Detection of Post COVID-Pneumonia Using Histogram Equalization, CLAHE Deep Learning Techniques

doi:10.4114/intartif.vol26iss72pp137-145

Detection of Post COVID-Pneumonia Using Histogram Equalization, CLAHE Deep Learning Techniques

2023-09-06

0

OA

AI

R

Rajkumar, Sujatha *

R

Reddy, Mure Vamsi Kalyan

DOI：10.4114/intartif.vol26iss72pp137-145

Original

Original request for help

Save

Abstract

En 中文

Pneumonia, also known as bronchitis, is caused by bacteria, viruses, or fungi. Pneumonia can be fatal to an infected person because the lungs cannot exchange air. The disease primarily affects infants and people over the age of 65. Every year, nearly 4 million people are killed by the disease, affecting an estimated 420 million people. Detecting and diagnosing the condition as soon as possible is also critical. Diagnosing the condition using the patient's X-ray is the most effective method. Experienced radiologists will use a chest x-ray of the affected patient to make an informed decision. Recently, coronavirus has been a contagious viral disease caused by the SARSCoV2 virus and affects the human respiratory system. The virus also causes pneumonia (COVID pneumonia), which is far more dangerous than ordinary pneumonia. The primary purpose of the work is to study and compare several deep-learning enhancement techniques applied to medical x-ray, and CT scan images to detect COVID-19 (pneumonia).A convolutional neural network (CNN) is used to design a model that can distinguish between COVID-19 pneumonia and ordinary pneumonia. In addition, image enhancement techniques (Histogram Equalization (HE), and Contrast-Limited Adaptive Histogram Equalization (CLAHE) have been processed against the dataset to find more efficient methods and models for detecting pneumonia. A dataset of 6432 CXRs was used -576 COVID pneumonia CXRs, 1583 ordinary pneumonia CXRs, and 4273 healthy lung CXRs. The proposed results proved that the equalized histogram and the equalized dataset of CLAHE run faster than the original dataset. A computer-aided diagnosis (CAD) system is influenced by the framework that can distinguish between COVID pneumonia, ordinary pneumonia, and healthy lungs. In addition, the improved VGG16 achieved 96% accuracy in detecting X-ray images of COVID-19 pneumonia.

Keywords:

Convolution Neural Network

Histogram Equalization (HE)

Contrast Limited Adaptive Histogram Equalization (CLAHE)

Covid-19 (Pneumonia)

Visual Geometry Group (VGG16)

Detection of Post COVID-Pneumonia Using Histogram Equalization, CLAHE Deep Learning Techniques

Abstract

Journal

Organization