Advances in Deep Learning for Tuberculosis Screening using Chest X-rays: The Last 5 Years Review

Abstract

There has been an explosive growth in research over the last decade exploring machine learning techniques for analyzing chest X-ray (CXR) images for screening cardiopulmonary abnormalities. In particular, we have observed a strong interest in screening for tuberculosis (TB). This interest has coincided with the spectacular advances in deep learning (DL) that is primarily based on convolutional neural networks (CNNs). These advances have resulted in significant research contributions in DL techniques for TB screening using CXR images. We review the research studies published over the last five years (2016-2021). We identify data collections, methodical contributions, and highlight promising methods and challenges. Further, we discuss and compare studies and identify those that offer extension beyond binary decisions for TB, such as region-of-interest localization. In total, we systematically review 54 peer-reviewed research articles and perform meta-analysis.

Detection of sarcopenia using deep learning-based artificial intelligence body part measure system (AIBMS)

“…Deep learning applications in healthcare are undergoing rapid development ( Gulshan et al, 2016 ; Esteva et al, 2017 ; Smets et al, 2021 ). In particular, deep learning-based technologies demonstrated great potential in medical imaging diagnosis during COVID-19 ( Santosh, 2020 ; Mukherjee et al, 2021 ; Santosh and Ghosh, 2021 ; Santosh et al, 2022a ; Santosh et al, 2022b ; Mahbub et al, 2022 ). Recently, a number of deep learning techniques for body part analysis using CT images have been developed ( Pickhardt et al, 2020 ; Gao et al, 2021 ).…”

Guest Editorial Multimodal Learning in Medical Imaging Informatics

“…In addition, we aimed for research articles that employed substantial amounts of data, rather than works based on a limited pool of evidence. As we are not limited to one event or disease type (e.g., Tuberculosis [4], lung cancer, cardiac diseases [5], and COVID-19 [6], [7]), the proposed SI aimed at attracting many submissions, ranging from screening to diagnosis, prognosis, and surgery/treatment plans.…”

Artificial intelligence in interventional pulmonology

“…Artificial intelligence technologies have been widely applied and researched in various healthcare fields, including pulmonary medicine. In the last decade, automated chest X-rays image analysis techniques for early tuberculosis screening have grown rapidly [5]. Several commercial products of deep learning based computer-aided detection (CADe) systems for pulmonary tuberculosis are available.…”