A novel framework for the automated characterization of Gram-stained blood culture slides using a large-scale vision transformer
Journal of Clinical Microbiology · 12.03.2025 · 63 (3)
DOI: 10.1128/jcm.01514-24 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Clinical Microbiology, erschienen am 12.03.2025. Verfasst von Jack McMahon und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Dartmouth College, Hanover, New Hampshire, USA. Hauptthemen laut MEDLINE: Gentian Violet, Phenazines, Blood Culture, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NLM NIH HHS, HHS | NIH | U.S. National Library of Medicine (NLM).
Abstract (Originalsprache)
This study introduces a new framework for the artificial intelligence-based characterization of Gram-stained whole-slide images (WSIs). As a test for the diagnosis of bloodstream infections, Gram stains provide critical early data to inform patient treatment in conjunction with data from rapid molecular tests. In this work, we developed a novel transformer-based model for Gram-stained WSI classification, which is more scalable to large data sets than previous convolutional neural network-based methods as it does not require patch-level manual annotations. We also introduce a large Gram stain data set from Dartmouth-Hitchcock Medical Center (Lebanon, New Hampshire, USA) to evaluate our model, exploring the classification of five major categories of Gram-stained WSIs: gram-positive cocci in clusters, gram-positive cocci in pairs/chains, gram-positive rods, gram-negative rods, and slides with no bacteria. Our model achieves a classification accuracy of 0.858 (95% CI: 0.805, 0.905) and an area under the receiver operating characteristic curve (AUC) of 0.952 (95% CI: 0.922, 0.976) using fivefold nested cross-validation on our 475-slide data set, demonstrating the potential of large-scale transformer models for Gram stain classification. Results were measured against the final clinical laboratory Gram stain report after growth of organism in culture. We further demonstrate the generalizability of our trained model by applying it without additional fine-tuning on a second 27-slide external data set from Stanford Health (Palo Alto, California, USA) where it achieves a binary classification accuracy of 0.926 (95% CI: 0.885, 0.960) and an AUC of 0.8651 (95% CI: 0.6337, 0.9917) while distinguishing gram-positive from gram-negative bacteria. IMPORTANCE This study introduces a scalable transformer-based deep learning model for automating Gram-stained whole-slide image classification. It surpasses previous methods by eliminating the need for manual annotations and demonstrates high accuracy and generalizability across multiple data sets, enhancing the speed and reliability of Gram stain analysis.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Computer Science, Dartmouth College, Hanover, New Hampshire, USA.
- Department of Biomedical Data Science, Geisel School of Medicine at Dartmouth, Hanover, New Hampshire, USA.
- Department of Pathology and Laboratory Medicine, Dartmouth-Hitchcock Medical Center, Lebanon, New Hampshire, USA.
- Department of Pathology, Stanford University School of Medicine, Stanford, California, USA.
- Department of Medicine, Division of Infectious Diseases and Geographic Medicine, Stanford University School of Medicine, Stanford, California, USA.
- Clinical Microbiology Laboratory, Stanford Health Care, Palo Alto, California, USA.
ORCID-Profile: Niaz Banaei, Isabella W Martin, Saeed Hassanpour
Förderung
- NLM NIH HHS
- HHS | NIH | U.S. National Library of Medicine (NLM)
Zitieren
APA
McMahon, J., Tomita, N., Tatishev, E. S., Workman, A. A., Costales, C. R., Banaei, N., Martin, I. W., & Hassanpour, S. (2025). A novel framework for the automated characterization of Gram-stained blood culture slides using a large-scale vision transformer. Journal of Clinical Microbiology, 63(3). https://doi.org/10.1128/jcm.01514-24
Vancouver
McMahon J, Tomita N, Tatishev ES, Workman AA, Costales CR, Banaei N, et al. A novel framework for the automated characterization of Gram-stained blood culture slides using a large-scale vision transformer. Journal of Clinical Microbiology. 2025;63(3). doi:10.1128/jcm.01514-24
BibTeX
@article{McMahon2025,
author = {McMahon, Jack and Tomita, Naofumi and Tatishev, Elizabeth S and Workman, Adrienne A and Costales, Cristina R and Banaei, Niaz and Martin, Isabella W and Hassanpour, Saeed},
title = {A novel framework for the automated characterization of Gram-stained blood culture slides using a large-scale vision transformer},
journal = {Journal of Clinical Microbiology},
year = {2025},
volume = {63},
number = {3},
doi = {10.1128/jcm.01514-24}
}
EUVIMED