Federated Distillation for Medical Image Classification: Towards Trustworthy Computer-Aided Diagnosis

TL;DR

This paper introduces FedMIC, a federated learning framework for medical image classification that preserves privacy, reduces communication costs, and adapts to diverse data distributions in resource-constrained healthcare settings.

Contribution

FedMIC is a novel privacy-preserving federated learning framework that improves local data representation and model customization for medical imaging tasks.

Findings

FedMIC achieves high classification accuracy on four public datasets.

It reduces communication overhead compared to traditional federated learning.

The framework is robust under resource constraints.

Abstract

Medical image classification plays a crucial role in computer-aided clinical diagnosis. While deep learning techniques have significantly enhanced efficiency and reduced costs, the privacy-sensitive nature of medical imaging data complicates centralized storage and model training. Furthermore, low-resource healthcare organizations face challenges related to communication overhead and efficiency due to increasing data and model scales. This paper proposes a novel privacy-preserving medical image classification framework based on federated learning to address these issues, named FedMIC. The framework enables healthcare organizations to learn from both global and local knowledge, enhancing local representation of private data despite statistical heterogeneity. It provides customized models for organizations with diverse data distributions while minimizing communication overhead and improving efficiency without compromising performance. Our FedMIC enhances robustness and practical applicability under resource-constrained conditions. We demonstrate FedMIC's effectiveness using four public medical image datasets for classical medical image classification tasks.