Quantum Adaptive Sensing for Accelerated MRI

2026-07-23

AI Summary

This work addresses the critical yet underexplored challenge of designing efficient adaptive sampling strategies in accelerated MRI, where sampling distribution profoundly impacts compressed sensing reconstruction quality. The authors propose the first formulation of adaptive sampling as a fixed-cardinality Quadratic Unconstrained Binary Optimization (QUBO) problem, enabling sequential selection of Cartesian phase-encoding lines by jointly optimizing k-space center preference, acquired signal energy, and spatial dispersion. The approach is compatible with both classical and quantum annealers and integrates SENSE reconstruction, total variation regularization, and parallel tempering. Validated on the D-Wave quantum-classical hybrid platform, the method consistently outperforms static Cartesian sampling at 10%–20% sampling rates across multiple metrics—PSNR, SSIM, NMSE, and HFEN—and achieves reconstruction quality comparable to variable-density Poisson disk sampling, thereby opening new avenues for quantum optimization in medical imaging.

Abstract

Compressed sensing accelerates MRI by reconstructing images from undersampled k-space, but performance depends strongly on sampling distribution. We propose an adaptive framework that selects Cartesian phase-encode lines sequentially using a fixed-cardinality quadratic unconstrained binary optimization (QUBO) formulation. The objective combines a preference for central k-space, signal-energy information from previously acquired measurements, and pairwise terms that encourage spatially dispersed sampling. The formulation is compatible with classical annealing and quantum-annealing hardware. Retrospective experiments used simulated eight-coil 3D MRI data; QUBO problems were solved with parallel tempering, and images were reconstructed with SENSE and total-variation regularization. At 20% and 10% sampling, the proposed method improved PSNR, SSIM, NMSE, and HFEN compared with the evaluated static Cartesian strategies, including variable-density Poisson-disc sampling, although gains varied with resolution, acceleration, and noise level. In a reduced-pool experiment, a D-Wave quantum-classical hybrid solver achieved reconstruction quality comparable to variable-density Poisson-disc sampling, demonstrating feasibility on current quantum optimization infrastructure. While these results do not establish quantum computational advantage, the direct QUBO representation provides a practical framework for adaptive MRI sampling and may benefit from future advances in quantum-annealing hardware. Prospective scanner validation and systematic quantum-classical benchmarking remain necessary.

Problem

• accelerated MRI
• adaptive sensing
• compressed sensing
• k-space sampling
• image reconstruction

Innovation

• quantum adaptive sensing
• QUBO
• accelerated MRI
• compressed sensing
• quantum annealing