Deep Learning Pipeline for Fully Automated Myocardial Infarct Segmentation from Clinical Cardiac MR Scans

2025-02-05

AI Summary

This study addresses the limitations of manual segmentation of myocardial infarction (MI) in late gadolinium enhancement cardiac magnetic resonance (LGE-CMR)—namely, low efficiency, high inter-observer variability, and dependence on expert annotation. We propose an end-to-end fully automated deep learning framework based on a novel cascaded 2D/3D CNN architecture that directly generates MI segmentations without manual preprocessing. In a blinded evaluation across 152 clinical cases, radiologists preferred AI-generated segmentations over human annotations in 33.4% of cases versus 25.1%, demonstrating—for the first time—that AI surpasses human inter-observer consistency in MI delineation. Infarct volume quantification showed excellent agreement with the reference standard (Spearman’s ρc = 0.9). Inference time is minimal, and segmentation quality is comparable to that of experienced cardiologists. However, microvascular obstruction (MVO) detection still requires manual refinement.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Hardware-aware ML
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Purpose: To develop and evaluate a deep learning-based method that allows to perform myocardial infarct segmentation in a fully-automated way. Materials and Methods: For this retrospective study, a cascaded framework of two and three-dimensional convolutional neural networks (CNNs), specialized on identifying ischemic myocardial scars on late gadolinium enhancement (LGE) cardiac magnetic resonance (CMR) images, was trained on an in-house training dataset consisting of 144 examinations. On a separate test dataset from the same institution, including images from 152 examinations obtained between 2021 and 2023, a quantitative comparison between artificial intelligence (AI)-based segmentations and manual segmentations was performed. Further, qualitative assessment of segmentation accuracy was evaluated for both human and AI-generated contours by two CMR experts in a blinded experiment. Results: Excellent agreement could be found between manually and automatically calculated infarct volumes ($ ho_c$ = 0.9). The qualitative evaluation showed that compared to human-based measurements, the experts rated the AI-based segmentations to better represent the actual extent of infarction significantly (p<0.001) more often (33.4% AI, 25.1% human, 41.5% equal). On the contrary, for segmentation of microvascular obstruction (MVO), manual measurements were still preferred (11.3% AI, 55.6% human, 33.1% equal). Conclusion: This fully-automated segmentation pipeline enables CMR infarct size to be calculated in a very short time and without requiring any pre-processing of the input images while matching the segmentation quality of trained human observers. In a blinded experiment, experts preferred automated infarct segmentations more often than manual segmentations, paving the way for a potential clinical application.

Problem

• Automated myocardial infarct segmentation
• Deep learning for cardiac MR scans
• Comparison of AI vs manual segmentations

Innovation

• Deep learning automates infarct segmentation
• CNN cascades analyze LGE CMR images
• AI matches human segmentation accuracy