A Novel Approach to Breast Cancer Segmentation using U-Net Model with Attention Mechanisms and FedProx

2025-10-21

AI Summary

Breast cancer ultrasound image segmentation faces dual challenges: stringent patient privacy requirements and model bias induced by non-independent and identically distributed (non-IID) data across clients. To address these, we propose a federated learning framework integrating FedProx optimization with an attention-enhanced U-Net architecture. FedProx mitigates convergence instability caused by local data heterogeneity, while the attention mechanism strengthens discriminative feature learning—particularly at tumor boundaries—and the U-Net backbone ensures high segmentation fidelity. Our method achieves 96% global segmentation accuracy without requiring raw data to leave local sites, significantly outperforming standard federated baselines. The key contribution is the first synergistic integration of FedProx and attention-augmented U-Net specifically for medical image segmentation in federated settings—thereby jointly ensuring privacy preservation, model robustness under data heterogeneity, and clinically competitive segmentation performance.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Computer Vision: Segmentation
• Search and Optimization: Non-convex Optimization

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Security and Privacy: Data transparency and provenance
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

Breast cancer is a leading cause of death among women worldwide, emphasizing the need for early detection and accurate diagnosis. As such Ultrasound Imaging, a reliable and cost-effective tool, is used for this purpose, however the sensitive nature of medical data makes it challenging to develop accurate and private artificial intelligence models. A solution is Federated Learning as it is a promising technique for distributed machine learning on sensitive medical data while preserving patient privacy. However, training on non-Independent and non-Identically Distributed (non-IID) local datasets can impact the accuracy and generalization of the trained model, which is crucial for accurate tumour boundary delineation in BC segmentation. This study aims to tackle this challenge by applying the Federated Proximal (FedProx) method to non-IID Ultrasonic Breast Cancer Imaging datasets. Moreover, we focus on enhancing tumour segmentation accuracy by incorporating a modified U-Net model with attention mechanisms. Our approach resulted in a global model with 96% accuracy, demonstrating the effectiveness of our method in enhancing tumour segmentation accuracy while preserving patient privacy. Our findings suggest that FedProx has the potential to be a promising approach for training precise machine learning models on non-IID local medical datasets.

Problem

• Improving breast cancer segmentation accuracy on ultrasound images
• Addressing non-IID data challenges in federated learning for medical imaging
• Enhancing privacy-preserving AI models for sensitive medical data analysis

Innovation

• U-Net model with attention mechanisms
• FedProx for non-IID medical data
• Federated learning preserves patient privacy