CVLGJan 8, 2025

ContextMRI: Enhancing Compressed Sensing MRI through Metadata Conditioning

arXiv:2501.04284v210 citationsh-index: 47
Originality Incremental advance
AI Analysis

This work addresses the challenge of improving MRI reconstruction for medical imaging by leveraging untapped metadata, representing an incremental advance over prior diffusion-based methods.

The paper tackles the problem of accelerating MRI acquisition by using compressed sensing, proposing ContextMRI, a text-conditioned diffusion model that integrates clinical metadata to enhance reconstruction accuracy, showing consistent gains across datasets and acceleration factors.

Compressed sensing MRI seeks to accelerate MRI acquisition processes by sampling fewer k-space measurements and then reconstructing the missing data algorithmically. The success of these approaches often relies on strong priors or learned statistical models. While recent diffusion model-based priors have shown great potential, previous methods typically ignore clinically available metadata (e.g. patient demographics, imaging parameters, slice-specific information). In practice, metadata contains meaningful cues about the anatomy and acquisition protocol, suggesting it could further constrain the reconstruction problem. In this work, we propose ContextMRI, a text-conditioned diffusion model for MRI that integrates granular metadata into the reconstruction process. We train a pixel-space diffusion model directly on minimally processed, complex-valued MRI images. During inference, metadata is converted into a structured text prompt and fed to the model via CLIP text embeddings. By conditioning the prior on metadata, we unlock more accurate reconstructions and show consistent gains across multiple datasets, acceleration factors, and undersampling patterns. Our experiments demonstrate that increasing the fidelity of metadata, ranging from slice location and contrast to patient age, sex, and pathology, systematically boosts reconstruction performance. This work highlights the untapped potential of leveraging clinical context for inverse problems and opens a new direction for metadata-driven MRI reconstruction.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes