Tuberculosis Diagnostics and Localization in Chest X-Rays via Deep Learning Models

Abstract

For decades, tuberculosis (TB), a potentially serious infectious lung disease, continues to be a leading cause of worldwide death. Proven to be conveniently efficient and cost-effective, chest X-ray (CXR) has become the preliminary medical imaging tool for detecting TB. Arguably, the quality of TB diagnosis will improve vastly with automated CXRs for TB detection and the localization of suspected areas, which may manifest TB. The current line of research aims to develop an efficient computer-aided detection system that will support doctors (and radiologists) to become well-informed when making TB diagnosis from patients' CXRs. Here, an integrated process to improve TB diagnostics via convolutional neural networks (CNNs) and localization in CXRs via deep-learning models is proposed. Three key steps in the TB diagnostics process include (a) modifying CNN model structures, (b) model fine-tuning via artificial bee colony algorithm, and (c) the implementation of linear average-based ensemble method. Comparisons of the overall performance are made across all three steps among the experimented deep CNN models on two publicly available CXR datasets, namely, the Shenzhen Hospital CXR dataset and the National Institutes of Health CXR dataset. Validated performance includes detecting CXR abnormalities and differentiating among seven TB-related manifestations (consolidation, effusion, fibrosis, infiltration, mass, nodule, and pleural thickening). Importantly, class activation mapping is employed to inform a visual interpretation of the diagnostic result by localizing the detected lung abnormality manifestation on CXR. Compared to the state-of-the-art, the resulting approach showcases an outstanding performance both in the lung abnormality detection and the specific TB-related manifestation diagnosis vis-à-vis the localization in CXRs.

A multichannel EfficientNet deep learning-based stacking ensemble approach for lung disease detection using chest X-ray images

“…The model achieved an accuracy of 93. 5 Guo et al [11] proposed an approach to diagnosing TB by fine-tuning the CNN models using an artificial bee colony algorithm and later implementing an ensemble of those models to obtain the classification results. The approach attained an accuracy of 98% Gabor, Gist, histogram of oriented gradients (HOG), and pyramid histogram of oriented gradients (PHOG) features were extracted in [47] to differentiate TB from non-TB cases.…”

“…Out of the 1.4 million deaths caused by TB in 2019, more than 200 thousand patients were HIV positive. The statistics collected from 2018-2018 show how 58 million lives were saved by early diagnosis of TB [ 11 ]. Researchers feel that the time taken to detect and diagnose TB plays a vital role in mitigating the TB’s spread and reducing the death rates.…”

Accurate Integrated System to detect Pulmonary and Extra Pulmonary Tuberculosis using Machine Learning Algorithms

“…The whole process was performed following three important steps, namely the first CNN structures were modified, secondly, the artificial bee colony algorithm was used to fine-tune the model and the last linear average-based ensemble method was implemented. It is concluded that by superimposing the above three steps the overall performance of the Deep Convolution Neural Network increased (Guo, Passi and Jain, 2020).…”

“…The PTB parameters include the basic parameters that the TB patient has whereas the EPTB parameters include the basic as well as the site-related parameters. CXRs (X-Rays) are also collected for TB patients as it the primary tool used for the detection of TB as it is proven to be efficient, cost-effective and it is having high sensitivity (Guo, Passi and Jain, 2020), (Sathitratanacheewin, Sunanta and Pongpirul, 2020b). For PTB, X-rays of lungs are collected whereas, for EPTB, X-Rays of that particular site are collected where the TB is supposed to be.…”

COVID-19 Automatic Detection Using Deep Learning

“…For instance, with a method that can rapidly identify the object region along with a marked line passing, this region of interest might be zoomed in automatically on the display of an X-ray image even if the location and orientation of the object in the image vary appreciably. In this paper, occlusion sensitivity is used as a region localization technique [27], where this technique is a simple and straightforward technique for understanding which regions of an image are important for classification and segmentation purposes. Fig.…”