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

2025-08-23

AI Summary

This study addresses the clinical limitations of gadolinium-based contrast agents and low-efficiency manual interpretation in cardiomyopathy screening by proposing a contrast-free, automated cine cardiac magnetic resonance (CMR) diagnosis framework. We introduce CC-CMR, the first method to employ cross-modal contrastive learning for latent-space alignment between cine sequences and late gadolinium enhancement (LGE) images, thereby transferring fibrosis-related pathological information into contrast-free representations. Furthermore, we design an uncertainty-guided adaptive multi-task training strategy that jointly optimizes feature interaction and epistemic uncertainty modeling to enhance generalizability and diagnostic consistency. Evaluated on a multicenter cohort of 231 patients, CC-CMR achieves an accuracy of 0.943 (95% CI: 0.886–0.986), outperforming the best existing contrast-free cine-only method by 4.3 percentage points. Critically, it eliminates gadolinium dependency entirely while maintaining robust performance and clinical deployability.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

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.

Problem

• Eliminating gadolinium contrast dependency in cardiomyopathy screening
• Aligning cine CMR and LGE sequences for fibrosis detection
• Improving accuracy of gadolinium-free cardiac MRI diagnosis

Innovation

• Cross-modality contrastive learning for alignment
• Feature interaction module optimizing diagnostic precision
• Uncertainty-guided adaptive training for model generalizability