Label Co-Occurrence Learning With Graph Convolutional Networks for Multi-Label Chest X-Ray Image Classification

计算机科学 人工智能 卷积神经网络 模式识别(心理学) 多标签分类 上下文图像分类 图形 图像(数学) 理论计算机科学
作者
Bingzhi Chen,Jinxing Li,Guangming Lu,Hongbing Yu,David Zhang
出处
期刊:IEEE Journal of Biomedical and Health Informatics [Institute of Electrical and Electronics Engineers]
卷期号:24 (8): 2292-2302 被引量:118
标识
DOI:10.1109/jbhi.2020.2967084
摘要

Existing multi-label medical image learning tasks generally contain rich relationship information among pathologies such as label co-occurrence and interdependency, which is of great importance for assisting in clinical diagnosis and can be represented as the graph-structured data. However, most state-of-the-art works only focus on regression from the input to the binary labels, failing to make full use of such valuable graph-structured information due to the complexity of graph data. In this paper, we propose a novel label co-occurrence learning framework based on Graph Convolution Networks (GCNs) to explicitly explore the dependencies between pathologies for the multi-label chest X-ray (CXR) image classification task, which we term the "CheXGCN". Specifically, the proposed CheXGCN consists of two modules, i.e., the image feature embedding (IFE) module and label co-occurrence learning (LCL) module. Thanks to the LCL model, the relationship between pathologies is generalized into a set of classifier scores by introducing the word embedding of pathologies and multi-layer graph information propagation. During end-to-end training, it can be flexibly integrated into the IFE module and then adaptively recalibrate multi-label outputs with these scores. Extensive experiments on the ChestX-Ray14 and CheXpert datasets have demonstrated the effectiveness of CheXGCN as compared with the state-of-the-art baselines.
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
1秒前
SciGPT应助xuan采纳,获得10
4秒前
lu完成签到,获得积分10
5秒前
梁皓然发布了新的文献求助10
6秒前
6秒前
大模型应助给大佬递茶采纳,获得10
7秒前
橘子发布了新的文献求助10
7秒前
喵喵喵发布了新的文献求助10
8秒前
烟花应助小浣熊采纳,获得10
8秒前
zty568发布了新的文献求助10
8秒前
supercherry发布了新的文献求助10
8秒前
maoxinnan发布了新的文献求助10
8秒前
12chow chow完成签到 ,获得积分10
9秒前
9秒前
wanci应助暴躁的不评采纳,获得10
9秒前
9秒前
dbdxyty完成签到,获得积分10
10秒前
xuan发布了新的文献求助10
13秒前
科研通AI5应助U9A采纳,获得10
13秒前
14秒前
单薄茗发布了新的文献求助10
14秒前
共享精神应助zzznznnn采纳,获得10
15秒前
风趣怜烟完成签到,获得积分10
15秒前
15秒前
16秒前
hhh完成签到,获得积分10
17秒前
17秒前
17秒前
17秒前
highlights完成签到,获得积分10
17秒前
17秒前
18秒前
JamesPei应助肉肉采纳,获得10
20秒前
21秒前
清脆语海完成签到,获得积分10
21秒前
xrq发布了新的文献求助10
21秒前
22秒前
YY发布了新的文献求助10
22秒前
细腻新之发布了新的文献求助10
22秒前
思源应助超人会飞233采纳,获得10
23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
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
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 3971791
求助须知:如何正确求助?哪些是违规求助? 3516425
关于积分的说明 11182785
捐赠科研通 3251636
什么是DOI,文献DOI怎么找? 1796048
邀请新用户注册赠送积分活动 876216
科研通“疑难数据库(出版商)”最低求助积分说明 805371