight fit into the RWN. The implants based on the manual segmentations failed to fit into the RWN and this suggests that the larger manual segmentations were over-segmentations. This study presents a semi-automated approach for segmenting the RWN and RWM in temporal bone CBCT scans that is efficient, fast, accurate, and not dependent on trained users. In addition, the manual segmentation, often positioned as the gold-standard, actually failed to pass the implantation validation.
20
Cahuina, Edward Cayllahua, Jean Cousty, Yukiko Kenmochi, Arnaldo de Albuquerque Araújo, Guillermo Cámara-Chávez, and Silvio Jamil F. Guimarães. "Efficient Algorithms for Hierarchical Graph-Based Segmentation Relying on the Felzenszwalb–Huttenlocher Dissimilarity." International Journal of Pattern Recognition and Artificial Intelligence 33, no. 11 (October 2019): 1940008. http://dx.doi.org/10.1142/s0218001419400081.
Повний текст джерелаАнотація:
Hierarchical image segmentation provides a region-oriented scale-space, i.e. a set of image segmentations at different detail levels in which the segmentations at finer levels are nested with respect to those at coarser levels. However, most image segmentation algorithms, among which a graph-based image segmentation method relying on a region merging criterion was proposed by Felzenszwalb–Huttenlocher in 2004, do not lead to a hierarchy. In order to cope with a demand for hierarchical segmentation, Guimarães et al. proposed in 2012 a method for hierarchizing the popular Felzenszwalb–Huttenlocher method, without providing an algorithm to compute the proposed hierarchy. This paper is devoted to providing a series of algorithms to compute the result of this hierarchical graph-based image segmentation method efficiently, based mainly on two ideas: optimal dissimilarity measuring and incremental update of the hierarchical structure. Experiments show that, for an image of size 321 × 481 pixels, the most efficient algorithm produces the result in half a second whereas the most naive one requires more than 4 h.
21
Kubicek, Jan, Alice Varysova, Martin Cerny, Kristyna Hancarova, David Oczka, Martin Augustynek, Marek Penhaker, Ondrej Prokop, and Radomir Scurek. "Performance and Robustness of Regional Image Segmentation Driven by Selected Evolutionary and Genetic Algorithms: Study on MR Articular Cartilage Images." Sensors 22, no. 17 (August 23, 2022): 6335. http://dx.doi.org/10.3390/s22176335.
Повний текст джерелаАнотація:
The analysis and segmentation of articular cartilage magnetic resonance (MR) images belongs to one of the most commonly routine tasks in diagnostics of the musculoskeletal system of the knee area. Conventional regional segmentation methods, which are based either on the histogram partitioning (e.g., Otsu method) or clustering methods (e.g., K-means), have been frequently used for the task of regional segmentation. Such methods are well known as fast and well working in the environment, where cartilage image features are reliably recognizable. The well-known fact is that the performance of these methods is prone to the image noise and artefacts. In this context, regional segmentation strategies, driven by either genetic algorithms or selected evolutionary computing strategies, have the potential to overcome these traditional methods such as Otsu thresholding or K-means in the context of their performance. These optimization strategies consecutively generate a pyramid of a possible set of histogram thresholds, of which the quality is evaluated by using the fitness function based on Kapur’s entropy maximization to find the most optimal combination of thresholds for articular cartilage segmentation. On the other hand, such optimization strategies are often computationally demanding, which is a limitation of using such methods for a stack of MR images. In this study, we publish a comprehensive analysis of the optimization methods based on fuzzy soft segmentation, driven by artificial bee colony (ABC), particle swarm optimization (PSO), Darwinian particle swarm optimization (DPSO), and a genetic algorithm for an optimal thresholding selection against the routine segmentations Otsu and K-means for analysis and the features extraction of articular cartilage from MR images. This study objectively analyzes the performance of the segmentation strategies upon variable noise with dynamic intensities to report a segmentation’s robustness in various image conditions for a various number of segmentation classes (4, 7, and 10), cartilage features (area, perimeter, and skeleton) extraction preciseness against the routine segmentation strategies, and lastly the computing time, which represents an important factor of segmentation performance. We use the same settings on individual optimization strategies: 100 iterations and 50 population. This study suggests that the combination of fuzzy thresholding with an ABC algorithm gives the best performance in the comparison with other methods as from the view of the segmentation influence of additive dynamic noise influence, also for cartilage features extraction. On the other hand, using genetic algorithms for cartilage segmentation in some cases does not give a good performance. In most cases, the analyzed optimization strategies significantly overcome the routine segmentation methods except for the computing time, which is normally lower for the routine algorithms. We also publish statistical tests of significance, showing differences in the performance of individual optimization strategies against Otsu and K-means method. Lastly, as a part of this study, we publish a software environment, integrating all the methods from this study.
22
Lacerda, M. G., E. H. Shiguemori, A. J. Damião, C. S. Anjos, and M. Habermann. "IMPACT OF SEGMENTATION PARAMETERS ON THE CLASSIFICATION OF VHR IMAGES ACQUIRED BY RPAS." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLII-3/W12-2020 (November 4, 2020): 43–48. http://dx.doi.org/10.5194/isprs-archives-xlii-3-w12-2020-43-2020.
Повний текст джерелаАнотація:
Abstract. RPAs (Remotely Piloted Aircrafts) have been used in many Remote Sensing applications, featuring high-quality imaging sensors. In some situations, the images are interpreted in an automated fashion using object-oriented classification. In this case, the first step is segmentation. However, the setting of segmentation parameters such as scale, shape, and compactness may yield too many different segmentations, thus it is necessary to understand the influence of those parameters on the final output. This paper compares 24 segmentation parameter sets by taking into account classification scores. The results indicate that the segmentation parameters exert influence on both classification accuracy and processing time.
23
Gurari, Danna, Mehrnoosh Sameki, and Margrit Betke. "Investigating the Influence of Data Familiarity to Improve the Design of a Crowdsourcing Image Annotation System." Proceedings of the AAAI Conference on Human Computation and Crowdsourcing 4 (September 21, 2016): 59–68. http://dx.doi.org/10.1609/hcomp.v4i1.13294.
Повний текст джерелаАнотація:
Crowdsourced demarcations of object boundaries in images (segmentations) are important for many vision-based applications. A commonly reported challenge is that a large percentage of crowd results are discarded due to concerns about quality. We conducted three studies to examine (1) how does the quality of crowdsourced segmentations differ for familiar everyday images versus unfamiliar biomedical images?, (2) how does making familiar images less recognizable (rotating images upside down) influence crowd work with respect to the quality of results, segmentation time, and segmentation detail?, and (3) how does crowd workers’ judgments of the ambiguity of the segmentation task, collected by voting, differ for familiar everyday images and unfamiliar biomedical images? We analyzed a total of 2,525 segmentations collected from 121 crowd workers and 1,850 votes from 55 crowd workers. Our results illustrate the potential benefit of explicitly accounting for human familiarity with the data when designing computer interfaces for human interaction.
24
Jones, R. Kenny, Aalia Habib, and Daniel Ritchie. "SHRED." ACM Transactions on Graphics 41, no. 6 (November 30, 2022): 1–11. http://dx.doi.org/10.1145/3550454.3555440.
Повний текст джерелаАнотація:
We present SHRED, a method for 3D SHape REgion Decomposition. SHRED takes a 3D point cloud as input and uses learned local operations to produce a segmentation that approximates fine-grained part instances. We endow SHRED with three decomposition operations: splitting regions, fixing the boundaries between regions, and merging regions together. Modules are trained independently and locally, allowing SHRED to generate high-quality segmentations for categories not seen during training. We train and evaluate SHRED with fine-grained segmentations from PartNet; using its merge-threshold hyperparameter, we show that SHRED produces segmentations that better respect ground-truth annotations compared with baseline methods, at any desired decomposition granularity. Finally, we demonstrate that SHRED is useful for downstream applications, out-performing all baselines on zero-shot fine-grained part instance segmentation and few-shot finegrained semantic segmentation when combined with methods that learn to label shape regions.
25
Platero, Carlos, and M. Carmen Tobar. "A Multiatlas Segmentation Using Graph Cuts with Applications to Liver Segmentation in CT Scans." Computational and Mathematical Methods in Medicine 2014 (2014): 1–16. http://dx.doi.org/10.1155/2014/182909.
Повний текст джерелаАнотація:
An atlas-based segmentation approach is presented that combines low-level operations, an affine probabilistic atlas, and a multiatlas-based segmentation. The proposed combination provides highly accurate segmentation due to registrations and atlas selections based on the regions of interest (ROIs) and coarse segmentations. Our approach shares the following common elements between the probabilistic atlas and multiatlas segmentation: (a) the spatial normalisation and (b) the segmentation method, which is based on minimising a discrete energy function using graph cuts. The method is evaluated for the segmentation of the liver in computed tomography (CT) images. Low-level operations define a ROI around the liver from an abdominal CT. We generate a probabilistic atlas using an affine registration based on geometry moments from manually labelled data. Next, a coarse segmentation of the liver is obtained from the probabilistic atlas with low computational effort. Then, a multiatlas segmentation approach improves the accuracy of the segmentation. Both the atlas selections and the nonrigid registrations of the multiatlas approach use a binary mask defined by coarse segmentation. We experimentally demonstrate that this approach performs better than atlas selections and nonrigid registrations in the entire ROI. The segmentation results are comparable to those obtained by human experts and to other recently published results.
26
Li, Collin, Dominick Romano, Sophie J. Wang, Hang Zhang, Martin R. Prince, and Yi Wang. "IRIS—Intelligent Rapid Interactive Segmentation for Measuring Liver Cyst Volumes in Autosomal Dominant Polycystic Kidney Disease." Tomography 8, no. 1 (February 9, 2022): 447–56. http://dx.doi.org/10.3390/tomography8010037.
Повний текст джерелаАнотація:
Purpose: To develop and integrate interactive features with automatic methods for accurate liver cyst segmentation in patients with autosomal dominant polycystic kidney and liver disease (ADPKD). Methods: SmartClick and antiSmartClick were developed using iterative region growth guided by spatial and intensity connections and were integrated with automated level set (LS) segmentation and graphical user interface, forming an intelligent rapid interactive segmentation (IRIS) tool. IRIS and LS segmentations of liver cysts on T2 weighted images of patients with ADPKD (n = 17) were compared with manual segmentation as ground truth (GT). Results: Compared to manual GT, IRIS reduced the segmentation time by more than 10-fold. Compared to automated LS, IRIS reduced the mean liver cyst volume error from 42.22% to 13.44% (p < 0.001). IRIS segmentation agreed well with manual GT (79% dice score and 99% intraclass correlation coefficient). Conclusion: IRIS is feasible for fast, accurate liver cyst segmentation in patients with ADPKD.
27
Beasley, Ryan A. "Semiautonomous Medical Image Segmentation Using Seeded Cellular Automaton Plus Edge Detector." ISRN Signal Processing 2012 (May 17, 2012): 1–9. http://dx.doi.org/10.5402/2012/914232.
Повний текст джерелаАнотація:
Segmentations of medical images are required in a number of medical applications such as quantitative analyses and patient-specific orthotics, yet accurate segmentation without significant user attention remains a challenge. This work presents a novel segmentation algorithm combining the region-growing Seeded Cellular Automata with a boundary term based on an edge-detected image. Both single processor and parallel processor implementations are developed and the algorithm is shown to be suitable for quick segmentations (2.2 s for voxel brain MRI) and interactive supervision (2–220 Hz). Furthermore, a method is described for generating appropriate edge-detected images without requiring additional user attention. Experiments demonstrate higher segmentation accuracy for the proposed algorithm compared with both Graphcut and Seeded Cellular Automata, particularly when provided minimal user attention.
28
Qayyum, Abdul, Mohamed Khan Afthab Ahamed Khan, Rana Umar Mukhtar, Moona Mazher, Mastaneh Mokayef, Chun Kit Ang, and Lim Wei Hong. "Automatic segmentation of intracranial hemorrhage using coarse and fine deep learning models." Imaging and Radiation Research 6, no. 1 (October 31, 2023): 3088. http://dx.doi.org/10.24294/irr.v6i1.3088.
Повний текст джерелаАнотація:
To save patients’ lives, it is important to go for an early diagnosis of intracranial hemorrhage (ICH). For diagnosing ICH, the widely used method is non-contrast computed tomography (NCCT). It has fast acquisition and availability in medical emergency facilities. To predict hematoma progression and mortality, it is important to estimate the volume of intracranial hemorrhage. Radiologists can manually delineate the ICH region to estimate the hematoma volume. This process takes time and undergoes inter-rater variability. In this research paper, we develop and discuss a fine segmentation model and a coarse model for intracranial hemorrhage segmentations. Basically, two different models are discussed for intracranial hemorrhage segmentation. We trained a 2DDensNet in the first model for coarse segmentation and cascaded the coarse segmentation mask output in the fine segmentation model along with input training samples. A nnUNet model is trained in the second fine stage and will use the segmentation labels of the coarse model with true labels for intracranial hemorrhage segmentation. An optimal performance for intracranial hemorrhage segmentation solution is obtained.
29
Ikokou, Guy Blanchard, and Kate Miranda Malale. "Unsupervised Image Segmentation Parameters Evaluation for Urban Land Use/Land Cover Applications." Geomatics 4, no. 2 (May 12, 2024): 149–72. http://dx.doi.org/10.3390/geomatics4020009.
Повний текст джерелаАнотація:
Image segmentation plays an important role in object-based classification. An optimal image segmentation should result in objects being internally homogeneous and, at the same time, distinct from one another. Strategies that assess the quality of image segmentation through intra- and inter-segment homogeneity metrics cannot always predict possible under- and over-segmentations of the image. Although the segmentation scale parameter determines the size of the image segments, it cannot synchronously guarantee that the produced image segments are internally homogeneous and spatially distinct from their neighbors. The majority of image segmentation assessment methods largely rely on a spatial autocorrelation measure that makes the global objective function fluctuate irregularly, resulting in the image variance increasing drastically toward the end of the segmentation. This paper relied on a series of image segmentations to test a more stable image variance measure based on the standard deviation model as well as a more robust hybrid spatial autocorrelation measure based on the current Moran’s index and the spatial autocorrelation coefficient models. The results show that there is a positive and inversely proportional correlation between the inter-segment heterogeneity and the intra-segment homogeneity since the global heterogeneity measure increases with a decrease in the image variance measure. It was also found that medium-scale parameters produced better quality image segments when used with small color weights, while large-scale parameters produced good quality segments when used with large color factor weights. Moreover, with optimal segmentation parameters, the image autocorrelation measure stabilizes and follows a near horizontal fluctuation while the image variance drops to values very close to zero, preventing the heterogeneity function from fluctuating irregularly towards the end of the image segmentation process.
30
Pitkänen, Johanna, Juha Koikkalainen, Tuomas Nieminen, Ivan Marinkovic, Sami Curtze, Gerli Sibolt, Hanna Jokinen, et al. "Evaluating severity of white matter lesions from computed tomography images with convolutional neural network." Neuroradiology 62, no. 10 (April 13, 2020): 1257–63. http://dx.doi.org/10.1007/s00234-020-02410-2.
Повний текст джерелаАнотація:
Abstract Purpose Severity of white matter lesion (WML) is typically evaluated on magnetic resonance images (MRI), yet the more accessible, faster, and less expensive method is computed tomography (CT). Our objective was to study whether WML can be automatically segmented from CT images using a convolutional neural network (CNN). The second aim was to compare CT segmentation with MRI segmentation. Methods The brain images from the Helsinki University Hospital clinical image archive were systematically screened to make CT-MRI image pairs. Selection criteria for the study were that both CT and MRI images were acquired within 6 weeks. In total, 147 image pairs were included. We used CNN to segment WML from CT images. Training and testing of CNN for CT was performed using 10-fold cross-validation, and the segmentation results were compared with the corresponding segmentations from MRI. Results A Pearson correlation of 0.94 was obtained between the automatic WML volumes of MRI and CT segmentations. The average Dice similarity index validating the overlap between CT and FLAIR segmentations was 0.68 for the Fazekas 3 group. Conclusion CNN-based segmentation of CT images may provide a means to evaluate the severity of WML and establish a link between CT WML patterns and the current standard MRI-based visual rating scale.
31
Hong Dien, Le, Nguyen Phuc Son, Pham Hoang Uyen, and Le Van Hinh. "On a segmentation of Coopextra customers in Thu Duc district." Science & Technology Development Journal - Economics - Law and Management 3, no. 1 (May 20, 2019): 28–36. http://dx.doi.org/10.32508/stdjelm.v3i1.537.
Повний текст джерелаАнотація:
Customer segmentation is the process of grouping customers based on similar characteristics such as behavior, shopping habits…so that businesses can do marketing to each customer group effectively and appropriately. Customer segmentation helps businesses determine different strategies and different marketing approaches to different groups. Customer segmentation helps marketers better understand customers as well as provide goals, strategies and marketing methods for different target groups. This paper aims to examine the customer segmentation using clustering method in statistics and unsupervised machine learning. The algorithms used are K-means and Elbow which are famous algorithms that have been successfully applied in many areas such as marketing, biology, library, insurance, finance... The purpose of clustering is to find meaningful market segments. However, the adoption and adjustment of parameters in the algorithms so as to find significant customer segmentations remain a challenge at present. In this paper, we used data of customers of Thu Duc CoopExtra and found significant customer segmentations which can be useful for more effective marketing and customer care by the supermarket.
32
Guo, Songyi, Zhiming Wang, Daju Shi, Quanshu Zeng, Jianguo Zhang, Haitao Li, Yunhui Deng, and Heng Xue. "Research on Segmentation Methods of Horizontal Wells." Journal of Physics: Conference Series 2650, no. 1 (November 1, 2023): 012018. http://dx.doi.org/10.1088/1742-6596/2650/1/012018.
Повний текст джерелаАнотація:
Abstract To equalize the inflow profile of horizontal well and reduce the influence of water breakthrough, the horizontal well should be divided into several sections. The problem of horizontal well segmentation can be classified into two types. The first one is how to segment with sufficient data, and the second one is how to segment with insufficient data. For the former, three segmentation methods have been proposed, named uniform segmentation method, ordered clustering segmentation method, and optimization segmentation method. In this study, for further indicate the application scope and condition of these three methods, the advantages and disadvantages of each method are fully studied. For the latter, the influence of reservoir parameter uncertainty should be considered. In this study, the segmentation method based on robust optimization is proposed to solve this problem. Assume that the horizontal well could be divided into 5 segmentations. For horizontal wells with sufficient data, three segmentation methods are discussed and compared through reservoir simulation. Results show that, in terms of cumulative oil production, the optimization segmentation method is the highest, followed by the ordered clustering segmentation method, and the uniform segmentation method is the lowest. In terms of simulation time, the optimization segmentation method is the longest because the optimal segmentation scheme will be found after iterative simulation. The ordered clustering segmentation method and the uniform segmentation method do not need iterations, so the segmentation scheme could be determined quickly. Therefore, if the computational cost is available, the optimization segmentation method is recommended; if not, the ordered clustering segmentation method is recommended. For horizontal wells with insufficient data, the segmentation method based on robust optimization proposed in this study has been proven to be effective, because the cumulative oil production of this method is greater than that of the uniform segmentation method. In conclusion, the segmentation strategies for horizontal wells with sufficient or insufficient data are presented and discussed. It will contribute to the completion design of horizontal well. Meanwhile, it will also help to delay water breakthrough and enhance oil production.
33
Warfield, Simon K., Kelly H. Zou, and William M. Wells. "Validation of image segmentation by estimating rater bias and variance." Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences 366, no. 1874 (April 11, 2008): 2361–75. http://dx.doi.org/10.1098/rsta.2008.0040.
Повний текст джерелаАнотація:
The accuracy and precision of segmentations of medical images has been difficult to quantify in the absence of a ‘ground truth’ or reference standard segmentation for clinical data. Although physical or digital phantoms can help by providing a reference standard, they do not allow the reproduction of the full range of imaging and anatomical characteristics observed in clinical data. An alternative assessment approach is to compare with segmentations generated by domain experts. Segmentations may be generated by raters who are trained experts or by automated image analysis algorithms. Typically, these segmentations differ due to intra-rater and inter-rater variability. The most appropriate way to compare such segmentations has been unclear. We present here a new algorithm to enable the estimation of performance characteristics, and a true labelling, from observations of segmentations of imaging data where segmentation labels may be ordered or continuous measures. This approach may be used with, among others, surface, distance transform or level-set representations of segmentations, and can be used to assess whether or not a rater consistently overestimates or underestimates the position of a boundary.
34
Fan, Fan, Xiangfeng Zeng, Shunjun Wei, Hao Zhang, Dianhua Tang, Jun Shi, and Xiaoling Zhang. "Efficient Instance Segmentation Paradigm for Interpreting SAR and Optical Images." Remote Sensing 14, no. 3 (January 23, 2022): 531. http://dx.doi.org/10.3390/rs14030531.
Повний текст джерелаАнотація:
Instance segmentation in remote sensing images is challenging due to the object-level discrimination and pixel-level segmentation for the objects. In remote sensing applications, instance segmentation adopts the instance-aware mask, rather than horizontal bounding box and oriented bounding box in object detection, or category-aware mask in semantic segmentation, to interpret the objects with the boundaries. Despite these distinct advantages, versatile instance segmentation methods are still to be discovered for remote sensing images. In this paper, an efficient instance segmentation paradigm (EISP) for interpreting the synthetic aperture radar (SAR) and optical images is proposed. EISP mainly consists of the Swin Transformer to construct the hierarchical features of SAR and optical images, the context information flow (CIF) for interweaving the semantic features from the bounding box branch to mask branch, and the confluent loss function for refining the predicted masks. Experimental conclusions can be drawn on the PSeg-SSDD (Polygon Segmentation—SAR Ship Detection Dataset) and NWPU VHR-10 instance segmentation dataset (optical dataset): (1) Swin-L, CIF, and confluent loss function in EISP acts on the whole instance segmentation utility; (2) EISP* exceeds vanilla mask R-CNN 4.2% AP value on PSeg-SSDD and 11.2% AP on NWPU VHR-10 instance segmentation dataset; (3) The poorly segmented masks, false alarms, missing segmentations, and aliasing masks can be avoided to a great extent for EISP* in segmenting the SAR and optical images; (4) EISP* achieves the highest instance segmentation AP value compared to the state-of-the-art instance segmentation methods.
35
Xiong, Hui, Laith R. Sultan, Theodore W. Cary, Susan M. Schultz, Ghizlane Bouzghar, and Chandra M. Sehgal. "The diagnostic performance of leak-plugging automated segmentation versus manual tracing of breast lesions on ultrasound images." Ultrasound 25, no. 2 (January 25, 2017): 98–106. http://dx.doi.org/10.1177/1742271x17690425.
Повний текст джерелаАнотація:
Purpose To assess the diagnostic performance of a leak-plugging segmentation method that we have developed for delineating breast masses on ultrasound images. Materials and methods Fifty-two biopsy-proven breast lesion images were analyzed by three observers using the leak-plugging and manual segmentation methods. From each segmentation method, grayscale and morphological features were extracted and classified as malignant or benign by logistic regression analysis. The performance of leak-plugging and manual segmentations was compared by: size of the lesion, overlap area ( Oa) between the margins, and area under the ROC curves ( Az). Results The lesion size from leak-plugging segmentation correlated closely with that from manual tracing ( R2 of 0.91). Oa was higher for leak plugging, 0.92 ± 0.01 and 0.86 ± 0.06 for benign and malignant masses, respectively, compared to 0.80 ± 0.04 and 0.73 ± 0.02 for manual tracings. Overall Oa between leak-plugging and manual segmentations was 0.79 ± 0.14 for benign and 0.73 ± 0.14 for malignant lesions. Az for leak plugging was consistently higher (0.910 ± 0.003) compared to 0.888 ± 0.012 for manual tracings. The coefficient of variation of Az between three observers was 0.29% for leak plugging compared to 1.3% for manual tracings. Conclusion The diagnostic performance, size measurements, and observer variability for automated leak-plugging segmentations were either comparable to or better than those of manual tracings.
36
Dadras, Armin A., and Philipp Aichinger. "Deep Learning-Based Detection of Glottis Segmentation Failures." Bioengineering 11, no. 5 (April 30, 2024): 443. http://dx.doi.org/10.3390/bioengineering11050443.
Повний текст джерелаАнотація:
Medical image segmentation is crucial for clinical applications, but challenges persist due to noise and variability. In particular, accurate glottis segmentation from high-speed videos is vital for voice research and diagnostics. Manual searching for failed segmentations is labor-intensive, prompting interest in automated methods. This paper proposes the first deep learning approach for detecting faulty glottis segmentations. For this purpose, faulty segmentations are generated by applying both a poorly performing neural network and perturbation procedures to three public datasets. Heavy data augmentations are added to the input until the neural network’s performance decreases to the desired mean intersection over union (IoU). Likewise, the perturbation procedure involves a series of image transformations to the original ground truth segmentations in a randomized manner. These data are then used to train a ResNet18 neural network with custom loss functions to predict the IoU scores of faulty segmentations. This value is then thresholded with a fixed IoU of 0.6 for classification, thereby achieving 88.27% classification accuracy with 91.54% specificity. Experimental results demonstrate the effectiveness of the presented approach. Contributions include: (i) a knowledge-driven perturbation procedure, (ii) a deep learning framework for scoring and detecting faulty glottis segmentations, and (iii) an evaluation of custom loss functions.
37
Zeng, Xiangfeng, Shunjun Wei, Jinshan Wei, Zichen Zhou, Jun Shi, Xiaoling Zhang, and Fan Fan. "CPISNet: Delving into Consistent Proposals of Instance Segmentation Network for High-Resolution Aerial Images." Remote Sensing 13, no. 14 (July 15, 2021): 2788. http://dx.doi.org/10.3390/rs13142788.
Повний текст джерелаАнотація:
Instance segmentation of high-resolution aerial images is challenging when compared to object detection and semantic segmentation in remote sensing applications. It adopts boundary-aware mask predictions, instead of traditional bounding boxes, to locate the objects-of-interest in pixel-wise. Meanwhile, instance segmentation can distinguish the densely distributed objects within a certain category by a different color, which is unavailable in semantic segmentation. Despite the distinct advantages, there are rare methods which are dedicated to the high-quality instance segmentation for high-resolution aerial images. In this paper, a novel instance segmentation method, termed consistent proposals of instance segmentation network (CPISNet), for high-resolution aerial images is proposed. Following top-down instance segmentation formula, it adopts the adaptive feature extraction network (AFEN) to extract the multi-level bottom-up augmented feature maps in design space level. Then, elaborated RoI extractor (ERoIE) is designed to extract the mask RoIs via the refined bounding boxes from proposal consistent cascaded (PCC) architecture and multi-level features from AFEN. Finally, the convolution block with shortcut connection is responsible for generating the binary mask for instance segmentation. Experimental conclusions can be drawn on the iSAID and NWPU VHR-10 instance segmentation dataset: (1) Each individual module in CPISNet acts on the whole instance segmentation utility; (2) CPISNet* exceeds vanilla Mask R-CNN 3.4%/3.8% AP on iSAID validation/test set and 9.2% AP on NWPU VHR-10 instance segmentation dataset; (3) The aliasing masks, missing segmentations, false alarms, and poorly segmented masks can be avoided to some extent for CPISNet; (4) CPISNet receives high precision of instance segmentation for aerial images and interprets the objects with fitting boundary.
38
Wang, Guodong, Jie Xu, Qian Dong, and Zhenkuan Pan. "Active Contour Model Coupling with Higher Order Diffusion for Medical Image Segmentation." International Journal of Biomedical Imaging 2014 (2014): 1–8. http://dx.doi.org/10.1155/2014/237648.
Повний текст джерелаАнотація:
Active contour models are very popular in image segmentation. Different features such as mean gray and variance are selected for different purpose. But for image with intensity inhomogeneities, there are no features for segmentation using the active contour model. The images with intensity inhomogeneities often occurred in real world especially in medical images. To deal with the difficulties raised in image segmentation with intensity inhomogeneities, a new active contour model with higher-order diffusion method is proposed. With the addition of gradient and Laplace information, the active contour model can converge to the edge of the image even with the intensity inhomogeneities. Because of the introduction of Laplace information, the difference scheme becomes more difficult. To enhance the efficiency of the segmentation, the fast Split Bregman algorithm is designed for the segmentation implementation. The performance of our method is demonstrated through numerical experiments of some medical image segmentations with intensity inhomogeneities.
39
Wei, Yun Tao, and Yi Bing Zhou. "Segmentations of Liver and Hepatic Tumors from 3D Computed Tomography Abdominal Images." Advanced Materials Research 898 (February 2014): 684–87. http://dx.doi.org/10.4028/www.scientific.net/amr.898.684.
Повний текст джерелаАнотація:
The segmentation of liver using computed tomography (CT) data has gained a lot of importance in the medical image processing field. In this paper, we present a survey on liver segmentation methods and techniques using CT images for liver segmentation. An adaptive initialization method was developed to produce fully automatic processing frameworks based on graph-cut and gradient flow active contour algorithms. This method was applied to abdominal Computed Tomography (CT) images for segmentation of liver tissue and hepatic tumors. Twenty-five anonymized datasets were randomly collected from several radiology centres without specific request on acquisition parameter settings nor patient clinical situation as inclusion criteria. Resulting automatic segmentations of liver tissue and tumors were compared to their reference standard delineations manually performed by a specialist. Segmentation accuracy has been assessed through the following evaluation framework: dice similarity coefficient, false negative ratio, false positive ratio and processing time. The implemented initialization method allows fully automatic segmentation leading to superior overall performances of graph-cut algorithm in terms of accuracy and processing time. The initialization method here presented resulted suitable and reliable for two different segmentation techniques and could be further extended.
40
Bai, Shurui, Zhuo Deng, Jingyan Yang, Zheng Gong, Weihao Gao, Lei Shao, Fang Li, Wenbin Wei, and Lan Ma. "FTSNet: Fundus Tumor Segmentation Network on Multiple Scales Guided by Classification Results and Prompts." Bioengineering 11, no. 9 (September 22, 2024): 950. http://dx.doi.org/10.3390/bioengineering11090950.
Повний текст джерелаАнотація:
The segmentation of fundus tumors is critical for ophthalmic diagnosis and treatment, yet it presents unique challenges due to the variability in lesion size and shape. Our study introduces Fundus Tumor Segmentation Network (FTSNet), a novel segmentation network designed to address these challenges by leveraging classification results and prompt learning. Our key innovation is the multiscale feature extractor and the dynamic prompt head. Multiscale feature extractors are proficient in eliciting a spectrum of feature information from the original image across disparate scales. This proficiency is fundamental for deciphering the subtle details and patterns embedded in the image at multiple levels of granularity. Meanwhile, a dynamic prompt head is engineered to engender bespoke segmentation heads for each image, customizing the segmentation process to align with the distinctive attributes of the image under consideration. We also present the Fundus Tumor Segmentation (FTS) dataset, comprising 254 pairs of fundus images with tumor lesions and reference segmentations. Experiments demonstrate FTSNet’s superior performance over existing methods, achieving a mean Intersection over Union (mIoU) of 0.8254 and mean Dice (mDice) of 0.9042. The results highlight the potential of our approach in advancing the accuracy and efficiency of fundus tumor segmentation.
41
Nguyen, Philon, Thanh An Nguyen, and Yong Zeng. "Segmentation of design protocol using EEG." Artificial Intelligence for Engineering Design, Analysis and Manufacturing 33, no. 1 (April 3, 2018): 11–23. http://dx.doi.org/10.1017/s0890060417000622.
Повний текст джерелаАнотація:
AbstractDesign protocol data analysis methods form a well-known set of techniques used by design researchers to further understand the conceptual design process. Verbal protocols are a popular technique used to analyze design activities. However, verbal protocols are known to have some limitations. A recurring problem in design protocol analysis is to segment and code protocol data into logical and semantic units. This is usually a manual step and little work has been done on fully automated segmentation techniques. Physiological signals such as electroencephalograms (EEG) can provide assistance in solving this problem. Such problems are typical inverse problems that occur in the line of research. A thought process needs to be reconstructed from its output, an EEG signal. We propose an EEG-based method for design protocol coding and segmentation. We provide experimental validation of our methods and compare manual segmentation by domain experts to algorithmic segmentation using EEG. The best performing automated segmentation method (when manual segmentation is the baseline) is found to have an average deviation from manual segmentations of 2 s. Furthermore, EEG-based segmentation can identify cognitive structures that simple observation of design protocols cannot. EEG-based segmentation does not replace complex domain expert segmentation but rather complements it. Techniques such as verbal protocols are known to fail in some circumstances. EEG-based segmentation has the added feature that it is fully automated and can be readily integrated in engineering systems and subsystems. It is effectively a window into the mind.
42
Barteček, R., N. E. M. van Haren, P. C. M. P. Koolschijn, H. E. Hulshoff Pol, and R. S. Kahn. "Comparison of manual and automatic methods of hippocampus segmentation." European Psychiatry 26, S2 (March 2011): 914. http://dx.doi.org/10.1016/s0924-9338(11)72619-0.
Повний текст джерелаАнотація:
IntroductionPsychiatric Patients show abnormalities in volumes of several subcortical structures. Recently wider usage of automated segmentation methods in research of these abnormalities based on MR images has become possible. However manual segmentation is still considered to be the gold standard.ObjectivesTo compare differences in hippocampus volumes between manual segmentation and 2 packages for automatic segmentation (FSL and FreeSurfer).AimTo explore the overlap and differences between different segmentation methods used for segmentation of subcortical structures.MethodsStructural MR brain scans were aquired from 98 subjects (53 schizophrenia patients, 45 controls). Volumes of left and right hippocampus were measured after manual, FreeSurfer and FSL segmentations. Differences between volumes from different methods were tested by the t-test (using R). In addition percent volume differences, Pearson correlations, Bland-Altman plots and Cronbach’s alpha were computed.ResultsBoth automatic methods yielded significantly larger hippocampal volumes than the manual segmentation. FreeSurfer volumes showed a higher correlation and lower percent volume difference with manual segmentation than FSL. Bland-Altman plots and Cronbach’s alpha showed only limited agreement between manual and both automatic methods.ConclusionsAlthough volumes acquired by FreeSurfer appeared to be more related to manual segmentation, clear superiority of either of automatic methods could not be demonstrated. Therefore, all three methods seem to measure other aspects of hippocampus volume. An useful approach would be to compare effect-size of the difference between patients and healthy controls using different segmentation methods. We are currently pursuing this in a larger sample.
43
Aydin, Orhun Utku, Abdel Aziz Taha, Adam Hilbert, Ahmed A. Khalil, Ivana Galinovic, Jochen B. Fiebach, Dietmar Frey, and Vince Istvan Madai. "An evaluation of performance measures for arterial brain vessel segmentation." BMC Medical Imaging 21, no. 1 (July 16, 2021). http://dx.doi.org/10.1186/s12880-021-00644-x.
Повний текст джерелаАнотація:
Abstract Background Arterial brain vessel segmentation allows utilising clinically relevant information contained within the cerebral vascular tree. Currently, however, no standardised performance measure is available to evaluate the quality of cerebral vessel segmentations. Thus, we developed a performance measure selection framework based on manual visual scoring of simulated segmentation variations to find the most suitable measure for cerebral vessel segmentation. Methods To simulate segmentation variations, we manually created non-overlapping segmentation errors common in magnetic resonance angiography cerebral vessel segmentation. In 10 patients, we generated a set of approximately 300 simulated segmentation variations for each ground truth image. Each segmentation was visually scored based on a predefined scoring system and segmentations were ranked based on 22 performance measures common in the literature. The correlation of visual scores with performance measure rankings was calculated using the Spearman correlation coefficient. Results The distance-based performance measures balanced average Hausdorff distance (rank = 1) and average Hausdorff distance (rank = 2) provided the segmentation rankings with the highest average correlation with manual rankings. They were followed by overlap-based measures such as Dice coefficient (rank = 7), a standard performance measure in medical image segmentation. Conclusions Average Hausdorff distance-based measures should be used as a standard performance measure in evaluating cerebral vessel segmentation quality. They can identify more relevant segmentation errors, especially in high-quality segmentations. Our findings have the potential to accelerate the validation and development of novel vessel segmentation approaches.
44
Aydin, Orhun Utku, Abdel Aziz Taha, Adam Hilbert, Ahmed A. Khalil, Ivana Galinovic, Jochen B. Fiebach, Dietmar Frey, and Vince Istvan Madai. "On the usage of average Hausdorff distance for segmentation performance assessment: hidden error when used for ranking." European Radiology Experimental 5, no. 1 (January 21, 2021). http://dx.doi.org/10.1186/s41747-020-00200-2.
Повний текст джерелаАнотація:
AbstractAverage Hausdorff distance is a widely used performance measure to calculate the distance between two point sets. In medical image segmentation, it is used to compare ground truth images with segmentations allowing their ranking. We identified, however, ranking errors of average Hausdorff distance making it less suitable for applications in segmentation performance assessment. To mitigate this error, we present a modified calculation of this performance measure that we have coined “balanced average Hausdorff distance”. To simulate segmentations for ranking, we manually created non-overlapping segmentation errors common in magnetic resonance angiography cerebral vessel segmentation as our use-case. Adding the created errors consecutively and randomly to the ground truth, we created sets of simulated segmentations with increasing number of errors. Each set of simulated segmentations was ranked using both performance measures. We calculated the Kendall rank correlation coefficient between the segmentation ranking and the number of errors in each simulated segmentation. The rankings produced by balanced average Hausdorff distance had a significantly higher median correlation (1.00) than those by average Hausdorff distance (0.89). In 200 total rankings, the former misranked 52 whilst the latter misranked 179 segmentations. Balanced average Hausdorff distance is more suitable for rankings and quality assessment of segmentations than average Hausdorff distance.
45
Saillard, Emile, Marc Gardegaront, Aurélie Levillain, François Bermond, David Mitton, Jean-Baptiste Pialat, Cyrille Confavreux, Thomas Grenier, and Hélène Follet. "Finite element models with automatic computed tomography bone segmentation for failure load computation." Scientific Reports 14, no. 1 (July 17, 2024). http://dx.doi.org/10.1038/s41598-024-66934-w.
Повний текст джерелаАнотація:
AbstractBone segmentation is an important step to perform biomechanical failure load simulations on in-vivo CT data of patients with bone metastasis, as it is a mandatory operation to obtain meshes needed for numerical simulations. Segmentation can be a tedious and time consuming task when done manually, and expert segmentations are subject to intra- and inter-operator variability. Deep learning methods are increasingly employed to automatically carry out image segmentation tasks. These networks usually need to be trained on a large image dataset along with the manual segmentations to maximize generalization to new images, but it is not always possible to have access to a multitude of CT-scans with the associated ground truth. It then becomes necessary to use training techniques to make the best use of the limited available data. In this paper, we propose a dedicated pipeline of preprocessing, deep learning based segmentation method and post-processing for in-vivo human femurs and vertebrae segmentation from CT-scans volumes. We experimented with three U-Net architectures and showed that out-of-the-box models enable automatic and high-quality volume segmentation if carefully trained. We compared the failure load simulation results obtained on femurs and vertebrae using either automatic or manual segmentations and studied the sensitivity of the simulations on small variations of the automatic segmentation. The failure loads obtained using automatic segmentations were comparable to those obtained using manual expert segmentations for all the femurs and vertebrae tested, demonstrating the effectiveness of the automated segmentation approach for failure load simulations.
46
Meglič, Jakob, Mohammed R. S. Sunoqrot, Tone Frost Bathen, and Mattijs Elschot. "Label-set impact on deep learning-based prostate segmentation on MRI." Insights into Imaging 14, no. 1 (September 25, 2023). http://dx.doi.org/10.1186/s13244-023-01502-w.
Повний текст джерелаАнотація:
Abstract Background Prostate segmentation is an essential step in computer-aided detection and diagnosis systems for prostate cancer. Deep learning (DL)-based methods provide good performance for prostate gland and zones segmentation, but little is known about the impact of manual segmentation (that is, label) selection on their performance. In this work, we investigated these effects by obtaining two different expert label-sets for the PROSTATEx I challenge training dataset (n = 198) and using them, in addition to an in-house dataset (n = 233), to assess the effect on segmentation performance. The automatic segmentation method we used was nnU-Net. Results The selection of training/testing label-set had a significant (p < 0.001) impact on model performance. Furthermore, it was found that model performance was significantly (p < 0.001) higher when the model was trained and tested with the same label-set. Moreover, the results showed that agreement between automatic segmentations was significantly (p < 0.0001) higher than agreement between manual segmentations and that the models were able to outperform the human label-sets used to train them. Conclusions We investigated the impact of label-set selection on the performance of a DL-based prostate segmentation model. We found that the use of different sets of manual prostate gland and zone segmentations has a measurable impact on model performance. Nevertheless, DL-based segmentation appeared to have a greater inter-reader agreement than manual segmentation. More thought should be given to the label-set, with a focus on multicenter manual segmentation and agreement on common procedures. Critical relevance statement Label-set selection significantly impacts the performance of a deep learning-based prostate segmentation model. Models using different label-set showed higher agreement than manual segmentations. Key points • Label-set selection has a significant impact on the performance of automatic segmentation models. • Deep learning-based models demonstrated true learning rather than simply mimicking the label-set. • Automatic segmentation appears to have a greater inter-reader agreement than manual segmentation. Graphical Abstract
47
Niemann, Annika, Naomi Larsen, Bernhard Preim, and Sylvia Saalfeld. "Wall enhancement segmentation for intracranial aneurysm." Current Directions in Biomedical Engineering 6, no. 1 (September 17, 2020). http://dx.doi.org/10.1515/cdbme-2020-0045.
Повний текст джерелаАнотація:
AbstractWe present a tool for automatic segmentation of wall enhancement of intracranial aneurysms in black blood MRI. The results of the automatic segmentation with several configurations is compared to manual expert segmentations. While the manual segmentation includes some voxels of lower intensity not present in the automatic segmentation, overall the volume of the automatic segmentation is higher.
48
"Automatic Vertebral Body Segmentation using Semantic Segmentation." International Journal of Recent Technology and Engineering 8, no. 4 (November 30, 2019): 12163–67. http://dx.doi.org/10.35940/ijrte.d8584.118419.
Повний текст джерелаАнотація:
Segmentation of vertebral bodies (VB) is a preliminary and useful step for the diagnosis of spine pathologies, deformations and fractures caused due to various reasons. We present a method to address this challenging problem of VB segmentation using a trending method – Semantic Segmentation (SS). The objective of semantic segmentation of images usually consisting of three main components - convolutions, downsampling, and upsampling layers is to mark every pixel of an image with a correlating class of what is being described. In this study, we developed a unique automatic semantic segmentation architecture to segment the VB from Computed Tomography (CT) images, and we compared our segmentation results with reference segmentations obtained by the experts. We evaluated the proposed method on a publicly available dataset and achieved an average accuracy of 94.16% and an average Dice Similarity Coefficient (DSC) of 93.51% for VB segmentation.
49
Kock, Farina, Felix Thielke, Nasreddin Abolmaali, Hans Meine, and Andrea Schenk. "Suitability of DNN-based vessel segmentation for SIRT planning." International Journal of Computer Assisted Radiology and Surgery, August 3, 2023. http://dx.doi.org/10.1007/s11548-023-03005-x.
Повний текст джерелаАнотація:
Abstract Purpose The segmentation of the hepatic arteries (HA) is essential for state-of-the-art pre-interventional planning of selective internal radiation therapy (SIRT), a treatment option for malignant tumors in the liver. In SIRT a catheter is placed through the aorta into the tumor-feeding hepatic arteries, injecting small beads filled with radiation emitting material for local radioembolization. In this study, we evaluate the suitability of a deep neural network (DNN) based vessel segmentation for SIRT planning. Methods We applied our DNN-based HA segmentation on 36 contrast-enhanced computed tomography (CT) scans from the arterial contrast agent phase and rated its segmentation quality as well as the overall image quality. Additionally, we applied a traditional machine learning algorithm for HA segmentation as comparison to our deep learning (DL) approach. Moreover, we assessed by expert ratings whether the produced HA segmentations can be used for SIRT planning. Results The DL approach outperformed the traditional machine learning algorithm. The DL segmentation can be used for SIRT planning in $$61\%$$ 61 % of the cases, while the reference segmentations, which were manually created by experienced radiographers, are sufficient in $$75\%$$ 75 % . Seven DL cases cannot be used for SIRT planning while the corresponding reference segmentations are sufficient. However, there are two DL segmentations usable for SIRT, where the reference segmentations for the same cases were rated as insufficient. Conclusions HA segmentation is a difficult and time-consuming task. DL-based methods have the potential to support and accelerate the pre-interventional planning of SIRT therapy.
50
TIRADO-VELEZ, PEDRO L., SANGHOON KANG, HUIWEN JU, MARTHA CAMPBELL-THOMPSON, SARAH KIM, and DAMON LAMB. "78-PUB: Machine Learning–Assisted Segmentation of Pancreas MRI." Diabetes 73, Supplement_1 (June 14, 2024). http://dx.doi.org/10.2337/db24-78-pub.
Повний текст джерелаАнотація:
Introduction & Objective: Pancreas volume (PV) may be a useful biomarker for T1D, but manual segmentation of PV from an MRI is time consuming. The objective of this project was to develop and evaluate the efficiency of a machine-learning (ML) pipeline for pancreas MRI segmentation to calculate pancreas volume. Methods: Manual and ML-assisted PV MRI segmentations were created from a sample of 68 including 15 controls (no diabetes) from an existing dataset (PMID: 30552130). We linked a local 3D Slicer (PMID: 22770690) instance with a hardware-accelerated MONAI Label server instance on the UF HiPerGator cluster for our ML-assisted segmentations. We evaluated the relative efficiency of ML-assisted vs. manual to create high quality segmentation of the pancreas. Results: ML-assisted segmentations are of high-quality. ML-assisted segmentation resulted in a reduction of average time per segmentation by 5 minutes and a reduction of average total mouse-clicks by 28% when completed by a minimally-trained (non-radiologist) staff. Conclusion: ML-assted segmentation can result in significant productivity gains for pancreas segmentation without loss of data quality or accuracy, reducing costs associated with radiological MRI segmentation for PV. Disclosure P.L. Tirado-Velez: None. S. Kang: None. H. Ju: None. M. Campbell-Thompson: None. S. Kim: None. D. Lamb: None. Funding JDRF (3-SRA-2022-1157-S-B)