Peer-Reviewed Publication
J Clin Microbiol2025;63(3):e0151424.March 12, 2025Journal Article
A novel framework for the automated characterization of Gram-stained blood culture slides using a large-scale vision transformer.
Jack McMahon1, Naofumi Tomita2, Elizabeth S Tatishev1, Adrienne A Workman3, Cristina R Costales4, Niaz Banaei4,5,6, Isabella W Martin3, Saeed Hassanpour1,2,7
1Department of Computer Science, Dartmouth College, Hanover, New Hampshire, USA.
2Department of Biomedical Data Science, Geisel School of Medicine at Dartmouth, Hanover, New Hampshire, USA.
3Department of Pathology and Laboratory Medicine, Dartmouth-Hitchcock Medical Center, Lebanon, New Hampshire, USA.
4Department of Pathology, Stanford University School of Medicine, Stanford, California, USA.
5Department of Medicine, Division of Infectious Diseases and Geographic Medicine, Stanford University School of Medicine, Stanford, California, USA.
6Clinical Microbiology Laboratory, Stanford Health Care, Palo Alto, California, USA.
7Department of Epidemiology, Geisel School of Medicine at Dartmouth, Hanover, New Hampshire, USA.
Abstract
UNLABELLED: 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…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans