LGE-Guided Cross-Modality Contrastive Learning for Gadolinium-Free Cardiomyopathy Screening in Cine CMR

TL;DR

This paper introduces CC-CMR, a novel contrastive learning framework that aligns cine CMR and LGE sequences to enable gadolinium-free cardiomyopathy screening with high accuracy, reducing reliance on contrast agents and improving clinical applicability.

Contribution

The study presents a cross-modal contrastive learning approach that encodes fibrosis-specific pathology into cine CMR, enhancing diagnostic accuracy without gadolinium contrast, and introduces an adaptive training mechanism for better generalization.

Findings

Achieved 94.3% accuracy on multi-center data.

Outperformed state-of-the-art cine-CMR models by 4.3%.

Eliminated the need for gadolinium contrast agents.

Abstract

Cardiomyopathy, a principal contributor to heart failure and sudden cardiac mortality, demands precise early screening. Cardiac Magnetic Resonance (CMR), recognized as the diagnostic 'gold standard' through multiparametric protocols, holds the potential to serve as an accurate screening tool. However, its reliance on gadolinium contrast and labor-intensive interpretation hinders population-scale deployment. We propose CC-CMR, a Contrastive Learning and Cross-Modal alignment framework for gadolinium-free cardiomyopathy screening using cine CMR sequences. By aligning the latent spaces of cine CMR and Late Gadolinium Enhancement (LGE) sequences, our model encodes fibrosis-specific pathology into cine CMR embeddings. A Feature Interaction Module concurrently optimizes diagnostic precision and cross-modal feature congruence, augmented by an uncertainty-guided adaptive training mechanism that dynamically calibrates task-specific objectives to ensure model generalizability. Evaluated on multi-center data from 231 subjects, CC-CMR achieves accuracy of 0.943 (95% CI: 0.886-0.986), outperforming state-of-the-art cine-CMR-only models by 4.3% while eliminating gadolinium dependency, demonstrating its clinical viability for wide range of populations and healthcare environments.