Robust ventricular segmentation in cardiac MRI via fused attention and capsule networks
Open Access
- 17 March 2026
- journal article
- research article
- Published by Walter de Gruyter GmbH in Biomedical Engineering / Biomedizinische Technik
- Vol. 71 (4-5) , 285-300
Abstract
Objectives: An effective automatic system for ventricular segmentation from MRI is vital for diagnosing cardiovascular diseases, yet challenges persist due to anatomical variations and artifacts. Methods: We preprocess cardiac MRI with min-max normalization, then propose a hybrid segmentation network (ResFAU-net) integrating residual blocks, attention gates, and a Fused Accumulation Bridge module to delineate ventricle boundaries. The segmented regions are classified by the HAMC3 model, which combines cascaded capsule networks, CNNs, and hierarchical attention, with parameters optimized via the Coati Optimization Algorithm (COA). Results: Rigorous assessment on our CMRI dataset using metrics (Dice, IoU, accuracy, precision, etc.) demonstrates the model’s high performance in segmenting and classifying the left and right ventricles achieving an IoU of 96.29 % and accuracy of 99.03 %. Conclusions: The proposed ResFAU-net and HAMC3 framework offers a robust, end-to-end solution for precise ventricular cardiac analysis, demonstrating strong potential to automate and enhance the efficiency of cardiovascular diagnosis in clinical MRI workflows.Keywords
Funding Information
- Fujian Provincial Natural Science Foundation of China (2023J01895)
This publication has 43 references indexed in Scilit:
- Hybrid Optimization Algorithm Enabled Deep Learning Approach Brain Tumor Segmentation and Classification Using MRIJournal of Digital Imaging, 2023
- Application of Deep Convolutional Neural Networks MobileNetV2 and Xception for Detecting Cardiac Arrhythmia2023
- The auto segmentation for cardiac structures using a dual‐input deep learning network based on vision saliency and transformerJournal of Applied Clinical Medical Physics, 2022
- Automatic Cardiac Structure Contouring for Small Datasets with Cascaded Deep Learning ModelsJournal of Medical Systems, 2022
- COV-ECGNET: COVID-19 detection using ECG trace images with deep convolutional neural networkHealth Information Science and Systems, 2022
- Artificial neural networks in academic performance prediction: Systematic implementation and predictor evaluationComputers and Education: Artificial Intelligence, 2021
- Predictive modelling and analytics for diabetes using a machine learning approachApplied Computing and Informatics, 2020
- Improved arterial spin labeling after myocardial infarction in mice using cardiac and respiratory gated look-locker imaging with fuzzy C-means clusteringMagnetic Resonance in Medicine, 2010
- A Virtual Screening Method for Prediction of the hERG Potassium Channel Liability of Compound LibrariesChemBioChem, 2002
- Artificial neural networks for pattern recognitionSādhanā, 1994