TBNet:Pulmonary Tuberculosis Diagnosing System using Deep Neural Networks

TL;DR

This paper presents TBNet, a deep learning system using ResNet and feature-based data augmentation to improve early tuberculosis detection from chest X-rays, reducing reliance on traditional sputum tests.

Contribution

Introduces a novel deep neural network approach with feature-based data augmentation for more accurate and faster tuberculosis diagnosis from chest X-ray images.

Findings

Achieved a 10% increase in detection accuracy.

Utilized feature-based augmentation to enhance model robustness.

Outperformed previous methods in tuberculosis detection accuracy.

Abstract

Tuberculosis is a deadly infectious disease prevalent around the world. Due to the lack of proper technology in place, the early detection of this disease is unattainable. Also, the available methods to detect Tuberculosis is not up-to a commendable standards due to their dependency on unnecessary features, this make such technology obsolete for a reliable health-care technology. In this paper, I propose a deep-learning based system which diagnoses tuberculosis based on the important features in Chest X-rays along with original chest X-rays. Employing our system will accelerate the process of tuberculosis diagnosis by overcoming the need to perform the time-consuming sputum-based testing method (Diagnostic Microbiology). In contrast to the previous methods \cite{kant2018towards, melendez2016automated}, our work utilizes the state-of-the-art ResNet \cite{he2016deep} with proper data augmentation using traditional robust features like Haar \cite{viola2005detecting,viola2001rapid} and LBP \cite{ojala1994performance,ojala1996comparative}. I observed that such a procedure enhances the rate of tuberculosis detection to a highly satisfactory level. Our work uses the publicly available pulmonary chest X-ray dataset to train our network \cite{jaeger2014two}. Nevertheless, the publicly available dataset is very small and is inadequate to achieve the best accuracy. To overcome this issue I have devised an intuitive feature based data augmentation pipeline. Our approach shall help the deep neural network \cite{lecun2015deep,he2016deep,krizhevsky2012imagenet} to focus its training on tuberculosis affected regions making it more robust and accurate, when compared to other conventional methods that use procedures like mirroring and rotation. By using our simple yet powerful techniques, I observed a 10\% boost in performance accuracy.