A deep learning framework for pancreas segmentation with multi-atlas registration and 3D level-set |
| |
| Institution: | 1. Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, China;2. Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong, China;3. School of Computer and Electrical Engineering, Hunan University of Arts and Science, Hunan, China;4. School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, China;5. Department of Radiology, Third Military Medical University Southwest Hospital, Chongqing, China;6. Department of Electrical Engineering, University of Electronic Science and Technology of China, Chengdu, China;1. Vietnam National University of Agriculture, Vietnam;2. The University of South Australia, Australia;3. Australian Centre for Visual Technologies, The University of Adelaide, Australia;1. Clinical Image Processing Service, Radiology and Imaging Sciences Department, Clinical Center, National Institutes of Health, Bethesda, MD 20892-1182, USA;2. Imaging Biomarkers and Computer-aided Diagnosis Laboratory, Radiology and Imaging Sciences Department, Clinical Center, National Institutes of Health, Building 10 Room 1C224D MSC 1182, Bethesda, MD 20892-1182;3. Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, MD;4. Biostatistics and Clinical Epidemiology Service (BCES), National Institutes of Health Clinical Center, Bethesda, MD |
| |
| Abstract: | In this paper, we propose and validate a deep learning framework that incorporates both multi-atlas registration and level-set for segmenting pancreas from CT volume images. The proposed segmentation pipeline consists of three stages, namely coarse, fine, and refine stages. Firstly, a coarse segmentation is obtained through multi-atlas based 3D diffeomorphic registration and fusion. After that, to learn the connection feature, a 3D patch-based convolutional neural network (CNN) and three 2D slice-based CNNs are jointly used to predict a fine segmentation based on a bounding box determined from the coarse segmentation. Finally, a 3D level-set method is used, with the fine segmentation being one of its constraints, to integrate information of the original image and the CNN-derived probability map to achieve a refine segmentation. In other words, we jointly utilize global 3D location information (registration), contextual information (patch-based 3D CNN), shape information (slice-based 2.5D CNN) and edge information (3D level-set) in the proposed framework. These components form our cascaded coarse-fine-refine segmentation framework. We test the proposed framework on three different datasets with varying intensity ranges obtained from different resources, respectively containing 36, 82 and 281 CT volume images. In each dataset, we achieve an average Dice score over 82%, being superior or comparable to other existing state-of-the-art pancreas segmentation algorithms. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
