Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Nov 25:2021:1002799.
doi: 10.1155/2021/1002799. eCollection 2021.

A Novel and Robust Approach to Detect Tuberculosis Using Transfer Learning

Omar Faruk  1 , Eshan Ahmed  1 , Sakil Ahmed  1 , Anika Tabassum  1 , Tahia Tazin  1 , Sami Bourouis  2 , Mohammad Monirujjaman Khan  1
Affiliations

A Novel and Robust Approach to Detect Tuberculosis Using Transfer Learning

Omar Faruk et al. J Healthc Eng. .

Retraction in

Abstract

Deep learning has emerged as a promising technique for a variety of elements of infectious disease monitoring and detection, including tuberculosis. We built a deep convolutional neural network (CNN) model to assess the generalizability of the deep learning model using a publicly accessible tuberculosis dataset. This study was able to reliably detect tuberculosis (TB) from chest X-ray images by utilizing image preprocessing, data augmentation, and deep learning classification techniques. Four distinct deep CNNs (Xception, InceptionV3, InceptionResNetV2, and MobileNetV2) were trained, validated, and evaluated for the classification of tuberculosis and nontuberculosis cases using transfer learning from their pretrained starting weights. With an F1-score of 99 percent, InceptionResNetV2 had the highest accuracy. This research is more accurate than earlier published work. Additionally, it outperforms all other models in terms of reliability. The suggested approach, with its state-of-the-art performance, may be helpful for computer-assisted rapid TB detection.

PubMed Disclaimer

Conflict of interest statement

The authors declare that they have no conflicts of interest to report regarding this study.

Figures

Figure 1
Figure 1
Workflow diagram of the TB or normal image detection.
Figure 2
Figure 2
Non-TB X-ray images.
Figure 3
Figure 3
Tuberculosis X-ray images.
Figure 4
Figure 4
Total number of TB and non-TB records.
Figure 5
Figure 5
Block diagram of the proposed system.
Figure 6
Figure 6
System architecture with InceptionResNetV2.
Figure 7
Figure 7
Training and validation accuracy.
Figure 8
Figure 8
Training and validation loss.
Figure 9
Figure 9
Confusion matrix.
Figure 10
Figure 10
Normal prediction.
Figure 11
Figure 11
TB prediction.
See this image and copyright information in PMC

References

    1. Ramya R., Babu P. S. Automatic tuberculosis screening using canny Edge detection method. Proceedings of the 2nd International Conference on Electronics and Communication Systems (ICECS); February 2015; Coimbatore, India. pp. 282–285. - DOI
    1. Who. Geneva, Switzerland: WHO; 2020. Tuberculosis. https://www.who.int/news-room/fact-sheets/detail/tuberculosis .
    1. Sharma S. K., Mohan A. Tuberculosis: from an incurable scourge to a curable disease - journey over a millennium. Indian Journal of Medical Research . 2013;137(9):455–93. - PMC - PubMed
    1. Overview tuberculosis (TB) 2019. https://www.nhs.uk/conditions/tuberculosis-tb/ NHS.
    1. Silverman C. An appraisal of the contribution of mass radiography in the discovery of pulmonary Tuberculosis. American Review of Tuberculosis . 1949;60(4):466–482. doi: 10.1164/art.1949.60.4.466. - DOI - PubMed

Publication types

LinkOut - more resources