TUNet and domain adaptation based learning for joint optic disc and cup segmentation

Zhuorong Li, Chen Zhao, Zhike Han, Chaoyang Hong

Abstract: Highlights•A hybrid CNN-Transformer network is designed for Optic Disc and Cup Segmentation.•A method is proposed to reduce performance degradation caused by domain shift.•Proposed techniques can be used across various fundus image datasets.•Compelling performance on public fundus image datasets.