EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Bridging clinical microbiology and artificial intelligence: An image-based deep learning framework for automated antimicrobial susceptibility testing

Fatih Ciftci, Kadriye Yasemin Usta Ayanoğlu, Azime Erarslan

Biomedical Journal · 2026-12 · 49 (6) · 100965

DOI: 10.1016/j.bj.2026.100965 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomedical Journal, 2026-12. Verfasst von Fatih Ciftci und 2 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Engineering, Department of Biomedical Engineering, Fatih Sultan Mehmet Vakıf University, Istanbul, Turkey; Biomedical Electronic Design Ap…. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rising threat of antimicrobial resistance has underscored the urgent need for rapid, standardized, and automated antimicrobial susceptibility testing (AST) solutions. Leveraging recent advances in computer vision and deep learning, this study introduces a fully image-based diagnostic framework that integrates a YOLOv8n object detection model with a Convolutional Neural Network (CNN) to perform end-to-end bacterial identification and susceptibility classification directly from Petri dish images. The YOLOv8n model accurately localizes handwritten bacterial species labels with a mean Average Precision (mAP@0.50) exceeding 0.93, demonstrating robustness across diverse handwriting styles and imaging conditions. Complementarily, the CNN achieves a balanced accuracy of 94.7% and 100% sensitivity for susceptible cases by analyzing inhibition zone morphology without manual measurements or interpretive rules. Notably, the system achieved a 0% Very Major Error (VME) rate, ensuring no resistant isolates were misclassified as susceptible. The dual-model system generalizes effectively across experimental variations and produces high-confidence predictions, highlighting its potential to streamline AST workflows, minimize human variability, and enhance diagnostic reliability in clinical microbiology.

Schlagwörter

Stichwörter der Autor:innen

Antibiotic resistanceAntimicrobial susceptibilityDeep learningInhibition zone measurementTestingYOLOv8n

Autor:innen und Institutionen

  • Faculty of Engineering, Department of Biomedical Engineering, Fatih Sultan Mehmet Vakıf University, Istanbul, Turkey; Biomedical Electronic Design Application and Research Center (BETAM), Fatih Sultan Mehmet Vakıf Unive…
  • Department of Tropiko Software and Consultancy, Istanbul, Turkey; Faculty of Engineering, Department of Distributed Software System, Technische Universität Darmstadt, Germany.
  • Department of Bioengineering, Faculty of Chemical and Metallurgical Engineering, Yıldız Technical University, İstanbul, Turkey. Electronic address: azime@yildiz.edu.tr.

Zitieren

APA

Ciftci, F., Ayanoğlu, K. Y. U., & Erarslan, A. (2026). Bridging clinical microbiology and artificial intelligence: An image-based deep learning framework for automated antimicrobial susceptibility testing. Biomedical Journal, 49(6), 100965. https://doi.org/10.1016/j.bj.2026.100965

Vancouver

Ciftci F, Ayanoğlu KYU, Erarslan A. Bridging clinical microbiology and artificial intelligence: An image-based deep learning framework for automated antimicrobial susceptibility testing. Biomedical Journal. 2026;49(6):100965. doi:10.1016/j.bj.2026.100965

BibTeX
@article{Ciftci2026,
  author = {Ciftci, Fatih and Ayanoğlu, Kadriye Yasemin Usta and Erarslan, Azime},
  title = {Bridging clinical microbiology and artificial intelligence: An image-based deep learning framework for automated antimicrobial susceptibility testing},
  journal = {Biomedical Journal},
  year = {2026},
  volume = {49},
  number = {6},
  pages = {100965},
  doi = {10.1016/j.bj.2026.100965}
}
Kostenlos starten →