ArXiv Preprint
The application effect of artificial intelligence(AI) in the field of medical
imaging is remarkable. Robust AI model training requires large datasets, but
data collection faces constraints in communication, ethics, and privacy
protection. Federated learning can solve the above problems by coordinating
multiple clients to train the model without sharing the original data. In this
study, we design a federated contrastive learning framework(FCL) for
large-scale pathology images and the heterogeneity challenges. It enhances the
generalization ability of the model by maximizing the attention consistency
between the local client model and the server model. To alleviate the privacy
leakage problem when transferring weights and verify the robustness of FCL, we
use differential privacy to further protect the model by adding noise. We
evaluate the effectiveness of FCL on the cancer diagnosis task and Gleason
grading task on 19,635 prostate cancer WSIs from multiple clients. In the
diagnosis task, the average AUC of 7 clients is 95\% when the categories are
relatively balanced, and our FCL achieves 97\%. In the Gleason grading task,
the average Kappa of 6 clients is 0.74, and the Kappa of FCL reaches 0.84.
Furthermore, we also validate the robustness of the model on external
datasets(one public dataset and two private datasets). In addition, to better
explain the classification effect of the model, we show whether the model
focuses on the lesion area by drawing a heatmap. FCL brings a robust, accurate,
and low-cost AI training model to biomedical research, effectively protecting
the privacy of medical data.
Fei Kong, Jinxi Xiang, Xiyue Wang, Xinran Wang, Meng Yue, Jun Zhang, Sen Yang, Junhan Zhao, Xiao Han, Yuhan Dong, Yueping Liu
2023-02-13
