分割
计算机科学
人工智能
任务(项目管理)
网(多面体)
白内障手术
图像分割
计算机视觉
班级(哲学)
编码(集合论)
深度学习
医学
外科
工程类
数学
集合(抽象数据类型)
程序设计语言
系统工程
几何学
作者
Mingyang Ou,Heng Li,Haofeng Liu,Xiaoxuan Wang,Chenlang Yi,Luoying Hao,Yan Hu,Jiang Liu
标识
DOI:10.1109/embc48229.2022.9871673
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI