# Deep-Fed: A comprehensive solution for precise bone fracture identification in athletes

## TL;DR

Deep-Fed is a privacy-preserving AI system that improves the accuracy of bone fracture detection in athletes using federated learning.

## Contribution

A novel federated deep learning framework, Deep-Fed, that achieves high accuracy in fracture diagnosis while preserving data privacy.

## Key findings

- Deep-Fed achieved 96.23 ± 0.42% accuracy on the Deep-I dataset, outperforming existing baselines.
- The framework showed significant improvements over three baselines with p-values < 0.05 in statistical tests.
- Federated learning enabled accurate diagnosis across distributed clinics without sharing raw patient data.

## Abstract

Bone fracture diagnosis is a critical aspect of sports medicine, where accurate and timely detection enables effective treatment and rapid recovery. This study proposes Deep-Fed, a federated deep learning framework for fracture diagnosis in athletes. Deep-Fed integrates convolutional neural networks with a specialized classification module, FractureNet, and trains it across distributed athletic clinics using federated averaging without exchanging raw images, thereby preserving patient privacy while leveraging diverse data sources. The framework was evaluated on three benchmark datasets—Deep-I, Deep-II, and Deep-III—representing varied imaging conditions and patient groups. Deep-Fed achieved accuracy rates of 96.23 ± 0.42%, 97.11 ± 0.35%, and 96.73 ± 0.39%, respectively, significantly outperforming Baseline 1 (87.23 ± 0.68%), Baseline 2 (90.15 ± 0.55%), and Baseline 3 (94.49 ± 0.47%). Statistical analysis using paired t-tests confirmed that Deep-Fed’s improvements were significant (p < 0.05) across all comparisons. These results demonstrate that federated learning can be effectively applied for high-accuracy fracture detection in decentralized clinical settings, enabling collaboration across institutions without compromising data privacy.