MVD-Net: Semantic Segmentation of Cataract Surgery Using Multi-View Learning

Mingyang Ou1; Heng Li1; Haofeng Liu1; Xiaoxuan Wang1; Chenlang Yi1; Luoying Hao1; Yan Hu1; Jiang Liu2

10.1109/EMBC48229.2022.9871673

2022

2375-7477

978-1-7281-2783-5

2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)

5035-5038

11-15 July 2022

Glasgow, Scotland, United Kingdom

Semantic segmentation of surgery scenarios is a fundamental task for computer-aided surgery systems. Precise segmentation of surgical instruments and anatomies contributes to capturing accurate spatial information for tracking. However, uneven reflection and class imbalance lead the segmentation in cataract surgery to a challenging task. To desirably conduct segmentation, a network with multi-view decoders (MVD-Net) is proposed to present a generalizable segmentation for cataract surgery. Two discrepant decoders are implemented to achieve multi-view learning with the backbone of U-Net. The experiment is carried out on the Cataract Dataset for Image Segmentation (CaDIS). The ablation study verifies the effectiveness of the proposed modules in MVD-Net, and superior performance is provided by MVD-Net in the comparison with the state-of-the-art methods. The source code will be publicly released.

Cataracts Surgical instruments Image segmentation Instruments Semantics Surgery Lead

第一

IEEE

1.Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China
2.Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology, Shenzhen, China

Mingyang Ou,Heng Li,Haofeng Liu,et al. MVD-Net: Semantic Segmentation of Cataract Surgery Using Multi-View Learning[C],2022:5035-5038.