Federated Autoencoder Model for Secure Medical Image Analysis with Privacy Preservation and Assurance.

This paper addresses the challenge of enhancing medical imaging analysis on edge devices while maintaining patient privacy and security. In this paper, we present a novel federated autoencoder model, U-NeTrans, which prioritizes security and privacy and is designed for medical image reconstruction on edge devices. U-NeTrans uses random masking to increase training complexity while maintaining manageability by using partial data. Data secrecy is ensured by the encoder processing visible patches and the decoder using encoded data to reassemble the original image. U-NeTrans improves the representation of high-order features in medical images by combining auxiliary reconstruction tasks and contrastive loss. This allows for precise analysis while maintaining patient privacy. The proposed method has wide ramifications for chest X-ray analysis and other medical imaging applications and offers the potential to improve healthcare device capabilities at the edge significantly. Comparative experimental results with benchmark datasets highlight the effectiveness of U-NeTrans compared to state-of-the-art approaches for edge-based medical image analysis while maintaining security and privacy. Accuracy, precision, sensitivity, specificity, and AUROC are measured across multiple scales and are shown to total 98.97%, 98.68%, 98.73%, and 99.19%, respectively.