分割
人工智能
计算机科学
计算机视觉
模式识别(心理学)
视网膜
图像分割
眼底(子宫)
先验与后验
变压器
尺度空间分割
医学
眼科
电压
哲学
物理
认识论
量子力学
作者
Hanyu Zhang,Weihan Ni,Yi Luo,Yining Feng,Ruoxi Song,Xianghai Wang
标识
DOI:10.1016/j.compbiomed.2023.106937
摘要
Segmentation of retinal fundus images is a crucial part of medical diagnosis. Automatic extraction of blood vessels in low-quality retinal images remains a challenging problem. In this paper, we propose a novel two-stage model combining Transformer Unet (TUnet) and local binary energy function model (LBF), TUnet-LBF, for coarse to fine segmentation of retinal vessels. In the coarse segmentation stage, the global topological information of blood vessels is obtained by TUnet. The neural network outputs the initial contour and the probability maps, which are input to the fine segmentation stage as the priori information. In the fine segmentation stage, an energy modulated LBF model is proposed to obtain the local detail information of blood vessels. The proposed model reaches accuracy (Acc) of 0.9650, 0.9681 and 0.9708 on the public datasets DRIVE, STARE and CHASE_DB1 respectively. The experimental results demonstrate the effectiveness of each component in the proposed model.
科研通智能强力驱动
Strongly Powered by AbleSci AI