EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Use of a convolutional neural network for direct detection of acid-fast bacilli from clinical specimens

Paul English iD, Muir J Morrison iD, Blaine Mathison iD, Elizabeth Enrico, Ryan Shean iD, Brendan O'Fallon, Deven Rupp, Katie Knight, Alexandra Rangel, Jeffrey Gilivary, Amanda Vance, Haleina Hatch und 3 weitere

Microbiology Spectrum · 2025

DOI: 10.1128/spectrum.00602-25 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Microbiology Spectrum, 2025. Verfasst von Paul English und 14 weiteren Autor:innen. Beteiligte Einrichtung: ARUP Institute for Research and Innovation in Diagnostic and Precision Medicine, ARUP Laboratories, Salt Lake City, Utah, USA. Hauptthemen laut MEDLINE: Neural Networks, Computer, Mycobacterium tuberculosis, Tuberculosis. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Mycobacteria, including Mycobacterium tuberculosis (MTB) and non-tuberculosis mycobacteria (NTM), are important causes of infectious disease and cause significant mortality and morbidity globally. Fast detection is extremely important to reduce transmission and mortality associated with these infectious agents. Manual smear microscopy is a cost-effective tool for diagnosing and monitoring of these organisms; however, it is labor-intensive and requires highly-trained personnel. We present the development of an artificial intelligence computer vision process using a deep convolutional neural network to detect acid-fast bacilli (AFB) from Kinyoun acid-fast stained slides. We collected 231 clinical specimens between August 2023 and June 2024. Following acid-fast staining, whole slide images (WSI) were digitized, and AFB organisms were manually annotated. A machine learning computer vision model was trained using 11,411 annotated organisms across 109 WSI. Model predictions were correlated with final culture-confirmed results. The final model estimated AFB density per 1000 x microscope field of view (FOV). Using a density threshold of ≥10 −2 AFB/1000xFOV (corresponding to 1 + per Clinical and Laboratory Standards Institute (CLSI) guideline M48) to predict positive culture results, the model correctly classified 68% of validation slides, with a sensitivity of 79% and specificity of 63%. Manual AO compared to final culture read showed sensitivity of 76% and specificity of 96%. Although performance of our model was not sufficient to be clinically implemented in our laboratory, our study provides a framework for AI-based AFB detection and a publicly available data set to support future advancements in automated detection of AFB. IMPORTANCE We present the development of an artificial intelligence model to detect acid-fast bacilli (AFB) directly from stained clinical smears. While the model’s current performance requires further improvement to be clinically useful in our lab, we detail our approach and share our expertly annotated data set to support future advancements in this area. By building on our work, researchers can develop better algorithms to improve the diagnosis of AFB, reducing the burden on laboratory staff and improving diagnostic speed and accuracy of these medically important organisms.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerMycobacterium tuberculosisTuberculosisHumansMachine LearningImage Processing, Computer-AssistedMicroscopySensitivity and SpecificitySputumConvolutional Neural Networks

Stichwörter der Autor:innen

Mycobacteriumacid-fast bacilliartificial intelligencedigital pathologymicrobiologymycobacteriaobject detectiontuberculosis

Autor:innen und Institutionen

  • ARUP Institute for Research and Innovation in Diagnostic and Precision Medicine, ARUP Laboratories, Salt Lake City, Utah, USA.
  • ARUP Technical Operations Infectious Diseases, ARUP Laboratories, Salt Lake City, Utah, USA.
  • Department of Pathology, University of Utah, Salt Lake City, Utah, USA.

ORCID-Profile: Paul English, Muir J Morrison, Blaine Mathison, Ryan Shean, Salika M Shakir

Zitieren

APA

English, P., Morrison, M. J., Mathison, B., Enrico, E., Shean, R., O'Fallon, B., Rupp, D., Knight, K., Rangel, A., Gilivary, J., Vance, A., Hatch, H., Lin, L., Ng, D. P., & Shakir, S. M. (2025). Use of a convolutional neural network for direct detection of acid-fast bacilli from clinical specimens. Microbiology Spectrum. https://doi.org/10.1128/spectrum.00602-25

Vancouver

English P, Morrison MJ, Mathison B, Enrico E, Shean R, O'Fallon B, et al. Use of a convolutional neural network for direct detection of acid-fast bacilli from clinical specimens. Microbiology Spectrum. 2025. doi:10.1128/spectrum.00602-25

BibTeX
@article{English2025,
  author = {English, Paul and Morrison, Muir J and Mathison, Blaine and Enrico, Elizabeth and Shean, Ryan and O'Fallon, Brendan and Rupp, Deven and Knight, Katie and Rangel, Alexandra and Gilivary, Jeffrey and Vance, Amanda and Hatch, Haleina and Lin, Leo and Ng, David P and Shakir, Salika M},
  title = {Use of a convolutional neural network for direct detection of acid-fast bacilli from clinical specimens},
  journal = {Microbiology Spectrum},
  year = {2025},
  doi = {10.1128/spectrum.00602-25}
}
Kostenlos starten →