SecSAKE: Towards secure and efficient outsourcing of clinical MRI reconstruction

Magnetic Resonance Imaging (MRI) is a widely used technique to help form images of internal body structures for medical diagnosis. Recently, the Simultaneous Auto-calibrating and K-space Estimation (SAKE) becomes one of the most popular rapid imaging reconstruction methods to restore key information from scanned MRI data. This technique intrinsically requires a fair amount of high-resolution MRI data to accommodate the need of accurate diagnosis and imposes vast computational overhead onto resource-constrained clinics. To solve this problem, the practitioners start seeking the help of cloud computing platform to utilize its robust and economical computation power. However, the privacy concerns with outsourcing patients' private data to public cloud servers are ignited and hinder those practitioners from enjoying the benefits of cloud computing. Motivated by this practical need, we investigate the privacy requirements of MRI data and reconstruction process and propose the first secure and efficient clinical MRI reconstruction outsourcing scheme, SecSAKE. Our solution enables a clinic to outsource the most computationally-intensive tasks in SAKE to the resource-abundant cloud servers. In particular, two different protocols are put forward in SecSAKE, with extra emphasis on security and efficiency, respectively. In the first protocol, we carefully enforce a low-complexity matrix transformation in the k-space domain on the clinic end and harness the cloud server to perform iterative computation tasks. The corresponding security analysis shows that the outsourced MRI data are computationally indistinguishable under Chosen Plaintext Attack (CPA). In the second protocol, we largely reduce the computational complexity on the clinic side by leveraging a multi-server architecture of the cloud. The clinic only needs to perform a one-round data transformation to retrieve the reconstructed MRI data. Moreover, we conduct thorough privacy and efficiency analysis and extensive experiments over real-world image benchmark to evaluate the performance of the proposed designs. Compared with the original SAKE, the experimental results demonstrate that the proposed privacy-preserving mechanism can provide significant reconstruction time savings while achieving comparative performance on the quality of reconstructed images.