Chapter title |
Pancreas Segmentation in MRI Using Graph-Based Decision Fusion on Convolutional Neural Networks
|
---|---|
Chapter number | 51 |
Book title |
Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016
|
Published in |
Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention, October 2016
|
DOI | 10.1007/978-3-319-46723-8_51 |
Pubmed ID | |
Book ISBNs |
978-3-31-946722-1, 978-3-31-946723-8
|
Authors |
Jinzheng Cai, Le Lu, Zizhao Zhang, Fuyong Xing, Lin Yang, Qian Yin |
Abstract |
Automated pancreas segmentation in medical images is a prerequisite for many clinical applications, such as diabetes inspection, pancreatic cancer diagnosis, and surgical planing. In this paper, we formulate pancreas segmentation in magnetic resonance imaging (MRI) scans as a graph based decision fusion process combined with deep convolutional neural networks (CNN). Our approach conducts pancreatic detection and boundary segmentation with two types of CNN models respectively: 1) the tissue detection step to differentiate pancreas and non-pancreas tissue with spatial intensity context; 2) the boundary detection step to allocate the semantic boundaries of pancreas. Both detection results of the two networks are fused together as the initialization of a conditional random field (CRF) framework to obtain the final segmentation output. Our approach achieves the mean dice similarity coefficient (DSC) 76.1% with the standard deviation of 8.7% in a dataset containing 78 abdominal MRI scans. The proposed algorithm achieves the best results compared with other state of the arts. |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
Unknown | 87 | 100% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Student > Ph. D. Student | 20 | 23% |
Student > Master | 11 | 13% |
Researcher | 9 | 10% |
Student > Bachelor | 4 | 5% |
Student > Postgraduate | 4 | 5% |
Other | 10 | 11% |
Unknown | 29 | 33% |
Readers by discipline | Count | As % |
---|---|---|
Computer Science | 26 | 30% |
Medicine and Dentistry | 8 | 9% |
Engineering | 7 | 8% |
Biochemistry, Genetics and Molecular Biology | 4 | 5% |
Mathematics | 3 | 3% |
Other | 5 | 6% |
Unknown | 34 | 39% |