Related Experiment Video
Updated: Sep 28, 2025
09:47
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
Published on: December 15, 2023
1.3K
Advanced Cognitive Algorithm for Biomedical Data Processing: COVID-19 Pattern Recognition as a Case Study
Mohamed Elhoseny1,2, Zahraa Tarek2, Ibrahim M El-Hasnony2
1College of Computing and Informatics, University of Sharjah, Sharjah, UAE.
Journal of Healthcare Engineering
|April 1, 2022
Summary
This study introduces an artificial neural network (ANN) model optimized with a butterfly algorithm for accurate COVID-19 detection from chest X-rays and CT scans. The hybrid model achieved superior performance in identifying COVID-19 patterns compared to other methods.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Computational Biology
Background:
- Automated disease prediction is crucial for managing public health crises like COVID-19.
- Accurate and rapid diagnosis of COVID-19 is essential to reduce mortality rates.
- Challenges in COVID-19 diagnosis include viral mutation and the need for intelligent detection systems.
Purpose of the Study:
- To develop and evaluate a hybrid artificial neural network (ANN) model for automated COVID-19 detection using chest X-ray (CXR) and computerized tomography (CT) images.
- To optimize the ANN model's parameters using the butterfly optimization algorithm (BOA).
- To compare the proposed model's performance against established methods like AlexNet, GoogLeNet, and Support Vector Machine (SVM).
Main Methods:
- A hybrid model combining an artificial neural network (ANN) with parameter optimization via the butterfly optimization algorithm (BOA) was proposed.
- The model was trained and tested on six publicly available datasets comprising CXR and CT images.
- Performance was evaluated by comparing the proposed model against pretrained AlexNet, GoogLeNet, and SVM.
Main Results:
- The proposed hybrid ANN-BOA model demonstrated superior performance in recognizing COVID-19 patterns from medical images.
- The model achieved an average accuracy of 90.48%, outperforming SVM (81.09%), AlexNet (86.76%), and GoogLeNet (84.97%).
- The experimental results validated the model's effectiveness across both X-ray and CT imaging datasets.
Conclusions:
- The hybrid ANN-BOA model offers a highly accurate and effective approach for automated COVID-19 detection from CXR and CT scans.
- This intelligent detection system can significantly aid physicians in diagnosing COVID-19, leading to faster outcomes and potentially lower mortality rates.
- The study highlights the potential of optimized deep learning models in medical diagnostics for infectious diseases.
