AUTHOR=Liang Shufan , Ma Jiechao , Wang Gang , Shao Jun , Li Jingwei , Deng Hui , Wang Chengdi , Li Weimin 

TITLE=The Application of Artificial Intelligence in the Diagnosis and Drug Resistance Prediction of Pulmonary Tuberculosis

JOURNAL=Frontiers in Medicine

VOLUME=Volume 9 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2022.935080

DOI=10.3389/fmed.2022.935080

ISSN=2296-858X

ABSTRACT=With the increasing incidence and mortality of pulmonary tuberculosis (TB), in addition to tough and controversial disease management, time-wasting and resource-limited conventional diagnosis and differential approaches to TB are still awkward issues, especially in countries with high tuberculosis burden and backwardness. In the meantime, climbing proportion of drug resistant tuberculosis poses a significant hazard to public health. Thus, auxiliary diagnostic tools with higher efficiency and accuracy are urgently required. Artificial intelligence (AI), which is not new but has recently grown in popularity, provides researchers with opportunities and technical underpinnings to develop novel, precise, rapid, and automated tools for pulmonary tuberculosis care, including but not limited to TB detection. In this review, we aimed to introduce representative AI methods, focusing on deep learning and radiomics, followed by definite descriptions of state-of-the-art AI applications developed using medical images and genetic data to detect pulmonary tuberculosis, distinguish TB from other pulmonary diseases, and identify drug resistance in Mycobacterium tuberculosis (M.tb), with the aim of assisting physicians in deciding the appropriate therapeutic schedule in the early stage of the disease. We also enumerated the challenges in maximizing the impact of AI in pulmonary tuberculosis, including generalization, data standardization, clinical utility of models, and expectation of a more comprehensive application of AI for TB.