Deep Learning-Based Rapid Identification of Escherichia coli and Klebsiella pneumoniae from Chromogenic Agar Urine Cultures Using YOLOv12

Abdurrahman Sarmis,1 Serpil Ustebay,2 Muhammed Ali Mutlu,3 Furkan Adem Canbaz,4 Gulsum Kubra Kaya5 1Department of Microbiology Laboratory, Goztepe Prof. Dr Suleyman Yalcin City Hospital, Istanbul, Türkiye; 2Department of Computer Engineering, Istanbul University-Cerrahpaşa, Istanbul, Türkiye; 3Department of Microbiology Laboratory, Fatih Sultan Mehmet Training and Research Hospital, Istanbul, Türkiye; 4Department of Pediatric Surgery, Sancaktape Sehit Prof Dr Ilhan Varank Training and Research Hospital, Istanbul, Türkiye; 5Faculty of Engineering and Applied Sciences, Cranfield University, Bedford, UKCorrespondence: Abdurrahman Sarmis, Department of Microbiology Laboratory, Goztepe Prof. Dr Suleyman Yalcin City Hospital, Istanbul, Türkiye, Email [email protected]: Urinary tract infections (UTIs) are among the most common bacterial infections worldwide, with Escherichia coli and Klebsiella pneumoniae being the predominant pathogens. Diagnostic delays necessitate the use of broad-spectrum antibiotics, which fuels antimicrobial resistance. This study aimed to develop and validate an artificial intelligence (AI) model for the rapid identification of E. coli and K. pneumoniae colonies from urine culture images.Patients and Methods: We analyzed 1547 chromogenic agar urine culture images (850 E. coli, 697 K. pneumoniae) obtained using an automated Copan WASP system. A YOLOv12 deep learning model was trained on expert-labeled colonies. The reference standard comprised MALDI-TOF Mass Spectrometry (MS) for K. pneumoniae and a characteristic chromogenic morphology for E. coli. This phenotypic method is standard in clinical practice, with validation studies for the specific agar used reporting a sensitivity of 98.1– 99.0% and a specificity of 99.1% for E. coli identification. Performance was assessed on an internal test set and via external validation using 91 independent images.Results: The model achieved 99% accuracy (precision, recall, F1-score: 0.99) on internal testing. External validation yielded 100% accuracy, with the critical note that species labels in this independent set were inferred from colony colour. Rare errors involved atypical (eg, gold-pigmented) E. coli colonies. YOLOv12 outperformed five benchmark deep learning models.Conclusion: This AI model enables rapid (sub-second), accurate phenotypic classification of the most common UTI pathogens directly from routine culture plates. Integration into automated systems could reduce the diagnostic timeline by approximately 18 hours, facilitating earlier targeted therapy and supporting antimicrobial stewardship. A key consideration for implementation is the model’s basis in phenotypic identification, which aligns with standard laboratory workflow but requires awareness of rare chromogenic variants. The reliance on chromogenic morphology for E. coli ground truth has been a key limitation of the study.Keywords: urinary tract infection, Escherichia coli, Klebsiella pneumoniae, artificial intelligence, risk management, antibiotic stewardship