Tuberculosis Detection from Chest Radiographs with Pre-trained Deep Learning Scheme: A Study

Abstract

In human, the abnormality in lung causes a severe respiratory problem and breathing difficulties. Tuberculosis (TB) is one of the common lung abnormality caused due a bacterium named Mycobacterium tuberculosis. TB infection will cause harsh breathing issues and untreated TB will lead to death. Detection of the TB using Chest X-ray is one of the common techniques and in this research work; TB detection using Deep-Learning-Technique (DLT) is demonstrated. The various phases of this research involve; (i) Image collection and resizing, (ii) Deep-Feature (DF) extraction with chosen technique, (iii) Classification using SoftMax classifier and (iv) Performance evaluation with existing technique. The proposed work employs a 5-fold cross validation and the best value is considered as the result. The outcome of this study confirms that, the classification accuracy achieved with ResNetl8 and K-Nearest Neighbor (ResNet+KNN) offered better outcome >97% compared to other DLT of this study.