Open Access

ARTICLE

Semantic Pneumonia Segmentation and Classification for Covid-19 Using Deep Learning Network

M. M. Lotfy¹, Hazem M. El-Bakry², M. M. Elgayar³, Shaker El-Sappagh^4,5, G. Abdallah M. I¹, A. A. Soliman¹, Kyung Sup Kwak^6,*

1 Department of Mathematics, Faculty of Science, Arish University, Arish, 45511, Egypt
2 Department of Information Systems, Faculty of Computers and Information, Mansoura University, Mansoura, 35511, Egypt
3 Department of Information Technology, Faculty of Computers and Information, Mansoura University, Mansoura, 35511, Egypt
4 Centro Singular de Investigación en Tecnoloxías Intelixentes (CiTIUS), Universidade de Santiago de Compostela, Santiago de Compostela, 15705, Spain
5 Information Systems Department, Faculty of Computers and Artificial Intelligence, Benha University, Benha, 13512, Egypt
6 Department of Information and Communication Engineering, Inha University, Incheon, 22212, Korea

* Corresponding Author: Kyung Sup Kwak. Email:

Computers, Materials & Continua 2022, 73(1), 1141-1158. https://doi.org/10.32604/cmc.2022.024193

Received 08 October 2021; Accepted 29 December 2021; Issue published 18 May 2022

Abstract

Early detection of the Covid-19 disease is essential due to its higher rate of infection affecting tens of millions of people, and its high number of deaths also by 7%. For that purpose, a proposed model of several stages was developed. The first stage is optimizing the images using dynamic adaptive histogram equalization, performing a semantic segmentation using DeepLabv3Plus, then augmenting the data by flipping it horizontally, rotating it, then flipping it vertically. The second stage builds a custom convolutional neural network model using several pre-trained ImageNet. Finally, the model compares the pre-trained data to the new output, while repeatedly trimming the best-performing models to reduce complexity and improve memory efficiency. Several experiments were done using different techniques and parameters. Accordingly, the proposed model achieved an average accuracy of 99.6% and an area under the curve of 0.996 in the Covid-19 detection. This paper will discuss how to train a customized intelligent convolutional neural network using various parameters on a set of chest X-rays with an accuracy of 99.6%.

---

Keywords

---