mlsanityData to 7 Oct 2026

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

arXiv 2604.06849 ↗First posted 8 Apr 2026cs.CVcited by 0

On the map: Multimodal LLMs / vision-language models → Medical vision-language models

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 6 of its 41 references that are in the map. First posted on arXiv 8 Apr 2026.

Builds on

6 of 41 references.

References · 6

  1. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  2. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 464
  3. 2021fastMRI+: Clinical Pathology Annotations for Knee and Brain Fully Sampled Multi-Coil MRI Datacited by 29
  4. 2019PILOT: Physics-Informed Learned Optimized Trajectories for Accelerated MRIcited by 24
  5. 2024MOST: MR reconstruction Optimization for multiple downStream Tasks via continual learningcited by 3
  6. 2023Optimizing Sampling Patterns for Compressed Sensing MRI with Diffusion Generative Modelscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025OmniMRI: A Unified Vision--Language Foundation Model for Generalist MRI Interpretation
  2. 2024Fast MRI for All: Bridging Access Gaps by Training without Raw Data
  3. 2025On the Utility of Foundation Models for Fast MRI: Vision-Language-Guided Image Reconstruction
  4. 2026Multi-Contrast MRI Motion Correction via Parameter-Informed Disentanglement and Adaptive Experts
  5. 2026MoRE: A Mixture-of-Experts-Based Task-Adaptive End-to-End Network for Multimodal MRI Reconstruction
  6. 2025Lesion-Aware Post-Training of Latent Diffusion Models for Synthesizing Diffusion MRI from CT Perfusion
  7. 2024MRPD: Undersampled MRI reconstruction by prompting a large latent diffusion model
  8. 2024Accelerating MRI with Longitudinally-informed Latent Posterior Sampling