Seeing Beyond the Image: ECG and Anatomical Knowledge-Guided Myocardial Scar Segmentation from Late Gadolinium-Enhanced Images

2025-11-18

AI Summary

Late gadolinium enhancement (LGE) cardiac MRI suffers from low contrast and artifacts, hindering physiologically plausible myocardial scar segmentation. To address this, we propose a physiology-consistent multimodal segmentation framework that uniquely integrates electrocardiogram (ECG) time-series signals with the AHA-17 anatomical prior. We design a Time-Aware Feature Fusion (TAFF) mechanism to dynamically align asynchronously acquired ECG and MRI data, leveraging electrophysiological conduction abnormality cues to guide segmentation. Built upon nnU-Net, our architecture incorporates an ECG temporal modeling module and an AHA-17 region-constrained loss. Evaluated on clinical data, our method achieves a mean Dice score of 0.8463 (+23.1% over baselines), precision of 0.9115, and sensitivity of 0.9043—significantly outperforming state-of-the-art approaches. This work establishes a cross-modal electrophysiology–imaging synergy for precise, physiologically grounded scar localization.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

Accurate segmentation of myocardial scar from late gadolinium enhanced (LGE) cardiac MRI is essential for evaluating tissue viability, yet remains challenging due to variable contrast and imaging artifacts. Electrocardiogram (ECG) signals provide complementary physiological information, as conduction abnormalities can help localize or suggest scarred myocardial regions. In this work, we propose a novel multimodal framework that integrates ECG-derived electrophysiological information with anatomical priors from the AHA-17 atlas for physiologically consistent LGE-based scar segmentation. As ECGs and LGE-MRIs are not acquired simultaneously, we introduce a Temporal Aware Feature Fusion (TAFF) mechanism that dynamically weights and fuses features based on their acquisition time difference. Our method was evaluated on a clinical dataset and achieved substantial gains over the state-of-the-art image-only baseline (nnU-Net), increasing the average Dice score for scars from 0.6149 to 0.8463 and achieving high performance in both precision (0.9115) and sensitivity (0.9043). These results show that integrating physiological and anatomical knowledge allows the model to"see beyond the image", setting a new direction for robust and physiologically grounded cardiac scar segmentation.

Problem

• Segmenting myocardial scar from LGE-MRI using ECG and anatomical guidance
• Integrating ECG signals with anatomical priors for consistent scar segmentation
• Addressing temporal misalignment between ECG and MRI via dynamic feature fusion

Innovation

• Integrating ECG signals with anatomical priors for segmentation
• Using temporal aware feature fusion for multimodal data
• Achieving physiologically consistent myocardial scar segmentation