Abstract:Federated learning enables collaborative training of deep learning models across institutions without sharing sensitive patient data. However, its performance is often limited by small datasets and non-independent, identically distributed data, which can impair model generalization. In this work, we propose a generative model-based data augmentation framework for breast ultrasound classification. It leverages synthetic images generated by deep convolutional generative adversarial networks and a class-conditioned denoising diffusion probabilistic model. Experiments on three publicly available datasets (BUSI, BUS-BRA, and UDIAT) demonstrated that incorporating a suitable number of synthetic images improved average AUC from 0.9206 to 0.9362 for FedAvg and from 0.9429 to 0.9574 for FedProx. Furthermore, we noticed that excessive use of synthetic data reduced performance. This highlights the importance of balancing real and synthetic samples. Our results underscore the potential of generative model-based augmentation to enhance federated breast ultrasound image classification.
| Comments: | This paper has been accepted to EMBC2026 |
| Subjects: | Image and Video Processing (eess.IV); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2506.23334 [eess.IV] |
| (or arXiv:2506.23334v3 [eess.IV] for this version) | |
| https://doi.org/10.48550/arXiv.2506.23334 arXiv-issued DOI via DataCite |
From: Hongyi Pan Dr. [view email]
[v1]
Sun, 29 Jun 2025 17:05:50 UTC (1,049 KB)
[v2]
Tue, 8 Jul 2025 21:03:53 UTC (1,049 KB)
[v3]
Wed, 15 Apr 2026 21:01:49 UTC (3,639 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。