What type of study is this?

This is a Validation Study study.

What question did this study set out to answer?

This research aims to evaluate the prognostic value of deep learning methods for assessing myocardial scar and microvascular obstruction using CMR imaging.

March 14, 2026Open Access

Prognostic value of end-to-end deep learning assessment of myocardial scar and microvascular obstruction on late gadolinium enhancement cardiovascular magnetic resonance

Key Points

This research aims to evaluate the prognostic value of deep learning methods for assessing myocardial scar and microvascular obstruction using CMR imaging.
Developed and validated LGE-CMRnet for automated segmentation of myocardial scar and MVO using deep learning.
Analyzed 3,874 LGE images from 567 patients with acute myocardial infarction for model training and testing.
Performed Cox regression analysis to assess the prognostic impact of scar and MVO on major adverse cardiac events (MACE).
LGE-CMRnet achieved high segmentation accuracy with a mean Dice similarity coefficient of 0.83 for scar and 0.88 for MVO.
In the external validation, 22.2% of patients experienced MACE, with significant hazard ratios derived for %MVO and %Scar.
The model's performance in predicting MACE was comparable to expert analysis, indicating its viability for clinical risk stratification.

Abstract

Late gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) is the reference standard for assessing myocardial scar and microvascular obstruction (MVO), strong predictors of post-acute myocardial infarction (AMI) outcomes. However, manual segmentation is time-consuming and subject to inter-observer variability, limiting clinical scalability. This study develops and validates LGE-CMRnet, an end-to-end deep learning pipeline for automated scar and MVO segmentation on LGE CMR, and evaluates its prognostic value in AMI patients. A total of 3,874 LGE images from 567 AMI patients (409 for training/internal stress-test cohort; 158 for external testing) were analyzed. LGE-CMRnet integrates YOLOv8 for heart localization and nnU-Net for simultaneous segmentation of myocardium, scar, and MVO. Performance was evaluated using Dice similarity coefficient (DSC), correlation, and Bland-Altman analysis against expert annotations. Prognostic value was assessed using Cox regression for major adverse cardiac events (MACE) over a median follow-up of 24.4 months. LGE-CMRnet achieved rapid processing (0.05 seconds per image) and high segmentation accuracy. In the external validation cohort, the model achieved mean DSC of 0.83±0.11 for scar and 0.88±0.11 for MVO at the patient level, with strong volumetric correlations to expert reference segmentations (scar: r =0.90; MVO: r =0.98, both P <0.0001). Bland-Altman analysis showed minimal bias in volumetric measurements (scar: 2.5±8.9 cm 3 ; MVO: − 0.20±0.89 cm 3 ). Among the 158 patients in the external validation cohort (age 57±10 years, 80% male), 35 (22.2%) experienced MACE. LGE-CMRnet-derived %MVO (hazard ratio HR, 1.06; 95% confidence interval CI: 1.02 to 1.09; P =0.003) and %Scar (HR, 1.05; 95% CI: 1.02 to 1.08; P =0.001) were independent predictors of MACE after adjustment for established risk factors. Furthermore, LGE-CMRnet-derived metrics demonstrated non-inferior discrimination for MACE prediction compared with expert analysis. The differences in C-index were 0.02 for %MVO and 0.01 for %Scar, with the lower bounds of the 95% CIs remaining above the pre-specified non-inferiority margin. LGE-CMRnet enables fast and accurate scar and MVO quantification, with prognostic performance comparable to expert analysis, supporting its potential for automated clinical risk stratification after AMI. Prognostic Value of End-to-End Deep Learning Assessment of Myocardial Scar and Microvascular Obstruction on LGE-CMR. LGE-CMRnet enables fast, accurate scar and MVO quantification with prognostic performance equivalent to expert analysis

Read Full Paperexternally

AI에게 질문

Bookmark

View Full Paper