Vision-Language Model-Guided Deep Unrolling Enables Personalized, Fast MRI

TL;DR

This paper introduces PASS, a personalized MRI framework that uses a vision-language model to guide fast, task-specific imaging and improve diagnostic accuracy.

Contribution

It presents a novel integration of a vision-language model with a physics-based deep unrolling network for personalized, anomaly-aware MRI reconstruction.

Findings

Achieves superior image quality across diverse clinical scenarios.

Enhances downstream diagnostic tasks like anomaly detection and localization.

Personalizes MRI sampling and reconstruction based on patient-specific information.

Abstract

Magnetic Resonance Imaging (MRI) is a cornerstone in medicine and healthcare but suffers from long acquisition times. Traditional accelerated MRI methods optimize for generic image quality, lacking adaptability for specific clinical tasks. To address this, we introduce PASS (Personalized, Anomaly-aware Sampling and reconStruction), an intelligent MRI framework that leverages a Vision-Language Model (VLM) to guide a deep unrolling network for task-oriented, fast imaging. PASS dynamically personalizes the imaging pipeline through three core contributions: (1) a deep unrolled reconstruction network derived from a physics-based MRI model; (2) a sampling module that generates patient-specific $k$-space trajectories; and (3) an anomaly-aware prior, extracted from a pretrained VLM, which steers both sampling and reconstruction toward clinically relevant regions. By integrating the high-level clinical reasoning of a VLM with an interpretable, physics-aware network, PASS achieves superior image quality across diverse anatomies, contrasts, anomalies, and acceleration factors. This enhancement directly translates to improvements in downstream diagnostic tasks, including fine-grained anomaly detection, localization, and diagnosis.