Deep learning for the identification of Candida spp. directly from blood culture gram stains from candidemia patients
Medical Mycology · 04.11.2025 · 63 (11)
DOI: 10.1093/mmy/myaf097 ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical Mycology, online erschienen am 17.10.2025. Verfasst von Juan Carlos Cuevas-Tello und 12 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory of Bioinformatics, Centro de Investigación en Ciencias de la Salud y Biomedicina, Universidad Autónoma de San Luis Potosí, 78210, San Luis…. Hauptthemen laut MEDLINE: Deep Learning, Candida, Candidemia, Blood Culture. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 30 Literaturangaben.
Abstract (Originalsprache)
Candidemias caused by the yeasts formerly encompassed as Candida spp. require expedited identification to decide on the antifungal treatment and reduce mortality. Traditional methods rely on subcultures for diagnosis, with turnaround times of 72–96 h, or expensive equipment. Deep learning and convolutional neural networks (CNN) have shown high accuracy for image recognition in microbiology. We compared the accuracy of six CNNs (GoogLeNet, InceptionV3, AlexNet, ResNet18, ResNet50, and DenseNet161) to identify Candida spp. at the species level, with photographs obtained mainly from clinical blood cultures showing yeast structures in the Gram stain, which were identified as Candida spp. in the subculture. Images were obtained from January 2012 to May 2024 and stored in the image databank of two third-level teaching hospitals in Mexico City. We analyzed the five most frequent species from both centers’ clinical samples and included simulated blood culture images from Candida auris (Candidozyma auris) and C. krusei (Pichia kudriavzevii) strains. After processing and segmentation, we loaded the CNNs with 531 whole photographs and 2804 patches. The CNN Densnet161, using a scan-based approach, showed higher accuracy identifying 87%, 99%, 94%, 100%, 89%, and 95% of the images containing C. albicans, C. auris, C. glabrata (Nakaseomyces glabrata), C. krusei (P. kudriavzevii), C. parapsilosis, and C. tropicalis, respectively. These results show that CNN image recognition can identify clinically relevant Candida spp. directly from positive Gram-stained smears, which may help make early decisions for antifungal treatment.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Laboratory of Bioinformatics, Centro de Investigación en Ciencias de la Salud y Biomedicina, Universidad Autónoma de San Luis Potosí, 78210, San Luis Potosí, Mexico.
- Facultad de Ingeniería, Universidad Autónoma de San Luis Potosí, 78290, San Luis Potosí, Mexico.
- Department of Infectious Diseases, Instituto Nacional de Ciencias Médicas y Nutrición Salvador Zubirán, 14080, Mexico City, Mexico.
- Clinical Microbiology Laboratory, Instituto Nacional de Rehabilitación Luis Guillermo Ibarra Ibarra,14389, Mexico City, Mexico.
- Department of Biology, Facultad de Química, Universidad Nacional Autónoma de México, 04510, Mexico City, Mexico.
- Laboratory of Infectious Diseases, Centro de Investigación en Ciencias de la Salud y Biomedicina, Universidad Autónoma de San Luis Potosí,78210, San Luis Potosí, Mexico.
ORCID-Profile: Luis Esau López-Jacome, Rafael Franco-Cendejas, Pedro Torres-González
Zitieren
APA
Cuevas-Tello, J. C., Monreal-de la Rosa, A., Quistian-Navarro, J. L., Martinez-Gamboa, A., González-Lara, M. F., López-García, N. I., Rangel-Cordero, A., López-Jacome, L. E., Cervantes-Hernandez, M. I., Franco-Cendejas, R., Muñoz-Escalante, J. C., Noyola, D. E., & Torres-González, P. (2025). Deep learning for the identification of Candida spp. directly from blood culture gram stains from candidemia patients. Medical Mycology, 63(11). https://doi.org/10.1093/mmy/myaf097
Vancouver
Cuevas-Tello JC, Monreal-de la Rosa A, Quistian-Navarro JL, Martinez-Gamboa A, González-Lara MF, López-García NI, et al. Deep learning for the identification of Candida spp. directly from blood culture gram stains from candidemia patients. Medical Mycology. 2025;63(11). doi:10.1093/mmy/myaf097
BibTeX
@article{CuevasTello2025,
author = {Cuevas-Tello, Juan Carlos and Monreal-de la Rosa, Azael and Quistian-Navarro, Juan Luis and Martinez-Gamboa, Areli and González-Lara, Maria Fernanda and López-García, Norma Irene and Rangel-Cordero, Andrea and López-Jacome, Luis Esau and Cervantes-Hernandez, Mercedes Isabel and Franco-Cendejas, Rafael and Muñoz-Escalante, Juan Carlos and Noyola, Daniel E and Torres-González, Pedro},
title = {Deep learning for the identification of Candida spp. directly from blood culture gram stains from candidemia patients},
journal = {Medical Mycology},
year = {2025},
volume = {63},
number = {11},
doi = {10.1093/mmy/myaf097}
}
EUVIMED