EUVIMEDEUVIMED entdecken
Crossref

Decentralized learning for medical image classification with prototypical contrastive network

Zhantao Cao, Yuanbing Shi, Shuli Zhang, Huanan Chen, Weide Liu, Guanghui Yue, Huazhen Lin

Medical Physics · 2025

DOI: 10.1002/mp.17753 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Physics, 2025. Verfasst von Zhantao Cao und 6 weiteren Autor:innen. Beteiligte Einrichtung: Institutions for Research, CETC Cyberspace Security Technology CO., LTD., Chengdu, China. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Neural Networks, Computer, Diagnostic Imaging. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 36 Literaturangaben. Gefördert von: National Key Research and Development Program of China, Major Program of the Ministry of Industry and Information Technology, Xiongan New Area Science and Technology Innovation Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Recently, deep convolutional neural networks (CNNs) have shown great potential in medical image classification tasks. However, the practical usage of the methods is constrained by two challenges: 1) the challenge of using nonindependent and identically distributed (non‐IID) datasets from various medical institutions while ensuring privacy, and 2) the data imbalance problem due to the frequency of different diseases.

Purpose

The objective of this paper is to present a novel approach for addressing these challenges through a decentralized learning method using a prototypical contrastive network to achieve precise medical image classification while mitigating the non‐IID problem across different clients.

Methods

We propose a prototype contrastive network that minimizes disparities among heterogeneous clients. This network utilizes an approximate global prototype to alleviate the non‐IID dataset problem for each local client by projecting data onto a balanced prototype space. To validate the effectiveness of our algorithm, we employed three distinct datasets of color fundus photographs for diabetic retinopathy: the EyePACS, APTOS, and IDRiD datasets. During training, we incorporated 35k images from EyePACS, 3662 from APTOS, and 516 from IDRiD. For testing, we used 53k images from EyePACS. Additionally, we included the COVIDx dataset of chest X‐rays for comparative analysis, comprising 29 986 training images and 400 test samples.

Results

In this study, we conducted comprehensive comparisons with existing works using four medical image datasets. Specifically, on the EyePACS dataset under the balanced IID setting, our method outperformed the FedAvg baseline by 3.7% in accuracy. In the Dirichlet non‐IID setting, which presents an extremely unbalanced distribution, our method showed a notable 6.6% enhancement in accuracy over FedAvg. Similarly, on the APTOS dataset, our method achieved a 3.7% improvement in accuracy over FedAvg under the balanced IID setting and a 5.0% improvement under the Dirichlet non‐IID setting. Notably, on the DCC non‐IID and COVID‐19 datasets, our method established a new state‐of‐the‐art across all evaluation metrics, including WAccuracy, WPrecision, WRecall, and WF‐score.

Conclusions

Our proposed prototypical contrastive loss guides the local client's data distribution to align with the global distribution. Additionally, our method uses an approximate global prototype to address unbalanced dataset distribution across local clients by projecting all data onto a new balanced prototype space. Our model achieves state‐of‐the‐art performance on the EyePACS, APTOS, IDRiD, and COVIDx datasets.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedNeural Networks, ComputerDiagnostic ImagingHumansCOVID-19Deep LearningAlgorithms

Stichwörter der Autor:innen

decentralized learningfederated learningmedical image classificationprototypical contrastive

Autor:innen und Institutionen

  • Institutions for Research, CETC Cyberspace Security Technology CO., LTD., Chengdu, China.
  • Chengdu Westone Information Security Technology Co., Ltd., Chengdu, China.
  • Ubiquitous Intelligence and Trusted Services Key Laboratory of Sichuan Province, Chengdu, China.
  • Institute for Infocomm Research, A*STAR, Singapore, Singapore.
  • School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, China.
  • Center of Statistical Research and School of Statistics, Southwestern University of Finance and Economics, Chengdu, China.

Förderung

  • National Key Research and Development Program of China
  • Major Program of the Ministry of Industry and Information Technology
  • Xiongan New Area Science and Technology Innovation Project
  • National Natural Science Foundation of China

Zitieren

APA

Cao, Z., Shi, Y., Zhang, S., Chen, H., Liu, W., Yue, G., & Lin, H. (2025). Decentralized learning for medical image classification with prototypical contrastive network. Medical Physics. https://doi.org/10.1002/mp.17753

Vancouver

Cao Z, Shi Y, Zhang S, Chen H, Liu W, Yue G, et al. Decentralized learning for medical image classification with prototypical contrastive network. Medical Physics. 2025. doi:10.1002/mp.17753

BibTeX
@article{Cao2025,
  author = {Cao, Zhantao and Shi, Yuanbing and Zhang, Shuli and Chen, Huanan and Liu, Weide and Yue, Guanghui and Lin, Huazhen},
  title = {Decentralized learning for medical image classification with prototypical contrastive network},
  journal = {Medical Physics},
  year = {2025},
  doi = {10.1002/mp.17753}
}
Kostenlos starten →