%0 Conference Paper %F Oral %T Automatic Segmentation of Kidney and Renal Tumor in CT Images Based on 3D Fully Convolutional Neural Network with Pyramid Pooling Module %+ Laboratory of Image Science and Technology [Nanjing] (LIST) %+ Centre de Recherche en Information Biomédicale sino-français (CRIBS) %+ Laboratoire Traitement du Signal et de l'Image (LTSI) %+ Nanjing Medical University %A Yang, Guanyu %A Li, Guoqing %A Pan, Tan %A Kong, Youyong %A Wu, Jiasong %A Shu, Huazhong %A Luo, Limin %A Dillenseger, Jean-Louis %A Coatrieux, Jean-Louis %A Tang, Lijun %A Zhu, Xiaomei %Z National Natural Science Foundation of China, NSFC 31571001Science Foundation for Excellent Youth Scholars of Sichuan UniversityNational Basic Research Program of China (973 Program) 2017YFC0107903, WQ20163200398 %< avec comité de lecture %B 24th International Conference on Pattern Recognition, ICPR 2018 %C Beijing, China %I Institute of Electrical and Electronics Engineers Inc. %V 2018-August %P 3790-3795 %8 2018-08-20 %D 2018 %R 10.1109/ICPR.2018.8545143 %K 3D fully convolutional neural network %K CT image %K kidney %K pyramid pooling %K renal tumor %K segmentation %K Kidney segmentation %K renal tumor segmentation %K 3D fully convolutional networks %Z Life Sciences [q-bio]/Bioengineering %Z Engineering Sciences [physics]/Signal and Image processingConference papers %X Renal cancer is one of ten most common cancers in human beings. The laparoscopic partial nephrectomy (LPN) becomes the main therapeutic approach in treating renal cancer. Accurate kidney and tumor segmentation in CT images is a prerequisite step in the surgery planning. However, automatic and accurate kidney and renal tumor segmentation in CT images remains a challenge. In this paper, we propose a new method to perform a precise segmentation of kidney and renal tumor in CT angiography images. This method relies on a three-dimensional (3D) fully convolutional network (FCN) which combines a pyramid pooling module (PPM). The proposed network is implemented as an end-to-end learning system directly on 3D volumetric images. It can make use of the 3D spatial contextual information to improve the segmentation of the kidney as well as the tumor lesion. The experiments conducted on 140 patients show that these target structures can be segmented with a high accuracy. The resulting average dice coefficients obtained for kidney and renal tumor are equal to 0.931 and 0.802 respectively. These values are higher than those obtained from the other two neural networks. © 2018 IEEE. %G English %2 https://univ-rennes.hal.science/hal-02036719/document %2 https://univ-rennes.hal.science/hal-02036719/file/yang%20ICPR.pdf %L hal-02036719 %U https://univ-rennes.hal.science/hal-02036719 %~ INSERM %~ UNIV-RENNES1 %~ LTSI %~ CRIBS %~ METRIQ %~ STATS-UR1 %~ UR1-HAL %~ UR1-MATH-STIC %~ TEST-UR-CSS %~ UNIV-RENNES %~ UR1-MATH-NUM %~ UR1-BIO-SA