What question did this study set out to answer?

This research aims to improve the segmentation of myocardial structures and infarct regions in LGE-MRI images using a two-stage deep learning framework.

May 12, 2026

Two-stage deep learning framework for myocardial infarction segmentation in late-gadolinium enhancement magnetic resonance imaging images

Puntos clave

This research aims to improve the segmentation of myocardial structures and infarct regions in LGE-MRI images using a two-stage deep learning framework.
Developed a two-stage framework for segmentation with DeepLabv3+ (ResNet50 for LV cavity and Xception for myocardium and scar).
Utilized Dice loss and Adam optimizer for training, incorporating baseline evaluation and post-processing validation.
Phased development included model evaluation, loss exploration, integration, and final validation.
Achieved high segmentation performance for LV cavity (Dice = 0.947) and myocardium (Dice = 0.7351).
Scar segmentation was more challenging with a Dice score of only 0.0556 due to its small size and low contrast.
The two-stage framework enhanced anatomical accuracy and decreased inter-class misclassification.

Resumen

Accurate segmentation of myocardial structures and infarct regions in late-gadolinium enhancement magnetic resonance imaging (LGE-MRI) is essential for diagnosing ischemic heart disease (IHD). However, traditional and single-stage deep learning (DL) methods struggle with small or low-contrast regions such as myocardial scars. This study proposes a two-stage DL framework to address these limitations. Stage 1 segments the LV cavity using DeepLabv3+ (ResNet50), and Stage 2 segments the myocardium and scar using DeepLabv3+ (Xception). The framework was developed through four phases: baseline evaluation, loss and optimizer exploration, two-stage pipeline integration, and final validation with post-processing. Both models were trained using Dice loss and Adam optimizer. Final testing showed high segmentation performance for the LV cavity (Dice = 0.947) and myocardium (Dice = 0.7351). Scar segmentation remained challenging (Dice = 0.0556) due to small size and low contrast. Nonetheless, the modular design enhanced anatomical accuracy and reduced inter-class misclassification, demonstrating its potential for clinical cardiac image analysis.

Preguntar a la IA

Me gusta

Guardar

Ver artículo completo