MH-DNT: Noise-robust model-heterogeneous federated learning for medical image classification via dual noise tolerance
Authors:
- Chenhan ZhaiCZChenhan Zhai
- Hui LiuHLHui Liu
- Ertong ShangESErtong Shang
- Jingchao LuJLJingchao Lu
- Zeyu QiuZQZeyu Qiu
- Junzhao DuJDJunzhao Du
- 4 June 2026
- journal article
- Published by Elsevier in Knowledge-Based Systems
- Vol. 348
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62032017)
- National Natural Science Foundation of China (62272368)
- Fundamental Research Funds for the Central Universities (ZYTS25082)
- Xidian University (QTZX24004)
This publication has 34 references indexed in Scilit:
- ACFL: Communication-Efficient adversarial contrastive federated learning for medical image segmentationKnowledge-Based Systems, 2024
- A survey of label-noise deep learning for medical image analysisMedical Image Analysis, 2024
- Medical federated learning with joint graph purification for noisy label learningMedical Image Analysis, 2023
- MedMNIST v2 - A large-scale lightweight benchmark for 2D and 3D biomedical image classificationScientific Data, 2023
- The Liver Tumor Segmentation Benchmark (LiTS)Medical Image Analysis, 2022
- Dobbs and the future of health data privacy for patients and healthcare organizationsJournal of the American Medical Informatics Association, 2022
- Communication-efficient federated learning via knowledge distillationNature Communications, 2022
- A dataset of microscopic peripheral blood cell images for development of automatic recognition systemsData in Brief, 2020
- Automatic grading of prostate cancer in digitized histopathology images: Learning from multiple expertsMedical Image Analysis, 2018
- Deep Residual Learning for Image Recognition2016