Enhanced Tuberculosis Diagnosis through AI-Powered Analysis of Chest X-Rays

DOI

10.2991/978-94-6463-754-0_18How to use a DOI?

Keywords

Tuberculosis; diagnosis; Artificial Intelligence; Chest X-Rays; Convolutional Neural Networks; HealthCare Automation; Deep Learning; Medical Imaging

Abstract

Tuberculosis (TB) is still a worthy global health concern and more so in the low and middle-income countries. Till date, the early diagnosis of the disease still remains problematic due to the inadequacy of diagnostic technology that is accessible in today’s medical practice. One of the most utilised screening tools is the Chest X-ray since they are non-invasive, however their efficiency is disputed by the fact that they require radiologists and they are subject to human error. The goal of this paper is to introduce an AI based model to support the detection of Tuberculosis through automated X-ray image analysis. This paper therefore proposes a system with high accuracy and speed through deep learning most importantly, Convolutional Neural Networks (CNNs) for identifying TB-related abnormalities. An extensive collection of chest X-ray pictures that are either positive or negative for tuberculosis (TB) is used to train this AI model. There is first the preprocessing of the images which are used in the X-ray then came feature extraction and classification. Their performance is assessed using specific diagnostic parameters which includes specificity, sensitivity, accuracy, and F1 score where the new model shows relatively high accuracy compared to traditional diagnostic models that are in use. Moreover, it is also scalable and versatile that can be applied to various health care facilities, thus suitable for use when diagnosing TB in developing countries. It is done to design of an efficient AI model for the detection of TB, an assessment of the proposed approach when benchmarked against the existing methods of diagnosis and an analysis of the application of the proposed model in the real setting. According to this study, the AI-based strategy to interpretations of chest x-rays is a promising tool for complementing the existing diagnosis of TB, so as to alleviate the current load on the healthcare systems and enhance the quality of outcomes for patients.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - C. S. Sandeep
PY  - 2025
DA  - 2025/06/30
TI  - Enhanced Tuberculosis Diagnosis through AI-Powered Analysis of Chest X-Rays
BT  - Proceedings of the 2025 International Conference on Advanced Research in Electronics and Communication Systems (ICARECS-2025)
PB  - Atlantis Press
SP  - 189
EP  - 202
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6463-754-0_18
DO  - 10.2991/978-94-6463-754-0_18
ID  - Sandeep2025
ER  -