Boundary and Entropy-driven Adversarial Learning for Fundus Image Segmentation
This work addresses domain shift issues in medical image segmentation for glaucoma screening, offering incremental improvements over existing unsupervised domain adaptation techniques.
The paper tackles the problem of cross-domain discrepancy in optic disc and cup segmentation for glaucoma screening by proposing an unsupervised domain adaptation framework called BEAL, which improves segmentation performance on ambiguous boundary regions and outperforms state-of-the-art methods on two public datasets.
Accurate segmentation of the optic disc (OD) and cup (OC)in fundus images from different datasets is critical for glaucoma disease screening. The cross-domain discrepancy (domain shift) hinders the generalization of deep neural networks to work on different domain datasets.In this work, we present an unsupervised domain adaptation framework,called Boundary and Entropy-driven Adversarial Learning (BEAL), to improve the OD and OC segmentation performance, especially on the ambiguous boundary regions. In particular, our proposed BEAL frame-work utilizes the adversarial learning to encourage the boundary prediction and mask probability entropy map (uncertainty map) of the target domain to be similar to the source ones, generating more accurate boundaries and suppressing the high uncertainty predictions of OD and OC segmentation. We evaluate the proposed BEAL framework on two public retinal fundus image datasets (Drishti-GS and RIM-ONE-r3), and the experiment results demonstrate that our method outperforms the state-of-the-art unsupervised domain adaptation methods. Codes will be available at https://github.com/EmmaW8/BEAL.