A survey on incorporating domain knowledge into deep learning for medical image analysis

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, re-searchers have started looking for external information beyond current available medical datasets. Tra-ditional 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 ab-normality 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. (c) 2021 Elsevier B.V. All rights reserved.

Automated summary

In the field of medical image analysis, researchers are seeking external information beyond current medical datasets to address the small size issue. They integrate domain knowledge from medical doctors into deep learning models, mimicking diagnostic patterns and features of doctors, and applying them to tasks such as disease diagnosis and organ segmentation.