Abstract
Semantic segmentation of medical images provides an important cornerstone for subsequent tasks of image analysis and understanding. With rapid advancements in deep learning methods, conventional U-Net segmentation networks have been applied in many fields. Based on exploratory experiments, features at multiple scales have been found to be of great importance for the segmentation of medical images. In this paper, we propose a scale-attention deep learning network (SA-Net), which extracts features of different scales in a residual module and uses an attention module to enforce the scale-attention capability. SA-Net can better learn the multi-scale features and achieve more accurate segmentation for different medical image. In addition, this work validates the proposed method across multiple datasets. The experiment results show SA-Net achieves excellent performances in the applications of vessel detection in retinal images, lung segmentation, artery/vein(A/V) classification in retinal images and blastocyst segmentation. To facilitate SA-Net utilization by the scientific community, the code implementation will be made publicly available.
Funder
National Key Research and Development Program of China
National Natural Science Foundation of China
University Synergy Innovation Program of Anhui Province
Hefei Innovation Research Institute, Beihang University
‘the Thousand Talents Plan’ Workstation between Beihang University and Jiangsu Yuwell Medical Equipment and Supply Co. Ltd
Publisher
Public Library of Science (PLoS)
Reference42 articles.
1. MultiResUNet: Rethinking the U-Net architecture for multimodal biomedical image segmentation[J];N. Ibtehaz;Neural Networks
2. Joint optic disc and cup segmentation based on multi-label deep network and polar transformation;H. Fu;IEEE Trans. Med. Imaging,2018
Cited by
36 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献