The MRI Scanner as a Diagnostic: Image-less Active Sampling

TL;DR

This paper introduces a reinforcement learning-based active sampling method for MRI that enables disease diagnosis directly from undersampled data, reducing the need for full imaging and improving accessibility for point-of-care applications.

Contribution

It presents a novel ML framework that optimizes sampling strategies at the patient level for direct disease inference without image reconstruction.

Findings

Achieved diagnostic accuracy comparable to full data MRI using undersampled data.

Demonstrated task-specific sampling policies adaptable to different diagnostic tasks.

Potential to lower MRI hardware requirements for point-of-care diagnostics.

Abstract

Despite the high diagnostic accuracy of Magnetic Resonance Imaging (MRI), using MRI as a Point-of-Care (POC) disease identification tool poses significant accessibility challenges due to the use of high magnetic field strength and lengthy acquisition times. We ask a simple question: Can we dynamically optimise acquired samples, at the patient level, according to an (automated) downstream decision task, while discounting image reconstruction? We propose an ML-based framework that learns an active sampling strategy, via reinforcement learning, at a patient-level to directly infer disease from undersampled k-space. We validate our approach by inferring Meniscus Tear in undersampled knee MRI data, where we achieve diagnostic performance comparable with ML-based diagnosis, using fully sampled k-space data. We analyse task-specific sampling policies, showcasing the adaptability of our active sampling approach. The introduced frugal sampling strategies have the potential to reduce high field strength requirements that in turn strengthen the viability of MRI-based POC disease identification and associated preliminary screening tools.