Detection of Multiple Diseases from Chest X-Ray Using Machine Learning and Deep Learning Approaches

Abstract

Diagnosis with Chest X-Rays and other forms of medical images has soared to new heights as an alternative Covid-19, pneumonia, TB infection detector. Radiographic images, primarily X-Rays images play massive roles in assisting radiologists to detect and analyses severe medical conditions. Computer-Aided Diagnosis (CAD) systems are used successfully to detect diseases such as tuberculosis, pneumonia, covid-19 and other common diseases from chest X-ray images. The main objective of this study is to develop a model capable of detecting multiple diseases from chest X-rays, with the aim of assisting radiologists and other healthcare providers in making more informed and timely diagnoses. The proposed framework includes four main steps to identify various clinical states such as analysis of the chest X-Ray image dataset and dataset preprocessing, feature extraction, classification with machine and deep learning classifiers and building an ensemble method that can aid in the diagnosis of various diseases using image processing and artificial intelligence algorithms to quickly and accurately identify COVID-19, pneumonia, TB and other diseases from X-Rays to stop the rapid transmission of the virus. The authors obtained a training accuracy of 98% to 100% across all models. Keywords: convolutional neural network, VGG16, machine learning, deep learning. https://doi.org/10.55463/issn.1674-2974.50.4.23