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
. 2022 Nov 4;22(21):8497.
doi: 10.3390/s22218497.

Evaluation of an AI-Based TB AFB Smear Screening System for Laboratory Diagnosis on Routine Practice

Hsiao-Ting Fu  1   2 , Hui-Zin Tu  3 , Herng-Sheng Lee  3 , Yusen Eason Lin  4 , Che-Wei Lin  2   5   6   7
Affiliations

Evaluation of an AI-Based TB AFB Smear Screening System for Laboratory Diagnosis on Routine Practice

Hsiao-Ting Fu et al. Sensors (Basel). .

Abstract

The most robust and economical method for laboratory diagnosis of tuberculosis (TB) is to identify mycobacteria acid-fast bacilli (AFB) under acid-fast staining, despite its disadvantages of low sensitivity and labor intensity. In recent years, artificial intelligence (AI) has been used in TB-smear microscopy to assist medical technologists with routine AFB smear microscopy. In this study, we evaluated the performance of a TB automated system consisting of a microscopic scanner and recognition program powered by artificial intelligence and machine learning. This AI-based system can detect AFB and classify the level from 0 to 4+. A total of 5930 smears were evaluated on the performance of this automatic system in identifying AFB in daily lab practice. At the first stage, 120 images were analyzed per smear, and the accuracy, sensitivity, and specificity were 91.3%, 60.0%, and 95.7%, respectively. In the second stage, 200 images were analyzed per smear, and the accuracy, sensitivity, and specificity were increased to 93.7%, 77.4%, and 96.6%. After removing disqualifying smears caused by poor staining quality and smear preparation, the accuracy, sensitivity, and specificity were improved to 95.2%, 85.7%, and 96.9%, respectively. Furthermore, the automated system recovered 85 positive smears initially identified as negative by manual screening. Our results suggested that the automated TB system could achieve higher sensitivity and laboratory efficiency than manual microscopy under the quality control of smear preparation. Automated TB smear screening systems can serve as a screening tool at the first screen before manual microcopy.

Keywords: acid-fast bacilli; artificial intelligence; tuberculosis.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest. The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript; or in the decision to publish the results.

Figures

Figure 1
Figure 1
The general workflow of image processing and comparison of performance.
Figure 2
Figure 2
The automated microscopy system: (a) an eight-slide tray in one run. (b) The fixed 1 cm × 2 cm area where microscopy scanning. The slides of 1, 2 and 3 were inadequate smears, the slides of 4 and 5 (marked with red square) were adequate smears. The number represents the five different slides. (c) The fixed 1 cm × 2 cm area on the slide was divided into 10 small areas to be scanned one by one. The 10 areas were marked with the number from 1 to 10. When the suspicious bacteria are detected, the system will indicate the location of area number.
Figure 3
Figure 3
The AFB staining images from trace to 4+.
Figure 4
Figure 4
The two false-positive cases due to the poor smear staining quality.
Figure 5
Figure 5
The confusion matrix of automation system with 200 images capture setting.
Figure 6
Figure 6
The confusion matrix of automation system with 200 images capture setting after removal of inadequate cases.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. World Health Organization . Global Tuberculosis Report 2020. World Health Organization; Geneva, Switzerland: 2020.
    1. Reid M.J.A., Arinaminpathy N., Bloom A., Bloom B.R., Boehme C., Chaisson R., Chin D.P., Churchyard G., Cox H., Ditiu L., et al. Building a tuberculosis-free world: The Lancet Commission on tuberculosis. Lancet. 2019;393:1331–1384. doi: 10.1016/S0140-6736(19)30024-8. - DOI - PubMed
    1. World Health Organization . Global Tuberculosis Report 2021. World Health Organization; Geneva, Switzerland: 2021.
    1. Taiwan CDC . Taiwan Tuberculosis Control Repor 2019. Taiwan CDC (Centers for Disease Control); Taipei, Taiwan: 2019.
    1. Campelo T.A., Cardoso de Sousa P.R., Nogueira L.L., Frota C.C., Zuquim Antas P.R. Revisiting the methods for detecting Mycobacterium tuberculosis: What has the new millennium brought thus far? Access Microbiol. 2021;3:000245. doi: 10.1099/acmi.0.000245. - DOI - PMC - PubMed