Clinically Deployed Distributed Magnetic Resonance Imaging Reconstruction: Application to Pediatric Knee Imaging

TL;DR

This paper presents a distributed reconstruction pipeline for T2 Shuffling MRI that significantly reduces processing time, making it feasible for clinical use in pediatric knee imaging by leveraging algorithmic improvements and parallel computing.

Contribution

The authors developed a scalable, distributed MRI reconstruction method that achieves real-time processing, enabling clinical deployment of advanced 4D CS-based imaging techniques.

Findings

3x speedup on a single machine

2.1x additional speedup with distributed systems

Reconstruction time reduced to 90 seconds in hospital

Abstract

Magnetic resonance imaging is capable of producing volumetric images without ionizing radiation. Nonetheless, long acquisitions lead to prohibitively long exams. Compressed sensing (CS) can enable faster scanning via sub-sampling with reduced artifacts. However, CS requires significantly higher reconstruction computation, limiting current clinical applications to 2D/3D or limited-resolution dynamic imaging. Here we analyze the practical limitations to T2 Shuffling, a four-dimensional CS-based acquisition, which provides sharp 3D-isotropic-resolution and multi-contrast images in a single scan. Our improvements to the pipeline on a single machine provide a 3x overall reconstruction speedup, which allowed us to add algorithmic changes improving image quality. Using four machines, we achieved additional 2.1x improvement through distributed parallelization. Our solution reduced the reconstruction time in the hospital to 90 seconds on a 4-node cluster, enabling its use clinically. To understand the implications of scaling this application, we simulated running our reconstructions with a multiple scanner setup typical in hospitals.