Search papers, labs, and topics across Lattice.
This paper introduces PASS, a personalized MRI framework that uses a Vision-Language Model (VLM) to guide a deep unrolled reconstruction network for faster, task-oriented imaging. The VLM provides an anomaly-aware prior that informs both the k-space sampling and image reconstruction, personalizing the process to specific clinical tasks. Experiments demonstrate that PASS achieves superior image quality and improves downstream diagnostic tasks compared to traditional methods across various anatomies, contrasts, and acceleration factors.
Forget generic image quality – this VLM-guided MRI method personalizes the imaging pipeline for specific clinical tasks, dramatically improving anomaly detection and diagnosis.
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.
