Skip to content

Latest commit

 

History

History
8 lines (5 loc) · 674 Bytes

README.md

File metadata and controls

8 lines (5 loc) · 674 Bytes

FedAug

Federated Augmentation Framework to improve FL in non-IID Settings

A. E. Cetinkaya, M. Akin and S. Sagiroglu, "Improving Performance of Federated Learning based Medical Image Analysis in Non-IID Settings using Image Augmentation," 2021 International Conference on Information Security and Cryptology (ISCTURKEY), 2021, pp. 69-74, doi: 10.1109/ISCTURKEY53027.2021.9654356.

Aggregated dataset of 28833 publicly available CXR images that is a mixture of Covid-19, non-covid viral or bacterial pneumoni, lung opacity and normal cases can be reached through the link below.

Dataset: https://drive.google.com/file/d/1ChQRyqGVivJDUoAjQBvlB1r_1-_bWusB/view?usp=sharing