Journal
IEEE TRANSACTIONS ON MEDICAL IMAGING
Volume 41, Issue 12, Pages 3699-3711Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMI.2022.3193146
Keywords
Medical image segmentation; domain generalization; automated data augmentation; reinforcement learning
Categories
Funding
- Shenzhen Basic Research Program [JCYJ20200925153847004]
- National Natural Science Foundation of China [62071210]
- High-Level University Fund [G02236002]
Ask authors/readers for more resources
The article introduces a data manipulation based domain generalization method called Automated Augmentation for Domain Generalization (AADG). By sampling data augmentation policies in an appropriate search space, this method generates new domains and enriches the training set. Experimental results show that AADG has state-of-the-art generalization performance in medical image segmentation tasks.
Convolutional neural networks have been widely applied to medical image segmentation and have achieved considerable performance. However, the performance may be significantly affected by the domain gap between training data (source domain) and testing data (target domain). To address this issue, we propose a data manipulation based domain generalization method, called Automated Augmentation for Domain Generalization (AADG). Our AADG framework can effectively sample data augmentation policies that generate novel domains and diversify the training set from an appropriate search space. Specifically, we introduce a novel proxy task maximizing the diversity among multiple augmented novel domains as measured by the Sinkhorn distance in a unit sphere space, making automated augmentation tractable. Adversarial training and deep reinforcement learning are employed to efficiently search the objectives. Quantitative and qualitative experiments on 11 publicly-accessible fundus image datasets (four for retinal vessel segmentation, four for optic disc and cup (OD/OC) segmentation and three for retinal lesion segmentation) are comprehensively performed. Two OCTA datasets for retinal vasculature segmentation are further involved to validate cross-modality generalization. Our proposed AADG exhibits state-of-the-art generalization performance and outperforms existing approaches by considerable margins on retinal vessel, OD/OC and lesion segmentation tasks. The learned policies are empirically validated to be model-agnostic and can transfer well to other models. The source code is available at https://github.com/CRazorback/AADG.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available