MedSparseFL: Sparse and Privacy-Preserving Federated Learning for Healthcare Applications

This project provides processed data indexes for reproducing experiments from the MedSparseFL study, a sparse and privacy-preserving federated learning framework for healthcare applications. The datasets include CheXpert and HAM10000. For each dataset, CSV files (chexpert_index.csv and ham10000_index.csv) contain:
Image IDs referencing the official dataset files
Labels used in classification tasks
Train/Validation/Test splits for experiment reproducibility
The uploaded files do not include original medical images, ensuring compliance with privacy and ethical standards. Researchers can reconstruct the experiments by downloading the original datasets from official sources and following the provided indexes. These files support reproducibility and verification of MedSparseFL’s performance in medical imaging tasks under privacy-preserving federated learning settings.