Pub Date : 2017-04-18DOI: 10.1109/ISBI.2017.7950475
C. Gomez, Luca Dodero, A. Gozzi, Vittorio Murino, Diego Sona
Diffusion tensor imaging allows to infer brain connectivity from white matter, which can then be investigated aiming at finding possible biomarkers of disease. The usual initial step in graph construction is to identify the nodes in the brain using a predefined atlas. However, atlases are usually not considering the white matter structure. As a result, atlas-based brain parcellation and, hence, brain graphs are not fully considering the white matter organization. In this work, we are proposing an atlas-free scheme to map the structural brain networks. The idea is to identify the nodes in the brain exploiting the white matter structure inferred from the data. We first retrieve the white matter pathways from DTI, grouping fiber tracts into bundles. We then use these pathways in a clustering pipeline to identify the brain regions to map into the graph nodes, which are used to define the brain connectivity. We empirically tested the goodness of the proposed approach on a known case-control study obtaining results confirming findings in related literature.
{"title":"Atlas-free connectivity analysis driven by white matter structure","authors":"C. Gomez, Luca Dodero, A. Gozzi, Vittorio Murino, Diego Sona","doi":"10.1109/ISBI.2017.7950475","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950475","url":null,"abstract":"Diffusion tensor imaging allows to infer brain connectivity from white matter, which can then be investigated aiming at finding possible biomarkers of disease. The usual initial step in graph construction is to identify the nodes in the brain using a predefined atlas. However, atlases are usually not considering the white matter structure. As a result, atlas-based brain parcellation and, hence, brain graphs are not fully considering the white matter organization. In this work, we are proposing an atlas-free scheme to map the structural brain networks. The idea is to identify the nodes in the brain exploiting the white matter structure inferred from the data. We first retrieve the white matter pathways from DTI, grouping fiber tracts into bundles. We then use these pathways in a clustering pipeline to identify the brain regions to map into the graph nodes, which are used to define the brain connectivity. We empirically tested the goodness of the proposed approach on a known case-control study obtaining results confirming findings in related literature.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"46 1","pages":"89-92"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85261365","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-04-18DOI: 10.1109/ISBI.2017.7950483
Ardalan Benam, M. S. Drew, M. S. Atkins
We designed a content based image retrieval (CBIR) system for dermoscopic images focusing on images with pigment networks. The system locates and matches a query image that has a pigment network with the most similar images containing pigment networks in a database of dermoscopic images. Dermoscopy interest points in the query image are detected and a vector of 128 features is extracted as the descriptor from each keypoint. Then, the descriptors are matched according to our matching algorithm to similar features arising in the database images. This leads to a meaningful matching as we are matching similar dermoscopy structures with each other. The performance of the system has been tested on more than 1000 images. Results show that our system will locate and retrieve similar images with pigment networks, with accuracy > 75.4%. This system can help physicians in diagnosis as they are shown similar looking dermoscopy images with known pathology.
{"title":"A CBIR system for locating and retrieving pigment network in dermoscopy images using dermoscopy interest point detection","authors":"Ardalan Benam, M. S. Drew, M. S. Atkins","doi":"10.1109/ISBI.2017.7950483","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950483","url":null,"abstract":"We designed a content based image retrieval (CBIR) system for dermoscopic images focusing on images with pigment networks. The system locates and matches a query image that has a pigment network with the most similar images containing pigment networks in a database of dermoscopic images. Dermoscopy interest points in the query image are detected and a vector of 128 features is extracted as the descriptor from each keypoint. Then, the descriptors are matched according to our matching algorithm to similar features arising in the database images. This leads to a meaningful matching as we are matching similar dermoscopy structures with each other. The performance of the system has been tested on more than 1000 images. Results show that our system will locate and retrieve similar images with pigment networks, with accuracy > 75.4%. This system can help physicians in diagnosis as they are shown similar looking dermoscopy images with known pathology.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"57 1","pages":"122-125"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91025434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-04-18DOI: 10.1109/ISBI.2017.7950639
A. Schuh, A. Makropoulos, R. Wright, E. Robinson, N. Tusor, J. Steinweg, E. Hughes, Lucilio Cordero-Grande, A. Price, J. Hutter, J. Hajnal, D. Rueckert
We present a method based on deformable meshes for the reconstruction of the cortical surfaces of the developing human brain at the neonatal period. It employs a brain segmentation for the reconstruction of an initial inner cortical surface mesh. Errors in the segmentation resulting from poor tissue contrast in neonatal MRI and partial volume effects are subsequently accounted for by a local edge-based refinement. We show that the obtained surface models define the cortical boundaries more accurately than the segmentation. The surface meshes are further guaranteed to not intersect and subdivide the brain volume into disjoint regions. The proposed method generates topologically correct surfaces which facilitate both a flattening and spherical mapping of the cortex.
{"title":"A deformable model for the reconstruction of the neonatal cortex","authors":"A. Schuh, A. Makropoulos, R. Wright, E. Robinson, N. Tusor, J. Steinweg, E. Hughes, Lucilio Cordero-Grande, A. Price, J. Hutter, J. Hajnal, D. Rueckert","doi":"10.1109/ISBI.2017.7950639","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950639","url":null,"abstract":"We present a method based on deformable meshes for the reconstruction of the cortical surfaces of the developing human brain at the neonatal period. It employs a brain segmentation for the reconstruction of an initial inner cortical surface mesh. Errors in the segmentation resulting from poor tissue contrast in neonatal MRI and partial volume effects are subsequently accounted for by a local edge-based refinement. We show that the obtained surface models define the cortical boundaries more accurately than the segmentation. The surface meshes are further guaranteed to not intersect and subdivide the brain volume into disjoint regions. The proposed method generates topologically correct surfaces which facilitate both a flattening and spherical mapping of the cortex.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"37 1","pages":"800-803"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74054434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-04-18DOI: 10.1109/ISBI.2017.7950514
B. Bozorgtabar, ZongYuan Ge, R. Chakravorty, Mani Abedini, S. Demyanov, R. Garnavi
Accurate skin lesion segmentation is an important yet challenging problem for medical image analysis. The skin lesion segmentation is subject to variety of challenges such as the significant pattern and colour diversity found within the lesions, presence of various artifacts, etc. In this paper, we present two fully convolutional networks with several side outputs to take advantage of discriminative capability of features learned at intermediate layers with varying resolutions and scales for the lesion segmentation. More specifically, we integrate fine and coarse prediction scores of the side-layers which allows our framework to not only output accurate probability map for the lesion, but also extract fine lesion boundary details such as the fuzzy border, which further improves the lesion segmentation. Quantitative evaluation is performed on the 2016 International Symposium on Biomedical Imaging (ISBI 2016) dataset, which shows our proposed approach compares favorably with state-of-the-art skin segmentation methods.
{"title":"Investigating deep side layers for skin lesion segmentation","authors":"B. Bozorgtabar, ZongYuan Ge, R. Chakravorty, Mani Abedini, S. Demyanov, R. Garnavi","doi":"10.1109/ISBI.2017.7950514","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950514","url":null,"abstract":"Accurate skin lesion segmentation is an important yet challenging problem for medical image analysis. The skin lesion segmentation is subject to variety of challenges such as the significant pattern and colour diversity found within the lesions, presence of various artifacts, etc. In this paper, we present two fully convolutional networks with several side outputs to take advantage of discriminative capability of features learned at intermediate layers with varying resolutions and scales for the lesion segmentation. More specifically, we integrate fine and coarse prediction scores of the side-layers which allows our framework to not only output accurate probability map for the lesion, but also extract fine lesion boundary details such as the fuzzy border, which further improves the lesion segmentation. Quantitative evaluation is performed on the 2016 International Symposium on Biomedical Imaging (ISBI 2016) dataset, which shows our proposed approach compares favorably with state-of-the-art skin segmentation methods.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"49 1","pages":"256-260"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84744213","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-04-18DOI: 10.1109/ISBI.2017.7950576
Muhammad Naveed Iqbal Qureshi, H. Jo, Boreom Lee
The differential diagnosis among ADHD subtypes is an important research area for the neuroimaging community. We pursue this goal by using machine learning techniques in this study. Selective subjects matched by age and handedness information from publicly available ADHD-200 dataset were used in this study. In addition, this work is based only on the resting-state fMRI images. We calculated the global connectivity maps from the fMRI images and used the average of the connectivity measure of each atlas-based cortical parcellation as a feature for the classifier input. For the classification, we used hierarchical extreme learning machine (H-ELM) classifier. By using the proposed feature extraction method, we achieved a 71.11% (p < 0.0090) nested cross-validated accuracy and a kappa score of 0.57 in multiclass classification settings.
{"title":"ADHD subgroup discrimination with global connectivity features using hierarchical extreme learning machine: Resting-state FMRI study","authors":"Muhammad Naveed Iqbal Qureshi, H. Jo, Boreom Lee","doi":"10.1109/ISBI.2017.7950576","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950576","url":null,"abstract":"The differential diagnosis among ADHD subtypes is an important research area for the neuroimaging community. We pursue this goal by using machine learning techniques in this study. Selective subjects matched by age and handedness information from publicly available ADHD-200 dataset were used in this study. In addition, this work is based only on the resting-state fMRI images. We calculated the global connectivity maps from the fMRI images and used the average of the connectivity measure of each atlas-based cortical parcellation as a feature for the classifier input. For the classification, we used hierarchical extreme learning machine (H-ELM) classifier. By using the proposed feature extraction method, we achieved a 71.11% (p < 0.0090) nested cross-validated accuracy and a kappa score of 0.57 in multiclass classification settings.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"36 1","pages":"529-532"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85358172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-04-18DOI: 10.1109/ISBI.2017.7950532
S. Raza, Linda Cheung, David B. A. Epstein, S. Pelengaris, Michael Khan, N. Rajpoot
We propose a novel multiple-input multiple-output convolution neural network (MIMO-Net) for cell segmentation in fluorescence microscopy images. The proposed network trains the network parameters using multiple resolutions of the input image, connects the intermediate layers for better localization and context and generates the output using multi-resolution deconvolution filters. The MIMO-Net allows us to deal with variable intensity cell boundaries and highly variable cell size in the mouse pancreatic tissue by adding extra convolutional layers which bypass the max-pooling operation. The results show that our method outperforms state-of-the-art deep learning based approaches for segmentation.
{"title":"MIMO-Net: A multi-input multi-output convolutional neural network for cell segmentation in fluorescence microscopy images","authors":"S. Raza, Linda Cheung, David B. A. Epstein, S. Pelengaris, Michael Khan, N. Rajpoot","doi":"10.1109/ISBI.2017.7950532","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950532","url":null,"abstract":"We propose a novel multiple-input multiple-output convolution neural network (MIMO-Net) for cell segmentation in fluorescence microscopy images. The proposed network trains the network parameters using multiple resolutions of the input image, connects the intermediate layers for better localization and context and generates the output using multi-resolution deconvolution filters. The MIMO-Net allows us to deal with variable intensity cell boundaries and highly variable cell size in the mouse pancreatic tissue by adding extra convolutional layers which bypass the max-pooling operation. The results show that our method outperforms state-of-the-art deep learning based approaches for segmentation.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"35 1","pages":"337-340"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90842634","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-04-18DOI: 10.1109/ISBI.2017.7950622
Lucio Azzari, A. Foi
We consider the restoration of blurred images corrupted by Poisson noise using variance-stabilizing transformations (VST). Although VST are an established tool used extensively for denoising, their adoption in deconvolution problems is problematic because VST are necessarily nonlinear operators, and thus break the linear image-formation model typically adopted in deconvolution. We propose a deblurring framework where the image is 1) deconvolved by a linear regularized inverse filter, 2) transformed by VST into an image which can be treated as corrupted by strong spatially correlated noise with constant variance and known power spectrum, 3) denoised by a filter for additive colored Gaussian noise, 4) returned to the original range via inverse VST. We particularly analyze the stabilization of Poisson variates after linear filtering and characterize the noise power spectrum before and after application of VST. We present an efficient implementation of this original deblurring framework using the BM3D denoising filter, demonstrating state-of-the-art results which are especially appealing in low SNR imaging conditions.
{"title":"Variance stabilization in Poisson image deblurring","authors":"Lucio Azzari, A. Foi","doi":"10.1109/ISBI.2017.7950622","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950622","url":null,"abstract":"We consider the restoration of blurred images corrupted by Poisson noise using variance-stabilizing transformations (VST). Although VST are an established tool used extensively for denoising, their adoption in deconvolution problems is problematic because VST are necessarily nonlinear operators, and thus break the linear image-formation model typically adopted in deconvolution. We propose a deblurring framework where the image is 1) deconvolved by a linear regularized inverse filter, 2) transformed by VST into an image which can be treated as corrupted by strong spatially correlated noise with constant variance and known power spectrum, 3) denoised by a filter for additive colored Gaussian noise, 4) returned to the original range via inverse VST. We particularly analyze the stabilization of Poisson variates after linear filtering and characterize the noise power spectrum before and after application of VST. We present an efficient implementation of this original deblurring framework using the BM3D denoising filter, demonstrating state-of-the-art results which are especially appealing in low SNR imaging conditions.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"47 1","pages":"728-731"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86301372","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-04-18DOI: 10.1109/ISBI.2017.7950684
Rudrasis Chakraborty, Monami Banerjee, B. Vemuri
Statistical analysis of longitudinal data is a significant problem in Biomedical imaging applications. In the recent past, several researchers have developed mathematically rigorous methods based on differential geometry and statistics to tackle the problem of statistical analysis of longitudinal neuroimaging data. In this paper, we present a novel formulation of the longitudinal data analysis problem by identifying the structural changes over time (describing the trajectory of change) to a product Riemannian manifold endowed with a Riemannian metric and a probability measure. We present theoretical results showing that the maximum likelihood estimate of the mean and median of a Gaussian and Laplace distribution respectively on the product manifold yield the Fréchet mean and median respectively. We then present efficient recursive estimators for these intrinsic parameters and use them in conjunction with a nearest neighbor (NN) classifier to classify MR brain scans (acquired from the publicly available OASIS database) of patients with and without dementia.
{"title":"Statistics on the space of trajectories for longitudinal data analysis","authors":"Rudrasis Chakraborty, Monami Banerjee, B. Vemuri","doi":"10.1109/ISBI.2017.7950684","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950684","url":null,"abstract":"Statistical analysis of longitudinal data is a significant problem in Biomedical imaging applications. In the recent past, several researchers have developed mathematically rigorous methods based on differential geometry and statistics to tackle the problem of statistical analysis of longitudinal neuroimaging data. In this paper, we present a novel formulation of the longitudinal data analysis problem by identifying the structural changes over time (describing the trajectory of change) to a product Riemannian manifold endowed with a Riemannian metric and a probability measure. We present theoretical results showing that the maximum likelihood estimate of the mean and median of a Gaussian and Laplace distribution respectively on the product manifold yield the Fréchet mean and median respectively. We then present efficient recursive estimators for these intrinsic parameters and use them in conjunction with a nearest neighbor (NN) classifier to classify MR brain scans (acquired from the publicly available OASIS database) of patients with and without dementia.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"12 1","pages":"999-1002"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88808917","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-04-18DOI: 10.1109/ISBI.2017.7950455
Gopal Nataraj, J. Nielsen, J. Fessler
MRI parameter quantification has diverse applications, but likelihood-based methods typically require nonconvex optimization due to nonlinear signal models. To avoid expensive grid searches used in prior works, we propose to learn a nonlinear estimator from simulated training examples and (approximate) kernel ridge regression. As proof of concept, we apply kernel-based estimation to quantify six parameters per voxel describing the steady-state magnetization dynamics of two water compartments from simulated data. In relevant regions of fast-relaxing compartmental fraction estimates, kernel estimation achieves comparable mean-squared error as grid search, with dramatically reduced computation.
{"title":"Dictionary-free MRI parameter estimation via kernel ridge regression","authors":"Gopal Nataraj, J. Nielsen, J. Fessler","doi":"10.1109/ISBI.2017.7950455","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950455","url":null,"abstract":"MRI parameter quantification has diverse applications, but likelihood-based methods typically require nonconvex optimization due to nonlinear signal models. To avoid expensive grid searches used in prior works, we propose to learn a nonlinear estimator from simulated training examples and (approximate) kernel ridge regression. As proof of concept, we apply kernel-based estimation to quantify six parameters per voxel describing the steady-state magnetization dynamics of two water compartments from simulated data. In relevant regions of fast-relaxing compartmental fraction estimates, kernel estimation achieves comparable mean-squared error as grid search, with dramatically reduced computation.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"9 1","pages":"5-9"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77226963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-04-18DOI: 10.1109/ISBI.2017.7950726
C. Lian, S. Ruan, T. Denoeux, Hua Li, P. Vera
While accurate tumor delineation in FDG-PET is a vital task, noisy and blurring imaging system makes it a challenging work. In this paper, we propose to address this issue using the theory of belief functions, a powerful tool for modeling and reasoning with uncertain and/or imprecise information. An automatic segmentation method based on clustering is developed in 3-D, where, different from available methods, PET voxels are described not only by intensities but also complementally by features extracted from patches. Considering there are a large amount of features without consensus regarding the most informative ones, and some of them are even unreliable due to image quality, a specific procedure is adopted to adapt distance metric for properly representing clustering distortions and neighborhood similarities. A specific spatial regularization is also included in the clustering algorithm to effectively quantify local homogeneity. The proposed method has been evaluated by real-patient images, showing good performance.
{"title":"Tumor delineation in FDG-PET images using a new evidential clustering algorithm with spatial regularization and adaptive distance metric","authors":"C. Lian, S. Ruan, T. Denoeux, Hua Li, P. Vera","doi":"10.1109/ISBI.2017.7950726","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950726","url":null,"abstract":"While accurate tumor delineation in FDG-PET is a vital task, noisy and blurring imaging system makes it a challenging work. In this paper, we propose to address this issue using the theory of belief functions, a powerful tool for modeling and reasoning with uncertain and/or imprecise information. An automatic segmentation method based on clustering is developed in 3-D, where, different from available methods, PET voxels are described not only by intensities but also complementally by features extracted from patches. Considering there are a large amount of features without consensus regarding the most informative ones, and some of them are even unreliable due to image quality, a specific procedure is adopted to adapt distance metric for properly representing clustering distortions and neighborhood similarities. A specific spatial regularization is also included in the clustering algorithm to effectively quantify local homogeneity. The proposed method has been evaluated by real-patient images, showing good performance.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"21 1","pages":"1177-1180"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85968362","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：