Robust Collaborative Learning of Patch-Level and Image-Level Annotations for Diabetic Retinopathy Grading From Fundus Image

doi:10.1109/TCYB.2021.3062638

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 人工智能与机器学习（杨雪冰）-技术团队

	Robust Collaborative Learning of Patch-Level and Image-Level Annotations for Diabetic Retinopathy Grading From Fundus Image
	Yang, Yehui 1; Shang, Fangxin 1; Wu, Binghong 1; Yang, Dalu 1; Wang, Lei 1; Xu, Yanwu 1; Zhang, Wensheng2 ; Zhang, Tianzhu 3
发表期刊	IEEE TRANSACTIONS ON CYBERNETICS
ISSN	2168-2267
	2021-05-07
页码	11
通讯作者	Xu, Yanwu(ywxu@ieee.org)
摘要	Diabetic retinopathy (DR) grading from fundus images has attracted increasing interest in both academic and industrial communities. Most convolutional neural network-based algorithms treat DR grading as a classification task via image-level annotations. However, these algorithms have not fully explored the valuable information in the DR-related lesions. In this article, we present a robust framework, which collaboratively utilizes patch-level and image-level annotations, for DR severity grading. By an end-to-end optimization, this framework can bidirectionally exchange the fine-grained lesion and image-level grade information. As a result, it exploits more discriminative features for DR grading. The proposed framework shows better performance than the recent state-of-the-art algorithms and three clinical ophthalmologists with over nine years of experience. By testing on datasets of different distributions (such as label and camera), we prove that our algorithm is robust when facing image quality and distribution variations that commonly exist in real-world practice. We inspect the proposed framework through extensive ablation studies to indicate the effectiveness and necessity of each motivation. The code and some valuable annotations are now publicly available.
关键词	Lesions Annotations Generators Feature extraction Image segmentation Retinopathy Diabetes Collaborative learning convolutional neural networks (CNNs) diabetic retinopathy (DR) fundus image
DOI	10.1109/TCYB.2021.3062638
收录类别	SCI
语种	英语
WOS研究方向	Automation & Control Systems ; Computer Science
WOS类目	Automation & Control Systems ; Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS记录号	WOS:000732884800001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：28[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/46915
专题	多模态人工智能系统全国重点实验室_人工智能与机器学习（杨雪冰）-技术团队
通讯作者	Xu, Yanwu
作者单位	1.Baidu Inc, Intelligent Healthcare Unit, Artificial Intelligence Cloud Grp, Beijing 100085, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 3.Univ Sci & Technol China, Sch Data Sci, Hefei 230027, Peoples R China
推荐引用方式 GB/T 7714	Yang, Yehui,Shang, Fangxin,Wu, Binghong,et al. Robust Collaborative Learning of Patch-Level and Image-Level Annotations for Diabetic Retinopathy Grading From Fundus Image[J]. IEEE TRANSACTIONS ON CYBERNETICS,2021:11.
APA	Yang, Yehui.,Shang, Fangxin.,Wu, Binghong.,Yang, Dalu.,Wang, Lei.,...&Zhang, Tianzhu.(2021).Robust Collaborative Learning of Patch-Level and Image-Level Annotations for Diabetic Retinopathy Grading From Fundus Image.IEEE TRANSACTIONS ON CYBERNETICS,11.
MLA	Yang, Yehui,et al."Robust Collaborative Learning of Patch-Level and Image-Level Annotations for Diabetic Retinopathy Grading From Fundus Image".IEEE TRANSACTIONS ON CYBERNETICS (2021):11.