Lesion-Aware Contrastive Learning for Diabetic Retinopathy Diagnosis

计算机科学 假阳性悖论 人工智能 判别式 假阳性和假阴性 糖尿病性视网膜病变 病变 深度学习 模式识别(心理学) 分级(工程) 机器学习 监督学习 眼底(子宫) 特征学习 医学 放射科 病理 内分泌学 糖尿病 土木工程 工程类 人工神经网络
作者
Shuai Cheng,Qingshan Hou,Peng Cao,Jinzhu Yang,Xiaoli Liu,Osmar R. Zäıane
出处
期刊:Lecture Notes in Computer Science 卷期号:: 671-681 被引量:1
标识
DOI:10.1007/978-3-031-43990-2_63
摘要

Early diagnosis and screening of diabetic retinopathy are critical in reducing the risk of vision loss in patients. However, in a real clinical situation, manual annotation of lesion regions in fundus images is time-consuming. Contrastive learning(CL) has recently shown its strong ability for self-supervised representation learning due to its ability of learning the invariant representation without any extra labelled data. In this study, we aim to investigate how CL can be applied to extract lesion features in medical images. However, can the direct introduction of CL into the deep learning framework enhance the representation ability of lesion characteristics? We show that the answer is no. Due to the lesion-specific regions being insignificant in medical images, directly introducing CL would inevitably lead to the effects of false negatives, limiting the ability of the discriminative representation learning. Essentially, two key issues should be considered: (1) How to construct positives and negatives to avoid the problem of false negatives? (2) How to exploit the hard negatives for promoting the representation quality of lesions? In this work, we present a lesion-aware CL framework for DR grading. Specifically, we design a new generating positives and negatives strategy to overcome the false negatives problem in fundus images. Furthermore, a dynamic hard negatives mining method based on knowledge distillation is proposed in order to improve the quality of the learned embeddings. Extensive experimental results show that our method significantly advances state-of-the-art DR grading methods to a considerable 88.0%ACC/86.8% Kappa on the EyePACS benchmark dataset. Our code is available at https://github.com/IntelliDAL/Image .
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
天天快乐应助喜喵喵采纳,获得10
刚刚
shinysparrow应助dream采纳,获得200
刚刚
2秒前
KevenDing完成签到,获得积分10
4秒前
wulalala发布了新的文献求助30
5秒前
CipherSage应助loski采纳,获得10
5秒前
我是老大应助loski采纳,获得10
5秒前
完美世界应助loski采纳,获得10
6秒前
李健应助loski采纳,获得10
6秒前
欣喜沛芹发布了新的文献求助10
8秒前
可爱的函函应助橙色小人采纳,获得10
9秒前
ED应助多发论文采纳,获得10
11秒前
11秒前
量子星尘发布了新的文献求助10
11秒前
Owen应助机智思真采纳,获得10
12秒前
传奇3应助loski采纳,获得10
13秒前
万能图书馆应助自觉的凛采纳,获得10
15秒前
19秒前
积极幻桃应助ssjjzhou采纳,获得10
20秒前
讨厌科研完成签到,获得积分10
21秒前
24秒前
Xw发布了新的文献求助10
26秒前
27秒前
失眠的霸完成签到,获得积分10
28秒前
ChatGPT发布了新的文献求助10
29秒前
31秒前
多发论文完成签到,获得积分20
32秒前
32秒前
33秒前
su发布了新的文献求助10
33秒前
Xw关闭了Xw文献求助
33秒前
大个应助fjm采纳,获得10
36秒前
而为发布了新的文献求助30
36秒前
机智思真发布了新的文献求助10
36秒前
木樨316完成签到,获得积分10
36秒前
39秒前
花花完成签到 ,获得积分10
41秒前
沉默的小天鹅应助耀阳采纳,获得10
41秒前
lilila666完成签到,获得积分10
41秒前
43秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3989378
求助须知:如何正确求助?哪些是违规求助? 3531442
关于积分的说明 11254002
捐赠科研通 3270126
什么是DOI,文献DOI怎么找? 1804887
邀请新用户注册赠送积分活动 882087
科研通“疑难数据库(出版商)”最低求助积分说明 809173