EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Dual-input deep learning system for microbial identification from blood agar plates

Takao Naito, Satomi Takei iD, Shigeki Misawa, Miyuki Kuribara, Yoko Tabe iD

PLOS One · 27.07.2026 · 21 (7) · e0353761

DOI: 10.1371/journal.pone.0353761 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 27.07.2026. Verfasst von Takao Naito und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Clinical Microbiology Analysis Development Research, Juntendo University Graduate School of Medicine, Tokyo, Japan. Hauptthemen laut MEDLINE: Deep Learning, Image Processing, Computer-Assisted, Bacteria. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Society for the Promotion of Science, Shimadzu, Kurozumi Medical Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

The morphological classification of microbial cultures and colonies requires specialized knowledge and experience; therefore, automation in this field remains limited. This study examines the feasibility of automating the identification of pathogenic microbial species from colony images of cultured microorganisms.

Methods

Two distinct image datasets were constructed for 10 clinically relevant species: a colony image dataset, consisting of individual colony images cropped, and a tile image dataset, generated by dividing entire images of the culture plate into tiles. Separate ResNet-50–based models were trained in each dataset, and their outputs were integrated to evaluate the classification performance. Training was conducted using 10,048 colony images and 23,003 tile images collected from 418 strains, and performance was assessed with five-fold cross-validation (K = 5).

Results

The colony image model achieved a sensitivity of 0.934 and a specificity of 0.993, while the tile image model achieved a sensitivity of 0.918 and a specificity of 0.991. Integration of the two models into an ensemble model further improved performance, yielding a sensitivity of 0.955 and a specificity of 0.995 when tested on 76 independent strains.

Conclusion

The ensemble model approach provides high accuracy and robustness, suggesting its potential technical contributions to microbial identification in clinical microbiology laboratories.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningImage Processing, Computer-AssistedBacteriaAgarConvolutional Neural NetworksHumans

Substanzen

Agar

Autor:innen und Institutionen

  • Department of Clinical Microbiology Analysis Development Research, Juntendo University Graduate School of Medicine, Tokyo, Japan.
  • Department of Clinical Laboratory Medicine, Juntendo University Graduate School of Medicine, Tokyo, Japan.
  • Department of Clinical Laboratory Technology, Faculty of Medical Science, Juntendo University, Chiba, Japan.

ORCID-Profile: Satomi Takei, Yoko Tabe

Förderung

  • Japan Society for the Promotion of Science
  • Shimadzu
  • Kurozumi Medical Foundation
  • Morinomiyako Medical Research Foundation
  • Charitable Trust Laboratory Medical Research Promotion Fund

Zitieren

APA

Naito, T., Takei, S., Misawa, S., Kuribara, M., & Tabe, Y. (2026). Dual-input deep learning system for microbial identification from blood agar plates. PLOS One, 21(7), e0353761. https://doi.org/10.1371/journal.pone.0353761

Vancouver

Naito T, Takei S, Misawa S, Kuribara M, Tabe Y. Dual-input deep learning system for microbial identification from blood agar plates. PLOS One. 2026;21(7):e0353761. doi:10.1371/journal.pone.0353761

BibTeX
@article{Naito2026,
  author = {Naito, Takao and Takei, Satomi and Misawa, Shigeki and Kuribara, Miyuki and Tabe, Yoko},
  title = {Dual-input deep learning system for microbial identification from blood agar plates},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {7},
  pages = {e0353761},
  doi = {10.1371/journal.pone.0353761}
}
Kostenlos starten →