Metadata-Aligned 3D MRI Representations for Contrast Understanding and Quality Control
This addresses the challenge of automated MRI analysis across diverse clinical datasets, enabling label-efficient utilities like sequence recognition and quality control, though it is incremental as it builds on existing contrast learning methods.
The paper tackles the problem of data heterogeneity and lack of standardized contrast labels in MRI by introducing MR-CLIP, a framework that learns unified MRI contrast representations by aligning 3D images with DICOM metadata, resulting in distinct sequence clusters and outperforming supervised baselines in few-shot classification under data scarcity.
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.