# Metadata-Aligned 3D MRI Representations for Contrast Understanding and Quality Control

arXiv: https://arxiv.org/abs/2511.00681 · HTML: https://mlsanity.com/paper/2511.00681/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 15 references that are in the map.
- First posted on arXiv 1 Nov 2025.

## Builds on (most cited first, 9 of 9)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [SynthStrip: Skull-Stripping for Any Brain Image](https://mlsanity.com/paper/2203.09974/) (2022)
- [Metadata-enhanced contrastive learning from retinal optical coherence tomography images](https://mlsanity.com/paper/2208.02529/) (2022)
- [MRQy: An Open-Source Tool for Quality Control of MR Imaging Data](https://mlsanity.com/paper/2004.04871/) (2020)
- [ContextMRI: Enhancing Compressed Sensing MRI through Metadata Conditioning](https://mlsanity.com/paper/2501.04284/) (2025)
- [Towards General Text-guided Image Synthesis for Customized Multimodal Brain MRI Generation](https://mlsanity.com/paper/2409.16818/) (2024)
- [MR-CLIP: Efficient Metadata-Guided Learning of MRI Contrast Representations](https://mlsanity.com/paper/2507.00043/) (2025)

## Built on by (most cited first, 3 of 3)

- [DIST-CLIP: Arbitrary Metadata and Image Guided MRI Harmonization via Disentangled Anatomy-Contrast Representations](https://mlsanity.com/paper/2512.07674/) (2025)
- [Understanding Sources of Demographic Predictability in Brain MRI via Disentangling Anatomy and Contrast](https://mlsanity.com/paper/2603.04113/) (2026)
- [Volumetric Radiology AI in the Era of Multimodal Large Language Models](https://mlsanity.com/paper/2608.20549/) (2026)

## Abstract (arXiv)

Magnetic Resonance Imaging suffers from substantial data heterogeneity and the absence of standardized contrast labels across scanners, protocols, and institutions, which severely limits large-scale automated analysis. A unified representation of MRI contrast would enable a wide range of downstream utilities, from automatic sequence recognition to harmonization and quality control, without relying on manual annotations. To this end, we introduce MR-CLIP, a metadata-guided framework that learns MRI contrast representations by aligning volumetric images with their DICOM acquisition parameters. The resulting embeddings shows distinct clusters of MRI sequences and outperform supervised 3D baselines under data scarcity in few-shot sequence classification. Moreover, MR-CLIP enables unsupervised data quality control by identifying corrupted or inconsistent metadata through image-metadata embedding distances. By transforming routinely available acquisition metadata into a supervisory signal, MR-CLIP provides a scalable foundation for label-efficient MRI analysis across diverse clinical datasets.