Specificity-Aware Federated Learning With Dynamic Feature Fusion Network for Imbalanced Medical Image Classification

计算机科学 人工智能 特征(语言学) 机器学习 模式识别(心理学) 上下文图像分类 特征提取 图像(数学) 数据挖掘 语言学 哲学
作者
Guanghui Yue,Peishan Wei,Tianwei Zhou,Youyi Song,Cheng Zhao,Tianfu Wang,Baiying Lei
出处
期刊:IEEE Journal of Biomedical and Health Informatics [Institute of Electrical and Electronics Engineers]
卷期号:28 (11): 6373-6383 被引量:5
标识
DOI:10.1109/jbhi.2023.3319516
摘要

Recently, federated learning has become a powerful technique for medical image classification due to its ability to utilize datasets from multiple clinical clients while satisfying privacy constraints. However, there are still some obstacles in federated learning. Firstly, most existing methods directly average the model parameters collected by medical clients on the server, ignoring the specificities of the local models. Secondly, class imbalance is a common issue in medical datasets. In this article, to handle these two challenges, we propose a novel specificity-aware federated learning framework that benefits from an Adaptive Aggregation Mechanism (AdapAM) and a Dynamic Feature Fusion Strategy (DFFS). Considering the specificity of each local model, we set the AdapAM on the server. The AdapAM utilizes reinforcement learning to adaptively weight and aggregate the parameters of local models based on their data distribution and performance feedback for obtaining the global model parameters. For the class imbalance in local datasets, we propose the DFFS to dynamically fuse the features of majority classes based on the imbalance ratio in the min-batch and collaborate the rest of features. We conduct extensive experiments on a dermoscopic dataset and a fundus image dataset. Experimental results show that our method can achieve state-of-the-art results in these two real-world medical applications.
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
immm发布了新的文献求助10
2秒前
腾腾腾完成签到,获得积分10
4秒前
8秒前
科研通AI5应助大橙子采纳,获得10
9秒前
Rubby应助科研通管家采纳,获得10
9秒前
9秒前
10秒前
传奇3应助科研通管家采纳,获得10
10秒前
10秒前
俏皮火完成签到 ,获得积分10
10秒前
一一一应助Bin_Liu采纳,获得10
10秒前
11秒前
啾啾啾完成签到,获得积分20
12秒前
Wang完成签到,获得积分10
13秒前
15秒前
啾啾啾发布了新的文献求助10
15秒前
CHSLN完成签到 ,获得积分10
16秒前
biofresh发布了新的文献求助30
16秒前
16秒前
17秒前
超级无敌奥特大王完成签到,获得积分10
17秒前
NexusExplorer应助小包子采纳,获得10
17秒前
努力向前看完成签到,获得积分10
19秒前
19秒前
19秒前
agnes完成签到,获得积分10
20秒前
失眠的向日葵完成签到 ,获得积分10
20秒前
大橙子发布了新的文献求助10
21秒前
23秒前
24秒前
qq完成签到,获得积分10
25秒前
王二哈完成签到,获得积分10
26秒前
行者无疆发布了新的文献求助10
27秒前
令散内方完成签到,获得积分10
27秒前
外向的雁玉完成签到,获得积分10
27秒前
慧灰huihui发布了新的文献求助10
28秒前
Ava应助Desire采纳,获得10
29秒前
量子星尘发布了新的文献求助10
32秒前
风信子完成签到,获得积分10
32秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Handbook of Industrial Diamonds.Vol2 1100
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
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 4038201
求助须知:如何正确求助?哪些是违规求助? 3575940
关于积分的说明 11373987
捐赠科研通 3305747
什么是DOI,文献DOI怎么找? 1819274
邀请新用户注册赠送积分活动 892662
科研通“疑难数据库(出版商)”最低求助积分说明 815022