Atrial Fibrosis Discernment via Hybrid 2D-3D Trans-Dilated ResUnet++ Leverages Echocardiographic Spatial-Temporal Encoding

International Journal of Electrical and Electronics Engineering

© 2025 by SSRG - IJEEE Journal

Volume 12 Issue 11

Year of Publication : 2025

Authors : P. Sudheer, B. Kirubagari, A. Annamalai giri

10.14445/23488379/IJEEE-V12I11P114

How to Cite?

P. Sudheer, B. Kirubagari, A. Annamalai giri, "Atrial Fibrosis Discernment via Hybrid 2D-3D Trans-Dilated ResUnet++ Leverages Echocardiographic Spatial-Temporal Encoding," SSRG International Journal of Electrical and Electronics Engineering, vol. 12,  no. 11, pp. 163-181, 2025. Crossref, https://doi.org/10.14445/23488379/IJEEE-V12I11P114

Abstract:

Atrial fibrosis is a key pathological factor contributing to cardiac disorders such as Atrial Fibrillation (AF) and Congestive Heart Failure (CHF). AF, a prevalent arrhythmia in adults, significantly increases the risk of early mortality. Although various treatments-ranging from pharmacological interventions to surgical procedures-are available, the mechanisms driving AF and atrial fibrosis remain poorly understood. Moreover, distinguishing AF from normal sinus rhythm is complicated by signal noise and overlapping arrhythmic patterns. To address these diagnostic challenges, this study introduces a novel deep learning framework for early and accurate detection of atrial fibrosis. Initially, 2D echocardiographic images are collected from validated clinical sources. Feature extraction is performed using Convolutional Long Short-Term Memory (Conv-LSTM) networks, capturing fuzzy entropy, wavelet energy, hierarchical patterns, and deep semantic features. These are refined using the Hybrid Squirrel Crow Search Algorithm (HSCSA) to form Feature Set 1. Concurrently, sequential 2D frames are compiled into 3D volumes, forming Feature Set 2. Both feature sets are processed through a custom Hybrid Convolutional Transformer-Dilated Residual Unet++ (HC-TDRUnet++) model, which integrates 2D and 3D convolutional pathways for robust fibrosis detection. The proposed system demonstrates superior accuracy compared to existing models, offering a promising tool for managing AF and reducing the risk of stroke and heart failure.

Keywords:

Segmentation of Atrial Fibrosis, Echocardiogram images, Optimal Feature Selection, Hybrid Squirrel Search, Crow Search Algorithms, Hybrid (2D, 3D) Convolution Transformer-Dilated Residual Unet++.

References:

[1] Nabil Naser, Ivan Stankovic, and Aleksandar Neskovic, “The Reliability of Automated Three-Dimensional Echocardiography-HeartModelA.I. Versus 2D Echocardiography Simpson Methods in Evaluation of Left Ventricle Volumes and Ejection Fraction in Patients with Left Ventricular Dysfunction,” Medical Archives, vol. 76, no. 4, pp. 259-266, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Decai Zeng et al., “Machine Learning Model for Predicting Left Atrial Thrombus or Spontaneous Echo Contrast in Non-Valvular Atrial Fibrillation Patients based on Multimodal Echocardiographic Parameters,” medRxiv, pp. 1-32, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[3] N. Lu et al., “New Deep Learning Approach for Automated Diagnosis of Atrial Fibrillation by Echocardiography Without Ecg,” Canadian Journal of Diabetes, vol. 39, no. 10, pp. s217-s218, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Saroj Kumar Pandey et al., “Automatic Detection of Atrial Fibrillation from ECG Signal using Hybrid Deep Learning Techniques,” Journal of Sensors, vol. 2022, pp. 1-11, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[5] E.K. Mounika et al., “Quantum Feature Pruning for Scalable and Efficient Quantum Kernel-Based High-Dimensional Classification,” 2025 International Conference on Inventive Computation Technologies (ICICT), Kirtipur, Nepal, pp. 1412-1420, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Solomon Osarumwense Alile, “An Ischemic Heart Disease Prediction Model based on Observed Symptoms using Machine Learning,” International Journal of Computer Engineering in Research Trends, vol. 7, no. 9, pp. 9-23, 2020.
[Google Scholar] [Publisher Link]
[7] Sarah W.E. Baalman et al., “A Morphology based Deep Learning Model for Atrial Fibrillation Detection using Single Cycle Electrocardiographic Samples,” International Journal of Cardiology, vol. 316, pp. 130-136, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[8] P. SumanPrakash et al., “Learning-Driven Continuous Diagnostics and Mitigation Program for Secure Edge Management Through Zero-Trust Architecture,” Computer Communications, vol. 220, pp. 94-107, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Yunfan Chen et al., “Atrial Fibrillation Detection using a Feedforward Neural Network,” Journal of Medical and Biological Engineering, vol. 42, no. 1, 63-73, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Amin Ullah et al., “Classification of Arrhythmia by using Deep Learning with 2-D ECG Spectral Image Representation,” Remote Sensing, vol. 12, no. 10, pp. 1-14, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Li Jiahao et al., “An End-End Arrhythmia Diagnosis Model based on Deep Learning Neural Network with Multi-Scale Feature Extraction,” Physical and Engineering Sciences in Medicine, vol. 46, no. 3, pp. 1341-1352, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Yonggang Zou et al., “A Generalizable and Robust Deep Learning Method for Atrial Fibrillation Detection from Long-Term Electrocardiogram,” Biomedical Signal Processing and Control, vol. 90, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[13] R. Anand et al., “An Enhanced Resnet-50 Deep Learning Model for Arrhythmia Detection using Electrocardiogram Biomedical Indicators,” Evolving Systems, vol. 15, no. 1, pp. 83-97, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Yong-Soo Baek et al., “A New Deep Learning Algorithm of 12-Lead Electrocardiogram for Identifying Atrial Fibrillation During Sinus Rhythm,” Scientific Reports, vol. 11, no. 1, pp. 1-10, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Jianxin Xie, Stavros Stavrakis, and Bing Yao, “Automated Identification of Atrial Fibrillation from Single-Lead ECGs using Multi-Branching Resnet,” Frontiers in Physiology, vol. 15, pp. 1-17, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Xiangyu Zhao et al., “Atrial Fibrillation Detection with Single-Lead Electrocardiogram based on Temporal Convolutional Network-ResNet,” Sensors, vol. 24, no. 2, pp. 1-14, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Neal Yuan et al., “Deep Learning Evaluation of Echocardiograms to Identify Occult Atrial Fibrillation,” npj Digital Medicine, vol. 7, no. 1, pp. 1-8, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Bambang Tutuko et al., “Afibnet: An Implementation of Atrial Fibrillation Detection with Convolutional Neural Network,” BMC Medical Informatics and Decision Making, vol. 21, no. 1, pp. 1-17, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Luigi Di Biase et al., “Feasibility of Three-Dimensional Artificial Intelligence Algorithm Integration with Intracardiac Echocardiography for Left Atrial Imaging During Atrial Fibrillation Catheter Ablation,” EP Europace, vol. 25, no. 9, pp. 1-7, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Luan Tran et al., “Multifusionnet: Atrial Fibrillation Detection with Deep Neural Networks,” AMIA Summits on Translational Science Proceedings, pp. 654-663, 2020.
[Google Scholar] [Publisher Link]
[21] Xin Liu et al., “Deep Learning-Based Automated Left Ventricular Ejection Fraction Assessment using 2-D Echocardiography,” American Journal of Physiology-Heart and Circulatory Physiology, vol. 321, no. 2, pp. H390-H399, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Orod Razeghi et al., “Fully Automatic Atrial Fibrosis Assessment using a Multilabel Convolutional Neural Network,” Circulation: Cardiovascular Imaging, vol. 13, no. 12, pp. 1-11, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Nelson Lu et al., “Automated Atrial Fibrillation Diagnosis by Echocardiography without ECG: Accuracy and Applications of a New Deep Learning Approach,” Diseases, vol. 12, no. 2, pp. 1-10, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Alugonda Rajani, and Sai Lakshmi Dangeti, “Accuracy Enhancement during Atrial Fibrillation Detection using Hybrid Machine Learning Algorithm and Echo Peak Detection Algorithm,” International Conference on Recent Advances in Deep Learning (ICRADL-2021), Kakinada, India, vol. 9, no. 5, pp. 389-393, 2021.
[Google Scholar] [Publisher Link]
[25] S. Mounika et al., “Heart Disease Prediction using Machine Learning with Recursive Feature Elimination for Optimized Performance,” International Journal of Computer Engineering in Research Trends, vol. 11, no. 1s, pp. 61-67, 2024.
[Publisher Link]
[26] Wei Huang, Xiaobo Lu, and Xiaojing Ling, “Wavelet Packet based Feature Extraction and Recognition of License Plate Characters,” Chinese Science Bulletin, vol. 50, no. 2, pp. 97-100, 2005.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Di Wang et al., “Hfenet: Hierarchical Feature Extraction Network for Accurate Landcover Classification,” Remote Sensing, vol. 14, no. 17, pp. 1-24, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Linwei Ye, Zhi Liu, and Yang Wang, “Dual Convolutional LSTM Network for Referring Image Segmentation,” IEEE Transactions on Multimedia, vol. 22, no. 12, pp. 3224-3235, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Zijian Zhao et al., “Kolmogorov-Arnold-Based Network with Lightweight Feature Fusion Schema for Single-Lead Electrocardiogram Atrial Fibrillation Detection,” 2024 IEEE 24th International Conference on Bioinformatics and Bioengineering (BIBE), Kragujevac, Serbia, pp. 1-6, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Mohit Jain, Vijander Singh, and Asha Rani, “A Novel Nature-Inspired Algorithm for Optimization: Squirrel Search Algorithm,” Swarm and Evolutionary Computation, vol. 44, pp. 148-175, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Antono Adhi, Budi Santosa, and Nurhadi Siswanto, “A Meta-Heuristic Method for Solving Scheduling Problem: Crow Search Algorithm,” IOP Conference Series: Materials Science and Engineering, International Conference on Industrial and Systems Engineering (IConISE), Denpasar, Bali, Indonesia, vol. 337, pp. 1-6, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[32] R. Johny Elton et al., “Voice Activity Detection using Smoothed-Fuzzy Entropy (Smfuzzyen) and Support Vector Machine,” Journal of Applied Research and Technology, vol. 17, no. 1, pp. 8-19, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[33] Chao Che et al., “Constrained Transformer Network for ECG Signal Processing and Arrhythmia Classification,” BMC Medical Informatics and Decision Making, vol. 21, no. 1, pp. 1-13, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[34] Lirong Yin et al., “Convolution-Transformer for Image Feature Extraction,” CMES-Computer Modeling in Engineering and Sciences, vol. 141, no. 1, pp. 87-106, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[35] Tareq Hamadneh et al., “Addax Optimization Algorithm: A Novel Nature-Inspired Optimizer for Solving Engineering Applications,” International Journal of Intelligent Engineering and Systems, vol. 17, no. 3, pp. 732-743, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[36] Belal Al-Khateeb et al., “Rock Hyraxes Swarm Optimization: A New Nature-Inspired Metaheuristic Optimization Algorithm,” Computers, Materials and Continua, vol. 68, no. 1, pp. 643-654, 2021.
[CrossRef] [Google Scholar] [Publisher Link]