MR-CLIP: Efficient Metadata-Guided Learning of MRI Contrast Representations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Avci, Mehmet Yigit, Borges, Pedro, Wright, Paul, Yigitsoy, Mehmet, Ourselin, Sebastien, Cardoso, Jorge
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909716560478208
author Avci, Mehmet Yigit
Borges, Pedro
Wright, Paul
Yigitsoy, Mehmet
Ourselin, Sebastien
Cardoso, Jorge
author_facet Avci, Mehmet Yigit
Borges, Pedro
Wright, Paul
Yigitsoy, Mehmet
Ourselin, Sebastien
Cardoso, Jorge
contents Accurate interpretation of Magnetic Resonance Imaging scans in clinical systems is based on a precise understanding of image contrast. This contrast is primarily governed by acquisition parameters, such as echo time and repetition time, which are stored in the DICOM metadata. To simplify contrast identification, broad labels such as T1-weighted or T2-weighted are commonly used, but these offer only a coarse approximation of the underlying acquisition settings. In many real-world datasets, such labels are entirely missing, leaving raw acquisition parameters as the only indicators of contrast. Adding to this challenge, the available metadata is often incomplete, noisy, or inconsistent. The lack of reliable and standardized metadata complicates tasks such as image interpretation, retrieval, and integration into clinical workflows. Furthermore, robust contrast-aware representations are essential to enable more advanced clinical applications, such as achieving modality-invariant representations and data harmonization. To address these challenges, we propose MR-CLIP, a multimodal contrastive learning framework that aligns MR images with their DICOM metadata to learn contrast-aware representations, without relying on manual labels. Trained on a diverse clinical dataset that spans various scanners and protocols, MR-CLIP captures contrast variations across acquisitions and within scans, enabling anatomy-invariant representations. We demonstrate its effectiveness in cross-modal retrieval and contrast classification, highlighting its scalability and potential for further clinical applications. The code and weights are publicly available at https://github.com/myigitavci/MR-CLIP.
format Preprint
id arxiv_https___arxiv_org_abs_2507_00043
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MR-CLIP: Efficient Metadata-Guided Learning of MRI Contrast Representations
Avci, Mehmet Yigit
Borges, Pedro
Wright, Paul
Yigitsoy, Mehmet
Ourselin, Sebastien
Cardoso, Jorge
Computer Vision and Pattern Recognition
Artificial Intelligence
Accurate interpretation of Magnetic Resonance Imaging scans in clinical systems is based on a precise understanding of image contrast. This contrast is primarily governed by acquisition parameters, such as echo time and repetition time, which are stored in the DICOM metadata. To simplify contrast identification, broad labels such as T1-weighted or T2-weighted are commonly used, but these offer only a coarse approximation of the underlying acquisition settings. In many real-world datasets, such labels are entirely missing, leaving raw acquisition parameters as the only indicators of contrast. Adding to this challenge, the available metadata is often incomplete, noisy, or inconsistent. The lack of reliable and standardized metadata complicates tasks such as image interpretation, retrieval, and integration into clinical workflows. Furthermore, robust contrast-aware representations are essential to enable more advanced clinical applications, such as achieving modality-invariant representations and data harmonization. To address these challenges, we propose MR-CLIP, a multimodal contrastive learning framework that aligns MR images with their DICOM metadata to learn contrast-aware representations, without relying on manual labels. Trained on a diverse clinical dataset that spans various scanners and protocols, MR-CLIP captures contrast variations across acquisitions and within scans, enabling anatomy-invariant representations. We demonstrate its effectiveness in cross-modal retrieval and contrast classification, highlighting its scalability and potential for further clinical applications. The code and weights are publicly available at https://github.com/myigitavci/MR-CLIP.
title MR-CLIP: Efficient Metadata-Guided Learning of MRI Contrast Representations
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2507.00043