高级检索
当前位置: 首页 > 详情页

Weakly supervised training for eye fundus lesion segmentation in patients with diabetic retinopathy.

文献详情

资源类型:
WOS体系:
Pubmed体系:

收录情况: ◇ SCIE

机构: [1]Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China. [2]School of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China. [3]Beijing Tongren Hospital, Beijing 100730, China. [4]Beijing Institute of Diabetes Research, Beijing 100730, China.
出处:
ISSN:

摘要:
Diabetic retinopathy is the leading cause of vision loss in working-age adults. Early screening and diagnosis can help to facilitate subsequent treatment and prevent vision loss. Deep learning has been applied in various fields of medical identification. However, current deep learning-based lesion segmentation techniques rely on a large amount of pixel-level labeled ground truth data, which limits their performance and application. In this work, we present a weakly supervised deep learning framework for eye fundus lesion segmentation in patients with diabetic retinopathy.First, an efficient segmentation algorithm based on grayscale and morphological features is proposed for rapid coarse segmentation of lesions. Then, a deep learning model named Residual-Attention Unet (RAUNet) is proposed for eye fundus lesion segmentation. Finally, a data sample of fundus images with labeled lesions and unlabeled images with coarse segmentation results is jointly used to train RAUNet to broaden the diversity of lesion samples and increase the robustness of the segmentation model.A dataset containing 582 fundus images with labels verified by doctors, including hemorrhage (HE), microaneurysm (MA), hard exudate (EX) and soft exudate (SE), and 903 images without labels was used to evaluate the model. In ablation test, the proposed RAUNet achieved the highest intersection over union (IOU) on the labeled dataset, and the proposed attention and residual modules both improved the IOU of the UNet benchmark. Using both the images labeled by doctors and the proposed coarse segmentation method, the weakly supervised framework based on RAUNet architecture significantly improved the mean segmentation accuracy by over 7% on the lesions.This study demonstrates that combining unlabeled medical images with coarse segmentation results can effectively improve the robustness of the lesion segmentation model and proposes a practical framework for improving the performance of medical image segmentation given limited labeled data samples.

语种:
被引次数:
WOS:
PubmedID:
中科院(CAS)分区:
出版当年[2021]版:
大类 | 4 区 工程技术
小类 | 4 区 数学与计算生物学
最新[2023]版:
大类 | 4 区 工程技术
小类 | 4 区 数学与计算生物学
JCR分区:
出版当年[2020]版:
Q3 MATHEMATICAL & COMPUTATIONAL BIOLOGY
最新[2023]版:

影响因子: 最新[2023版] 最新五年平均 出版当年[2020版] 出版当年五年平均 出版前一年[2019版] 出版后一年[2021版]

第一作者:
第一作者机构: [1]Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China.
通讯作者:
推荐引用方式(GB/T 7714):
APA:
MLA:

资源点击量:21521 今日访问量:0 总访问量:1238 更新日期:2025-02-01 建议使用谷歌、火狐浏览器 常见问题

版权所有©2020 首都医科大学附属北京同仁医院 技术支持:重庆聚合科技有限公司 地址:北京市东城区东交民巷1号(100730)