Joint Diagnosis of Pneumonia, COVID-19, and Tuberculosis from Chest X-ray Images: A Deep Learning Approach
Mohammed Salih Ahmed,
Atta Rahman,
Faris AlGhamdi,
Saleh AlDakheel,
Hammam Hakami,
Ali AlJumah,
Zuhair AlIbrahim,
Mustafa Youldash,
Mohammad Aftab Alam Khan,
Mohammed Imran Basheer Ahmed
Affiliations
Mohammed Salih Ahmed
Department of Computer Engineering, College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam 31441, Saudi Arabia
Atta Rahman
Department of Computer Science, College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam 31441, Saudi Arabia
Faris AlGhamdi
Department of Computer Engineering, College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam 31441, Saudi Arabia
Saleh AlDakheel
Department of Computer Engineering, College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam 31441, Saudi Arabia
Hammam Hakami
Department of Computer Engineering, College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam 31441, Saudi Arabia
Ali AlJumah
Department of Computer Engineering, College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam 31441, Saudi Arabia
Zuhair AlIbrahim
Department of Computer Engineering, College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam 31441, Saudi Arabia
Mustafa Youldash
Department of Computer Engineering, College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam 31441, Saudi Arabia
Mohammad Aftab Alam Khan
Department of Computer Engineering, College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam 31441, Saudi Arabia
Mohammed Imran Basheer Ahmed
Department of Computer Engineering, College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam 31441, Saudi Arabia
Pneumonia, COVID-19, and tuberculosis are some of the most fatal and common lung diseases in the current era. Several approaches have been proposed in the literature for the diagnosis of individual diseases, since each requires a different feature set altogether, but few studies have been proposed for a joint diagnosis. A patient being diagnosed with one disease as negative may be suffering from the other disease, and vice versa. However, since said diseases are related to the lungs, there might be a likelihood of more than one disease being present in the same patient. In this study, a deep learning model that is able to detect the mentioned diseases from the chest X-ray images of patients is proposed. To evaluate the performance of the proposed model, multiple public datasets have been obtained from Kaggle. Consequently, the proposed model achieved 98.72% accuracy for all classes in general and obtained a recall score of 99.66% for Pneumonia, 99.35% for No-findings, 98.10% for Tuberculosis, and 96.27% for COVID-19, respectively. Furthermore, the model was tested using unseen data from the same augmented dataset and was proven to be better than state-of-the-art studies in the literature in terms of accuracy and other metrics.
