Optimal Diagnosis of COVID-19 Based on Convolutional Neural Network and Red Fox Optimization Algorithm

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Computer Vision

Background:

• The global COVID-19 pandemic, caused by SARS-CoV-2, necessitates rapid and accurate diagnosis.
• Human diagnostic errors in identifying COVID-19 from medical images can impact patient outcomes.
• Computer-aided diagnostic systems offer a potential solution to enhance diagnostic accuracy.

Purpose of the Study:

• To develop and validate a novel machine vision pipeline for the accurate detection of COVID-19 from chest X-ray images.
• To improve upon existing diagnostic methods by integrating advanced image processing and machine learning techniques.

Main Methods:

• A new pipeline system involving preprocessing, region segmentation, and feature extraction using Gray-Level Co-occurrence Matrix (GLCM) and Discrete Wavelet Transform (DWT).
• Classification of X-ray images using an improved Convolutional Neural Network (CNN) optimized with the Red Fox Optimization algorithm.
• Validation of the proposed method on three distinct datasets, comparing performance against state-of-the-art techniques.

Main Results:

• The proposed machine vision system demonstrated significant efficiency in diagnosing COVID-19.
• The combined GLCM and DWT feature extraction, coupled with the optimized CNN, yielded accurate classification results.
• Comparative analysis showed superior performance of the suggested method over existing approaches.

Conclusions:

• The developed computer-aided diagnostic system shows high potential for accurate COVID-19 detection from chest X-rays.
• This approach can assist physicians in reducing diagnostic errors and improving patient management during the pandemic.
• Further research and validation could lead to widespread clinical adoption of this AI-driven diagnostic tool.