Artificial intelligence-based screening for mycobacteria in whole-slide images of tissue samples
Abstract
OBJECTIVES: This study aimed to develop and validate a deep learning algorithm to screen digitized acid fast-stained (AFS) slides for mycobacteria within tissue sections. METHODS: A total of 441 whole-slide images (WSIs) of AFS tissue material were used to develop a deep learning algorithm. Regions of interest with possible acid-fast bacilli (AFBs) were displayed in a web-based gallery format alongside corresponding WSIs for pathologist review. Artificial intelligence (AI)-assisted analysis of another 138 AFS slides was compared to manual light microscopy and WSI evaluation without AI support. RESULTS: Algorithm performance showed an area under the curve of 0.960 at the image patch level. More AI-assisted reviews identified AFBs than manual microscopy or WSI examination (P < .001). Sensitivity, negative predictive value, and accuracy were highest for AI-assisted reviews. AI-assisted reviews also had the highest rate of matching the original sign-out diagnosis, were less time-consuming, and were much easier for pathologists to perform (P < .001). CONCLUSIONS: This study reports the successful development and clinical validation of an AI-based digital pathology system to screen for AFBs in anatomic pathology material. AI assistance proved to be more sensitive and accurate, took pathologists less time to screen cases, and was easier to use than either manual microscopy or viewing WSIs.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
There is potential for using AI models for the detection of fungal organisms, as already reported in other fields of histopathology.
“Hence, there is potential for using AI models for the detection of fungal organisms, as already reported in other fields of histopathology [27,28,29,30,31].”
From Artificial Intelligence in the Histopathological Assessment of Non-Neoplastic Skin Disorders: A Narrative Review with Future Perspectives (2025) · cites this paper as [30]
Dependence on special stains meant there was less potential of shortening turnaround times and reducing the use of resources.
“Additionally, the dependence on special stains meant there was less potential of shortening turnaround times and reducing the use of resources [26,27,28,29,30,31,32].”
From Artificial Intelligence in the Histopathological Assessment of Non-Neoplastic Skin Disorders: A Narrative Review with Future Perspectives (2025) · cites this paper as [30]
Cites
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016 · see citing works
Matplotlib: a 2D graphics environment
Hunter, J. D. (2007) · Computing in Science & Engineering · doi:10.1109/mcse.2007.55 · Cited by 39,249 · see citing works
Global tuberculosis report (2014)
Gabbasova, L. A., & Who, E. R. E. (2014) · Cited by 12,702 · see citing works
GhostNet: More Features From Cheap Operations
Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., & Xu, C. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00165 · Cited by 5,222 · see citing works
OpenSlide: A vendor-neutral software foundation for digital pathology
Goode, A., Gilbert, B., Harkes, J., Jukic, D., & Satyanarayanan, M. (2013) · Journal of Pathology Informatics · doi:10.4103/2153-3539.119005 · Cited by 546 · see citing works
A study about color normalization methods for histopathology images
Roy, S., Jain, A. K., Lal, S., & Kini, J. R. (2018) · Micron · doi:10.1016/j.micron.2018.07.005 · Cited by 185 · see citing works
Automatic detection of mycobacterium tuberculosis using artificial intelligence
Xiong, Y., Ba, X., Hou, A., Zhang, K., Chen, L., & Li, T. (2018) · Journal of Thoracic Disease · doi:10.21037/jtd.2018.01.91 · Cited by 162 · see citing works
Factors Affecting the Clinical Value of Microscopy for Acid-Fast Bacilli
Lipsky, B. A., Gates, J., Tenover, F. C., et al. (1984) · Clinical Infectious Diseases · doi:10.1093/clinids/6.2.214 · Cited by 155 · see citing works
Machine learning in the clinical microbiology laboratory: has the time come for routine practice?
Peiffer‐Smadja, N., Dellière, S., Rodriguez, C., Birgand, G., Lescure, F.-X., Fourati, S., & Ruppé, É. (2020) · Clinical Microbiology and Infection · doi:10.1016/j.cmi.2020.02.006 · Cited by 144 · see citing works
Image analysis and artificial intelligence in infectious disease diagnostics
Smith, K. P., & Kirby, J. E. (2020) · Clinical Microbiology and Infection · doi:10.1016/j.cmi.2020.03.012 · Cited by 118 · see citing works
Lessons From a Proficiency Testing Event for Acid-Fast Microscopy
Somoskövi, Á., Hotaling, J. E., Fitzgerald, M., et al. (2001) · CHEST Journal · doi:10.1378/chest.120.1.250 · Cited by 109 · see citing works
Automated focusing in bright‐field microscopy for tuberculosis detection
Osibote, O. A., Dendere, R., KRISHNAN, S., et al. (2010) · Journal of Microscopy · doi:10.1111/j.1365-2818.2010.03389.x · Cited by 88 · see citing works
Automatic identification of Mycobacterium tuberculosis by Gaussian mixture models
Forero, M. G., Cristóbal, G., & Desco, M. (2006) · Journal of Microscopy · doi:10.1111/j.1365-2818.2006.01610.x · Cited by 79 · see citing works
Colour in digital pathology: a review
Clarke, E. L., & Treanor, D. E. (2016) · Histopathology · doi:10.1111/his.13079 · Cited by 78 · see citing works
Automated Tuberculosis Diagnosis Using Fluorescence Images from a Mobile Microscope
Chang, J., Arbeláez, P., Switz, N. A., Reber, C. D., Tapley, A., Davis, J. L., Cattamanchi, A., Fletcher, D. A., & Malik, J. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33454-2_43 · Cited by 75 · see citing works
Image processing techniques for identifying Mycobacterium tuberculosis in Ziehl-Neelsen stains.
Sadaphal, P., Rao, J. B., Comstock, G. W., et al. (2008) · PubMed · Cited by 72 · see citing works
Panicker, R. O., Soman, B., Saini, G., & Rajan, J. (2015) · Journal of Medical Systems · doi:10.1007/s10916-015-0388-y · Cited by 72 · see citing works
The Acid-Fast Stain: A Specific and Predictive Test for Mycobacterial Disease
Murray, P. R., ELMORE, C., & KROGSTAD, D. J. (1980) · Annals of Internal Medicine · doi:10.7326/0003-4819-92-4-512 · Cited by 62 · see citing works
Automated identification of tubercle bacilli in sputum. A preliminary investigation.
Veropoulos, K., Learmonth, G., Campbell, C., Knight, B., & Simpson, J. (1999) · PubMed · Cited by 60 · see citing works
Khutlang, R., Krishnan, S. M., Whitelaw, A. C., et al. (2009) · Journal of Microscopy · doi:10.1111/j.1365-2818.2009.03308.x · Cited by 56 · see citing works
Automatic identification of mycobacterium tuberculosis with conventional light microscopy
Costa, M. G. F., Filho, C. F. F. C., Sena, J. F., et al. (2008) · doi:10.1109/iembs.2008.4649170 · Cited by 55 · see citing works
Mateos-Pérez, J. M., Redondo, R., Nava, R., et al. (2012) · Cytometry Part A · doi:10.1002/cyto.a.22020 · Cited by 55 · see citing works
Lewis, J. J., Chihota, V. N., van der Meulen, M., Fourie, P. B., Fielding, K., Grant, A. D., Dorman, S. E., & Churchyard, G. (2012) · PLoS ONE · doi:10.1371/journal.pone.0050173 · Cited by 49 · see citing works
Rhoads, D. D. (2020) · Journal of Clinical Microbiology · doi:10.1128/jcm.00511-20 · Cited by 46 · see citing works
Kuok, C., Horng, M., Liao, Y., et al. (2019) · Microscopy Research and Technique · doi:10.1002/jemt.23217 · Cited by 41 · see citing works
Automatic microscopic detection of mycobacteria in sputum: a proof-of-concept
Zingué, D., Weber, P., Soltani, F., Raoult, D., & Drancourt, M. (2018) · Scientific Reports · doi:10.1038/s41598-018-29660-8 · Cited by 38 · see citing works
Computer-Assisted Screening of Ziehl-Neelsen–Stained Tissue for Mycobacteria
Tadrous, P. J. (2010) · American Journal of Clinical Pathology · doi:10.1309/ajcpmr3blvbh8thv · Cited by 30 · see citing works
Visual Memory Effects on Intraoperator Study Design
Campbell, W. S., Talmon, G. A., Foster, K. W., Baker, J. J., Smith, L. M., & Hinrichs, S. H. (2015) · American Journal of Clinical Pathology · doi:10.1309/ajcpuc3tyms3qobm · Cited by 27 · see citing works
Osman, M. K., Mashor, . Y., & Jaafar, H. (2012) · International Conference on Computer, Information and Telecommunication Systems · doi:10.1109/cits.2012.6220378 · Cited by 20 · see citing works
Staining for acid-fast bacilli in surgical pathology: practice patterns and variations
Wu, R. I., Mark, E. J., & Hunt, J. L. (2012) · Human Pathology · doi:10.1016/j.humpath.2012.01.006 · Cited by 19 · see citing works
Cost-Effectiveness of Automated Digital Microscopy for Diagnosis of Active Tuberculosis
Jha, S., Ismail, N. A., Clark, D., Lewis, J. J., Omar, S. V., Dreyer, A. W., Chihota, V. N., Churchyard, G., & Dowdy, D. W. (2016) · PLoS ONE · doi:10.1371/journal.pone.0157554 · Cited by 13 · see citing works
Comparison of the diagnostic utility of digital pathology systems for telemicrobiology
Rhoads, D. D., Habib-Bein, N. F., Hariri, R. S., et al. (2016) · Journal of Pathology Informatics · doi:10.4103/2153-3539.177687 · Cited by 12 · see citing works
Tavolara, T. E., Niazi, K. M. K., Beamer, G., et al. (2020) · SPIE Medical Imaging: Digital Pathology · doi:10.1117/12.2549016 · Cited by 5 · see citing works
Russell, M. J. (2006) · Open University of Cape Town (University of Cape Town) · Cited by 3 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
The explainability paradox: Challenges for xAI in digital pathology
Evans, T., Retzlaff, C. O., Geißler, C., Kargl, M., Plass, M., Müller, H., Kiehl, T.-R., Zerbe, N., & Holzinger, A. (2022) · Future Generation Computer Systems · doi:10.1016/j.future.2022.03.009 · Cited by 135 · see citing works
Artificial intelligence-based tools applied to pathological diagnosis of microbiological diseases
Marletta, S., L’Imperio, V., Eccher, A., Antonini, P., Santonicco, N., Girolami, I., Dei Tos, A. P., Sbaraglia, M., Pagni, F., Brunelli, M., et al. (2023) · Pathology - Research and Practice · doi:10.1016/j.prp.2023.154362 · Cited by 49 · see citing works
Self-citationRappoport, N., Goldinger, G., Debby, A., Molchanov, Y., Barak, Y., Gildenblat, J., Hadar, O., Sagiv, C., & Barzilai, A. (2024) · Pathology - Research and Practice · doi:10.1016/j.prp.2024.155480 · Cited by 11 · see citing works
Della Mura, M., Sorino, J., Colagrande, A., Daruish, M., Ingravallo, G., Massaro, A., Cazzato, G., Lupo, C., Casatta, N., Ribatti, D., et al. (2025) · Medical Sciences · doi:10.3390/medsci13020070 · Cited by 6 · see citing works
- Authors
- Pantanowitz, L., Wu, U., Seigh, L., LoPresti, E., Yeh, F.-C., Salgia, P., Michelow, P., Hazelhurst, S., Chen, W.-Y., Hartman, D., & Yeh, C.-Y.
- Affiliations
- National Health Laboratory Service (ZA)
- National Cheng Kung University (TW)
- University of Pittsburgh Medical Center (US)
- University of Pittsburgh (US)
- University of the Witwatersrand (ZA)
- Wan Fang Hospital (TW)
- aetherAI, Taipei, Taiwan
- Corresponding author
- Pantanowitz, Liron
- ORCID
- Venue
- American Journal of Clinical Pathology
- Publisher
- Oxford University Press (OUP)
- Published
- 2021-02-02
- Volume
- 156
- Issue
- 1
- Pages
- 117-128
- ISSN
- 0002-9173 (ISSN-L)
- 1943-7722
- OpenAlex
- W3127039237
- Cited by
- 45
- References
- 34
- Citations by year
- 2026: 8 · 2025: 9 · 2024: 15 · 2023: 4 · 2022: 8 · 2021: 1
- FWCI
- 1.28
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model (vor)
- Locations
- American Journal of Clinical Pathology (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Keywords
- mycobacterial detection, acid-fast bacilli, whole slide images, deep learning, digital pathology, acid-fast staining, tuberculosis diagnosis, AI-assisted review, pathologist workload, diagnostic sensitivity
- MeSH terms
- Deep Learning, Adult, Aged, Aged, 80 and over, Female, Humans, Image Interpretation, Computer-Assisted, Male, Middle Aged, Mycobacterium, Mycobacterium Infections, Pathology, Clinical
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
