Graph cut segmentation with a statistical shape model in cardiac MRI. Grosgeorge, D., Petitjean, C., Dacher, J., & Ruan, S. Computer Vision and Image Understanding, 117(9):1027–1035, September, 2013.
Paper doi abstract bibtex Segmenting the right ventricle (RV) in magnetic resonance (MR) images is required for cardiac function assessment. The segmentation of the RV is a difficult task due to low contrast with surrounding tissues and high shape variability. To overcome these problems, we introduce a segmentation method based on a statistical shape model obtained with a principal component analysis (PCA) on a set of representative shapes of the RV. Shapes are not represented by a set of points, but by distance maps to their contour, relaxing the need for a costly landmark detection and matching process. A shape model is thus obtained by computing a PCA on the shape variations. This prior is registered onto the image via a very simple user interaction and then incorporated into the well-known graph cut framework in order to guide the segmentation. Our semi-automatic segmentation method has been applied on 248 MR images of a publicly available dataset (from MICCAI’12 Right Ventricle Segmentation Challenge). We show that encouraging results can be obtained for this challenging application.
@article{grosgeorge_graph_2013,
title = {Graph cut segmentation with a statistical shape model in cardiac {MRI}},
volume = {117},
issn = {10773142},
url = {https://linkinghub.elsevier.com/retrieve/pii/S1077314213000738},
doi = {10.1016/j.cviu.2013.01.014},
abstract = {Segmenting the right ventricle (RV) in magnetic resonance (MR) images is required for cardiac function assessment. The segmentation of the RV is a difficult task due to low contrast with surrounding tissues and high shape variability. To overcome these problems, we introduce a segmentation method based on a statistical shape model obtained with a principal component analysis (PCA) on a set of representative shapes of the RV. Shapes are not represented by a set of points, but by distance maps to their contour, relaxing the need for a costly landmark detection and matching process. A shape model is thus obtained by computing a PCA on the shape variations. This prior is registered onto the image via a very simple user interaction and then incorporated into the well-known graph cut framework in order to guide the segmentation. Our semi-automatic segmentation method has been applied on 248 MR images of a publicly available dataset (from MICCAI’12 Right Ventricle Segmentation Challenge). We show that encouraging results can be obtained for this challenging application.},
language = {en},
number = {9},
urldate = {2021-02-12},
journal = {Computer Vision and Image Understanding},
author = {Grosgeorge, D. and Petitjean, C. and Dacher, J.-N. and Ruan, S.},
month = sep,
year = {2013},
pages = {1027--1035},
}
Downloads: 0
{"_id":"WHFXAQkbpvTfgnDkJ","bibbaseid":"grosgeorge-petitjean-dacher-ruan-graphcutsegmentationwithastatisticalshapemodelincardiacmri-2013","author_short":["Grosgeorge, D.","Petitjean, C.","Dacher, J.","Ruan, S."],"bibdata":{"bibtype":"article","type":"article","title":"Graph cut segmentation with a statistical shape model in cardiac MRI","volume":"117","issn":"10773142","url":"https://linkinghub.elsevier.com/retrieve/pii/S1077314213000738","doi":"10.1016/j.cviu.2013.01.014","abstract":"Segmenting the right ventricle (RV) in magnetic resonance (MR) images is required for cardiac function assessment. The segmentation of the RV is a difficult task due to low contrast with surrounding tissues and high shape variability. To overcome these problems, we introduce a segmentation method based on a statistical shape model obtained with a principal component analysis (PCA) on a set of representative shapes of the RV. Shapes are not represented by a set of points, but by distance maps to their contour, relaxing the need for a costly landmark detection and matching process. A shape model is thus obtained by computing a PCA on the shape variations. This prior is registered onto the image via a very simple user interaction and then incorporated into the well-known graph cut framework in order to guide the segmentation. Our semi-automatic segmentation method has been applied on 248 MR images of a publicly available dataset (from MICCAI’12 Right Ventricle Segmentation Challenge). We show that encouraging results can be obtained for this challenging application.","language":"en","number":"9","urldate":"2021-02-12","journal":"Computer Vision and Image Understanding","author":[{"propositions":[],"lastnames":["Grosgeorge"],"firstnames":["D."],"suffixes":[]},{"propositions":[],"lastnames":["Petitjean"],"firstnames":["C."],"suffixes":[]},{"propositions":[],"lastnames":["Dacher"],"firstnames":["J.-N."],"suffixes":[]},{"propositions":[],"lastnames":["Ruan"],"firstnames":["S."],"suffixes":[]}],"month":"September","year":"2013","pages":"1027–1035","bibtex":"@article{grosgeorge_graph_2013,\n\ttitle = {Graph cut segmentation with a statistical shape model in cardiac {MRI}},\n\tvolume = {117},\n\tissn = {10773142},\n\turl = {https://linkinghub.elsevier.com/retrieve/pii/S1077314213000738},\n\tdoi = {10.1016/j.cviu.2013.01.014},\n\tabstract = {Segmenting the right ventricle (RV) in magnetic resonance (MR) images is required for cardiac function assessment. The segmentation of the RV is a difficult task due to low contrast with surrounding tissues and high shape variability. To overcome these problems, we introduce a segmentation method based on a statistical shape model obtained with a principal component analysis (PCA) on a set of representative shapes of the RV. Shapes are not represented by a set of points, but by distance maps to their contour, relaxing the need for a costly landmark detection and matching process. A shape model is thus obtained by computing a PCA on the shape variations. This prior is registered onto the image via a very simple user interaction and then incorporated into the well-known graph cut framework in order to guide the segmentation. Our semi-automatic segmentation method has been applied on 248 MR images of a publicly available dataset (from MICCAI’12 Right Ventricle Segmentation Challenge). We show that encouraging results can be obtained for this challenging application.},\n\tlanguage = {en},\n\tnumber = {9},\n\turldate = {2021-02-12},\n\tjournal = {Computer Vision and Image Understanding},\n\tauthor = {Grosgeorge, D. and Petitjean, C. and Dacher, J.-N. and Ruan, S.},\n\tmonth = sep,\n\tyear = {2013},\n\tpages = {1027--1035},\n}\n\n","author_short":["Grosgeorge, D.","Petitjean, C.","Dacher, J.","Ruan, S."],"key":"grosgeorge_graph_2013-1-1","id":"grosgeorge_graph_2013-1-1","bibbaseid":"grosgeorge-petitjean-dacher-ruan-graphcutsegmentationwithastatisticalshapemodelincardiacmri-2013","role":"author","urls":{"Paper":"https://linkinghub.elsevier.com/retrieve/pii/S1077314213000738"},"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/jjAllen01","dataSources":["b2rH2vd6Bpc9f2j4b"],"keywords":[],"search_terms":["graph","cut","segmentation","statistical","shape","model","cardiac","mri","grosgeorge","petitjean","dacher","ruan"],"title":"Graph cut segmentation with a statistical shape model in cardiac MRI","year":2013}