%0 Conference Proceedings %T Automatic whole heart segmentation in CT images based on multi-atlas image registration %+ Centre de Recherche en Information Biomédicale sino-français (CRIBS) %+ Laboratory of Image Science and Technology [Nanjing] (LIST) %+ Laboratoire Traitement du Signal et de l'Image (LTSI) %A Yang, G. %A Sun, C. %A Chen, Y. %A Tang, L. %A Shu, H. %A Dillenseger, Jean-Louis %Z 31571001, NSFC, National Natural Science Foundation of China %Z Science Foundation for Excellent Youth Scholars of Sichuan University %< avec comité de lecture %B 8th International Workshop on Statistical Atlases and Computational Models of the Heart, STACOM 2017, Held in Conjunction with MICCAI 2017 %C Quebec City, Canada %Y Bernard O.Jodoin P.Zhuang X.Yang G.Young A.Sermesant M.Lalande A.Pop M. %I Springer Verlag %3 Lecture Notes on Computer Science %V 10663 %P 250-257 %8 2017-09-10 %D 2017 %R 10.1007/978-3-319-75541-0_27 %K Multi-atlas %K Segmentation %K Whole heart segmentation %K Heart %K Cardiac chambers %K Car- diac chambers %Z Engineering Sciences [physics]/Signal and Image processing %Z Life Sciences [q-bio]/BioengineeringConference papers %X Whole heart segmentation in CT images is a significant prerequisite for clinical diagnosis or treatment. In this work, we present a three-step multi-atlas-based method for obtaining a segmentation of the whole heart. In the first step, the region of the heart was detected by aligning the down-sampled patient CT with the low-resolution atlas images. The detected region of heart was used to crop the original patient image. In the second step, the registration between high-resolution atlas images and cropped original patient images was performed to obtain the precise segmentation of the heart. In the third step, the registration was performed again by minimizing the dissimilarity within the heart region. Finally, the labels of four cardiac chambers, aorta and pulmonary artery were generated according to the similarity between the deformed atlas images and the patient image. A leave-one-out experiment has been performed on the 20 training datasets of MM-WHS 2017 challenge. The average Dice coefficient between our segmentation results and the manual segmentation results is 0.9051. The mean and standard deviation of Dice coefficients of each structure (i.e. LV, RV, LA, RA, Myo, Ao, PA) are 0.9601 ± 0.0324, 0.9344 ± 0.0418, 0.9594 ± 0.0316, 0.8836 ± 0.0826, 0.8724 ± 0.0707, 0.9295 ± 0.0883, 0.7966 ± 0.1149 respectively. %G English %2 https://univ-rennes.hal.science/hal-01777688/document %2 https://univ-rennes.hal.science/hal-01777688/file/yangMICCAI2017.pdf %L hal-01777688 %U https://univ-rennes.hal.science/hal-01777688 %~ UNIV-RENNES1 %~ LTSI %~ CRIBS %~ STATS-UR1 %~ UR1-HAL %~ UR1-MATH-STIC %~ TEST-UR-CSS %~ UNIV-RENNES %~ UR1-MATH-NUM %~ UR1-BIO-SA