Parallel AI-driven framework for post-quantum secure medical image communication using swin-transformer restoration.

Authors

Abstract

Reliable and secure transmission of medical images is essential for telemedicine, remote diagnosis, and distributed healthcare systems. However, medical image communication over heterogeneous networks often suffers from packet loss, channel noise, and privacy risks, which may compromise diagnostic accuracy and patient confidentiality. Traditional solutions relying on Reed-Solomon error correction and conventional encryption provide limited resilience and are increasingly inadequate for modern high-resolution medical imaging environments. This study proposes a next-generation AI-assisted communication framework for privacy-preserving medical image transmission that integrates recent advances in hybrid Transformer architectures, neural communication coding, and post-quantum cryptography. First, image corruption detection and restoration are performed using a Restormer/Swin-Transformer hybrid reconstruction network, which demonstrates superior performance in recovering corrupted regions compared with conventional GAN-based repair models. Second, to enhance transmission robustness, the framework incorporates Deep Joint Source-Channel Coding (DeepJSCC) and Neural Error Correction Codes (NECC) that jointly optimize image representation and channel robustness through deep neural networks. Third, communication security is strengthened using lattice-based post-quantum cryptographic primitives, including CRYSTALS-Kyber for key encapsulation and CRYSTALS-Dilithium for authentication, ensuring resilience against quantum computing attacks. To support real-time medical applications, the proposed framework employs a parallel GPU-accelerated processing pipeline with CUDA-based model inference and distributed training strategies. Additionally, federated learning with secure aggregation and differential privacy enables collaborative model training across healthcare institutions while preserving sensitive patient data. Experimental evaluation on benchmark medical imaging datasets demonstrates that the proposed framework significantly improves image reconstruction fidelity, transmission robustness, and cryptographic security compared with traditional ECC-based communication systems and recent AI-assisted transmission methods.

Tags

Topics