Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{167101,
        author = {Darbha Sai Srikanth and Dr. K. Santhi Sree},
        title = {Empowering Tuberculosis Diagnosis with Deep Learning: Unveiling the Strengths of Xception and  DenseNet},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {3},
        pages = {313-321},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=167101},
        abstract = {Mycobacterium tuberculosis is a bacterium which causes TB(Tuberculosis). It can easily pass/transfer from one person to another. It is one of the major health problems particularly in developing countries. Tuberculosis can be detected in a person depending on some symptoms, and from analyzing the CXR (Chest X-Ray). Under this scenario, fast detection of TB is important and is must for quick treatment, recovery and control of the disease. One of the reliable tests to detect TB is Isolating the bacteria which causes TB this is an effective method to detect TB but takes more time to get report and a bit expensive. As early detection of TB is very important for control of disease So, in current study we’ll use deep learning to address this issue and find to better way to diagnose Tuberculosis with low cost and high specificity. Comparing different models in deep learning we’ll find best model which works effectively for Tuberculosis. After analyzing CBAMDensenet, WideResnet, Densenet, Resnet, Xception, Inception etc. Xcepion surpasses all the model in accuracy making it very good and efficient for TB diagnosis using CXR},
        keywords = {Chest X-ray, convolutional neural network, deep learning, disease diagnosis, tuberculosis},
        month = {August},
        }