Federated Breast Cancer Detection Enhanced by Synthetic Ultrasound Image Augmentation
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 37 references that are in the map. First posted on arXiv 29 Jun 2025.
Builds on
20 of 37 references.
References · 20
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2016Densely Connected Convolutional Networkscited by 6,720
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
- 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
- 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
- 2021Towards Personalized Federated Learningcited by 464
- 2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 287
- 2023DiffBoost: Enhancing Medical Image Segmentation via Text-Guided Diffusion Modelcited by 23
8 more
- 2023DIGEST: Fast and Communication Efficient Decentralized Learning with Local Updatescited by 12
- 2022Federated Momentum Contrastive Clusteringcited by 7
- 2024Frequency-Based Federated Domain Generalization for Polyp Segmentationcited by 7
- 2024Adaptive Aggregation Weights for Federated Segmentation of Pancreas MRIcited by 5
- 2023Domain Generalization with Fourier Transform and Soft Thresholdingcited by 4
- 2022Multi-Contrast MRI Segmentation Trained on Synthetic Imagescited by 2
- 2024IPMN Risk Assessment under Federated Learning Paradigmcited by 2
- 2025A Privacy-Preserving Domain Adversarial Federated learning for multi-site brain functional connectivity analysiscited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Subtyping Breast Lesions via Generative Augmentation based Long-tailed Recognition in Ultrasound
- 2026Hybrid Diffusion Model for Breast Ultrasound Image Augmentation
- 2025Ultrasound Image Generation using Latent Diffusion Models
- 2024MEDDAP: Medical Dataset Enhancement via Diversified Augmentation Pipeline
- 2025ADAptation: Reconstruction-based Unsupervised Active Learning for Breast Ultrasound Diagnosis
- 2024Generative Diffusion Model Bootstraps Zero-shot Classification of Fetal Ultrasound Images In Underrepresented African Populations
- 2025Generative augmentations for improved cardiac ultrasound segmentation using diffusion models
- 2025Enhancing Fetal Plane Classification Accuracy with Data Augmentation Using Diffusion Models