Federated attention consistent learning models for prostate cancer diagnosis and Gleason grading
This addresses privacy and data heterogeneity issues in AI for prostate cancer pathology, offering a robust and accurate model, though it is incremental as it builds on federated learning with attention mechanisms.
The study tackled the challenge of training AI models on multicenter medical imaging data without sharing raw data due to privacy concerns, by introducing a federated attention-consistent learning framework that achieved an AUC of 0.9718 for prostate cancer diagnosis and a Kappa score of 0.8463 for Gleason grading, outperforming individual center averages.
Artificial intelligence (AI) holds significant promise in transforming medical imaging, enhancing diagnostics, and refining treatment strategies. However, the reliance on extensive multicenter datasets for training AI models poses challenges due to privacy concerns. Federated learning provides a solution by facilitating collaborative model training across multiple centers without sharing raw data. This study introduces a federated attention-consistent learning (FACL) framework to address challenges associated with large-scale pathological images and data heterogeneity. FACL enhances model generalization by maximizing attention consistency between local clients and the server model. To ensure privacy and validate robustness, we incorporated differential privacy by introducing noise during parameter transfer. We assessed the effectiveness of FACL in cancer diagnosis and Gleason grading tasks using 19,461 whole-slide images of prostate cancer from multiple centers. In the diagnosis task, FACL achieved an area under the curve (AUC) of 0.9718, outperforming seven centers with an average AUC of 0.9499 when categories are relatively balanced. For the Gleason grading task, FACL attained a Kappa score of 0.8463, surpassing the average Kappa score of 0.7379 from six centers. In conclusion, FACL offers a robust, accurate, and cost-effective AI training model for prostate cancer pathology while maintaining effective data safeguards.