Curriculum-Guided Myocardial Scar Segmentation for Ischemic and Non-ischemic Cardiomyopathy

TL;DR

This paper introduces a curriculum learning framework for myocardial scar segmentation in cardiac MRI, improving accuracy and robustness especially in challenging cases with diffuse or minimal scars.

Contribution

The work presents a novel progressive training strategy that guides the model from high-confidence to ambiguous scar regions, enhancing segmentation performance under difficult conditions.

Findings

Improved segmentation accuracy over standard methods.

Enhanced robustness to uncertain labels and subtle scar features.

Better performance on cases with diffuse or minimal scars.

Abstract

Identification and quantification of myocardial scar is important for diagnosis and prognosis of cardiovascular diseases. However, reliable scar segmentation from Late Gadolinium Enhancement Cardiac Magnetic Resonance (LGE-CMR) images remains a challenge due to variations in contrast enhancement across patients, suboptimal imaging conditions such as post contrast washout, and inconsistencies in ground truth annotations on diffuse scars caused by inter observer variability. In this work, we propose a curriculum learning-based framework designed to improve segmentation performance under these challenging conditions. The method introduces a progressive training strategy that guides the model from high-confidence, clearly defined scar regions to low confidence or visually ambiguous samples with limited scar burden. By structuring the learning process in this manner, the network develops robustness to uncertain labels and subtle scar appearances that are often underrepresented in conventional training pipelines. Experimental results show that the proposed approach enhances segmentation accuracy and consistency, particularly for cases with minimal or diffuse scar, outperforming standard training baselines. This strategy provides a principled way to leverage imperfect data for improved myocardial scar quantification in clinical applications. Our code is publicly available on GitHub.