Cardiac MRI Semantic Segmentation for Ventricles and Myocardium Using Deep Learning

2025-04-18

Sai

AI Summary

To address insufficient segmentation accuracy of the left ventricular cavity (LV), right ventricular cavity (RV), and left ventricular myocardium (LMyo) in cardiac MRI, this paper proposes an enhanced U-Net architecture that synergistically integrates edge awareness and contextual enhancement. Specifically, an edge-aware downsampling module is embedded in the encoder path, while a dynamic contextual attention fusion mechanism is introduced in the decoder path; optimization employs a joint loss function combining Dice loss and boundary-weighted cross-entropy. This work is the first to jointly model edge structures and global semantics throughout both encoding and decoding stages of U-Net, significantly improving robustness for small structures and boundary delineation. Evaluated on the standard CMR dataset, the method achieves mean Dice score improvements of 2–11% for LV/RV/LMyo and reduces Hausdorff distance by 1.6–5.7 mm, outperforming state-of-the-art approaches.

Technology Category

Computer Vision: SegmentationMachine Learning: Learning on the Edge & Model CompressionSearch and Optimization: Learning to Search

Application Category

Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMsSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingGraph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Automated noninvasive cardiac diagnosis plays a critical role in the early detection of cardiac disorders and cost-effective clinical management. Automated diagnosis involves the automated segmentation and analysis of cardiac images. Precise delineation of cardiac substructures and extraction of their morphological attributes are essential for evaluating the cardiac function, and diagnosing cardiovascular disease such as cardiomyopathy, valvular diseases, abnormalities related to septum perforations, and blood-flow rate. Semantic segmentation labels the CMR image at the pixel level, and localizes its subcomponents to facilitate the detection of abnormalities, including abnormalities in cardiac wall motion in an aging heart with muscle abnormalities, vascular abnormalities, and valvular abnormalities. In this paper, we describe a model to improve semantic segmentation of CMR images. The model extracts edge-attributes and context information during down-sampling of the U-Net and infuses this information during up-sampling to localize three major cardiac structures: left ventricle cavity (LV); right ventricle cavity (RV); and LV myocardium (LMyo). We present an algorithm and performance results. A comparison of our model with previous leading models, using similarity metrics between actual image and segmented image, shows that our approach improves Dice similarity coefficient (DSC) by 2%-11% and lowers Hausdorff distance (HD) by 1.6 to 5.7 mm.

Problem

• Automated segmentation of cardiac MRI for ventricles and myocardium
• Improving accuracy in detecting cardiac structural abnormalities
• Enhancing semantic segmentation performance using deep learning

Innovation

• U-Net with edge-attribute extraction
• Context infusion during up-sampling
• Improved Dice and Hausdorff metrics