Novel Self-Calibrated Threshold-Free Probabilistic Fibrosis Signature Technique for 3D Late Gadolinium Enhancement MRI

Abstract

Myocardial fibrosis is a crucial marker of heart muscle injury in several heart disease like myocardial infarction, cardiomyopathies, and atrial fibrillation (AF). Fibrosis and associated scarring (dense fibrosis) are also vital for assessing heart muscle pre- and post-intervention, such as evaluating left atrial (LA) fibrosis/scarring in patients undergoing catheter ablation for AF. Although cardiac MRI is the gold standard for fibrosis assessment, current quantification methods are unreliable due to their reliance on variable thresholding and sensitivity to MRI uncertainties, lacking standardization and reproducibility. Importantly, current methods focus solely on quantifying fibrosis volume ignoring the unique MRI characteristics of fibrosis density and unique distribution, that could better inform on disease severity. To address these issues, we propose a novel threshold-free self-calibrating probabilistic method called “Fibrosis Signatures.” This method efficiently encodes ∼9 billion MRI intensity co-disparities per scan into standardized probability density functions, deriving a unique MRI fibrosis signature index (FSI). The FSI index quantitatively encodes fibrosis/scar extent, density, and distribution patterns simultaneously, providing a detailed assessment of burden/severity. Our self-calibrating design mitigates impacts of MRI uncertainties, ensuring robust evaluations pre- and post-intervention under varying MRI qualities. Extensively validated using a novel numerical phantom and 143 in vivo LA 3D MRIs of AF patients (pre- and post- ablation and serial post-ablation scans) and compared to 5 existing methods, our FSI index demonstrated strong correlations with traditional fibrosis measures and was able to quantify density and distribution pattern beyond entropy. FSI was up to 9 times more reliable and reproducible to MRI uncertainties (noise, segmentation, spatial resolution), highlighting its potential to improve cardiac MRI reliability and clinical utility.