Original scientific paper
https://doi.org/10.32985/ijeces.14.1.10
A Deep Learning Approach for Automated COVID-19 Detection
Amanpreet Singh
orcid.org/0000-0003-1280-4703
; Department of Electronics and Communication Engineering Punjabi University, Patiala, Punjab, India.
Charanjit Singh
; Department of Electronics and Communication Engineering Punjabi University, Patiala, Punjab, India.
Abstract
Nowadays, COVID-19 is a life-threatening virus for human beings, and the reason behind it is its attack on the respiratory system. A large number of cases of infection were reported with minor to no symptoms. So, detection of the disease at an earlier stage can decrease the death rate in the patients. Chest X-Rays scans can be used primarily for analyzing the infection. X-ray technology is chosen over CT scans because its equipment is readily available, results can be obtained quickly, and the process is quite affordable in terms of cost. This paper proposed a solution using a deep learning approach to detect COVID-19 infection in human lungs using Chest X-Ray scans. Here, we have used CLAHE (Contrast Limited Adaptive Histogram Equalization) to enhance the contrast of X-ray images and then Convolutional Neural Network on CLAHE processed images to improve the accuracy of the overall model. Further, these scans are classified using machine learning classifiers among COVID-19 infected and normal. The proposed model is trained and validated on a publicly available COVID-19 X-ray dataset containing 15917 X-ray Images. Confusion matrices and ROC curves have been generated to analyze the model's efficiency. Training and validation graphs are developed to calculate the other parameters like validation accuracy and training Accuracy. The model's accuracy is 99.8%, which is better than its existing state- of-the-art approaches. These results show that this model is promising for physicians to classify the chest X-Rays scans of infected patients with COVID-19.
Keywords
Deep learning; Medical images; Covid-19 detection; X-ray Images;
Hrčak ID:
292685
URI
Publication date:
26.1.2023.
Visits: 598 *