U-R-VEDA: Integrating UNET, Residual Links, Edge and Dual Attention, and Vision Transformer for Accurate Semantic Segmentation of CMRs

2025-06-25

AI Summary

This study addresses the limited accuracy of fully automatic semantic segmentation in cardiac magnetic resonance (CMR) images. To this end, we propose a hybrid architecture integrating convolutional neural networks and Transformers within a U-Net framework. Our method introduces three key innovations: (1) a dual attention mechanism jointly modeling channel-wise and spatial dependencies; (2) edge-guided residual skip connections to preserve structural boundaries; and (3) a visual Transformer module for long-range contextual modeling and multi-scale feature enhancement—thereby mitigating information loss inherent in pure convolutional designs. Evaluated on public CMR benchmarks, our model achieves a mean Dice similarity coefficient of 95.2%, outperforming state-of-the-art methods. Notably, it demonstrates robust performance in segmenting challenging structures—the right ventricle and left ventricular myocardium. This work establishes a high-accuracy, interpretable foundation for quantitative cardiac structural analysis and automated clinical diagnosis.

Technology Category

Computer Vision: SegmentationMachine Learning: Calibration & Uncertainty QuantificationIntelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMsSearch and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAGResponsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Artificial intelligence, including deep learning models, will play a transformative role in automated medical image analysis for the diagnosis of cardiac disorders and their management. Automated accurate delineation of cardiac images is the first necessary initial step for the quantification and automated diagnosis of cardiac disorders. In this paper, we propose a deep learning based enhanced UNet model, U-R-Veda, which integrates convolution transformations, vision transformer, residual links, channel-attention, and spatial attention, together with edge-detection based skip-connections for an accurate fully-automated semantic segmentation of cardiac magnetic resonance (CMR) images. The model extracts local-features and their interrelationships using a stack of combination convolution blocks, with embedded channel and spatial attention in the convolution block, and vision transformers. Deep embedding of channel and spatial attention in the convolution block identifies important features and their spatial localization. The combined edge information with channel and spatial attention as skip connection reduces information-loss during convolution transformations. The overall model significantly improves the semantic segmentation of CMR images necessary for improved medical image analysis. An algorithm for the dual attention module (channel and spatial attention) has been presented. Performance results show that U-R-Veda achieves an average accuracy of 95.2%, based on DSC metrics. The model outperforms the accuracy attained by other models, based on DSC and HD metrics, especially for the delineation of right-ventricle and left-ventricle-myocardium.

Problem

• Accurate semantic segmentation of cardiac magnetic resonance images
• Integration of UNET with advanced attention and transformer features
• Improved delineation for cardiac disorder diagnosis and management

Innovation

• UNet enhanced with residual links and dual attention
• Integrates vision transformers for local-feature interrelationships
• Edge-detection skip-connections reduce information-loss