No Detail Found!

Automated Pulmonary Tuberculosis Screening Based on Deep Convolutional Neural Networks Using Chest Radiographs

Author(s)
Amrat Anmol Department of Computer Science, University of Sargodha, Sargodha 40100, Pakistan
Mahwish Ilyas Department of Computer Science, University of Sargodha, Sargodha 40100, Pakistan
Muhammad Bilal Department of Computing and Information Systems, School of Engineering and Technology, Sunway University, Petaling Jaya 47500, Selangor, Malaysia; Department of Pharmaceutical Outcomes and Policy, Malachowsky Hall for Data Science and Information Technology, University of Florida, Gainesville 32610, Florida, USA
Hikmat Ullah Khan Department of Information Technology, University of Sargodha, Sargodha 40100, Pakistan
Muhammad Ramzan Department of Software Engineering, University of Sargodha, Sargodha 40100, Pakistan
Abstract
Pulmonary Tuberculosis (PTB) is a highly dangerous illness that can have severe consequences if left untreated. Researchers and physicians are taking more interest in using chest radiography to automate the investigation of pulmonary tuberculosis. For early detection and treatment, computer-aided diagnosis (CAD) systems are being used to automate the diagnosis of TB. Previous literature shows that many deep learning-based approaches (DL) have been introduced for the classification of pulmonary tuberculosis using chest radiographs. In this study, we introduced a modified convolutional neural network (CNN) model comprised of 21 layers with different architectural layers. This study aims to classify images into TB and Normal. The presented methodology is trained and evaluated on the dataset created by combining multiple publicly available datasets. Results of the proposed modified CNN model have been compared with the seven individual pre-trained state-of-art models, including VGG16, VGG19, ResNet50, InceptionV3, Xception, MobileNetV2, and EfficientNetB7. The comparison demonstrates that the modified CNN model outperformed pre-trained models by achieving an accuracy of 0.9081, precision of 0.9317, recall of 0.9323, F1 score of 0.9307, and AUC of 0.9474.
Publication Details
Page(s) 23-31
DOI DOI not available
Published Journal: University of Sindh Journal of Information and Communication Technology, Volume: 7, Issue: 1, Year: 2023

Request the full text from PASTIC

Keywords
Classification, deep learning, Tuberculosis, Chest radiographs, Pre-trained
0

Citations

0

Downloads

58

Views