A survey on incorporating domain knowledge into deep learning for medical image analysis |
| |
| Institution: | 1. State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, 37 Xueyuan Road, Haidian District, Beijing 100191, China;2. Beijing Advanced Innovation Center for Big Data and Brain Computing (BDBC) and Hangzhou Innovation Institute of Beihang University, 18 Chuanghui Street, Binjiang District, Hangzhou 310000, China;3. Jindal School of Management, The University of Texas at Dallas, 800 W Campbell Rd, Richardson, TX 75080-3021, USA;4. School of Computer Science, University of Technology Sydney, 15 Broadway, Ultimo NSW 2007, Australia;1. Biomedical Imaging Group Rotterdam, Departments Radiology and Medical Informatics, Erasmus Medical Center, Rotterdam, the Netherlands;2. Medical Image Analysis, Department Biomedical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands;3. Image Sciences Institute, University Medical Center Utrecht, Utrecht, the Netherlands;4. The Image Section, Department Computer Science, University of Copenhagen, Copenhagen, Denmark;1. Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China;2. Tencent Jarvis Lab, Shenzhen, China;1. BioMedIA Group, Department of Computing, Imperial College London, 180 Queen’s Gate, London, SW7 2AZ, UK;2. Division of Brain Sciences, Department of Medicine, Imperial College London, UK;3. Graduate School of Informatics, Nagoya University, Japan;4. Aichi Cancer Centre, Japan;5. Nagoya University Hospital, Japan |
| |
| Abstract: | Although deep learning models like CNNs have achieved great success in medical image analysis, the small size of medical datasets remains a major bottleneck in this area. To address this problem, researchers have started looking for external information beyond current available medical datasets. Traditional approaches generally leverage the information from natural images via transfer learning. More recent works utilize the domain knowledge from medical doctors, to create networks that resemble how medical doctors are trained, mimic their diagnostic patterns, or focus on the features or areas they pay particular attention to. In this survey, we summarize the current progress on integrating medical domain knowledge into deep learning models for various tasks, such as disease diagnosis, lesion, organ and abnormality detection, lesion and organ segmentation. For each task, we systematically categorize different kinds of medical domain knowledge that have been utilized and their corresponding integrating methods. We also provide current challenges and directions for future research. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
