Evaluating Deep Learning Models for Object Detection in Kirby-Bauer Test Result Images

Background The Kirby-Bauer disk diffusion method is a cost-effective and widely used technique for determining antimicrobial susceptibility, suitable for diverse laboratory settings. It involves placing antibiotic disks on a Mueller-Hinton agar plate inoculated with standardized bacteria, leading to inhibition zones after incubation. These zones are manually measured and compared to the Clinical and Laboratory Standards Institute (CLSI) criteria to classify bacteria. However, manual interpretation can introduce variability due to human error, operator skill, and environmental factors, especially in resource-limited settings. Advances in AI and deep learning now enable automation, reducing errors and enhancing consistency in antimicrobial resistance management. Objective This study evaluated two deep learning models—Faster R-CNN (ResNet-50 and ResNet-101 backbones) and RetinaNet (ResNet-50 backbone)—for detecting antibiotic disks, inhibition zones, and antibiotic abbreviations on Kirby-Bauer test images. The aim was to automate interpretation and improve clinical decision-making. Methods A dataset of 291 Kirby-Bauer test images was annotated for agar plates, antibiotic disks, and inhibition zones. Images were split into training (80%) and evaluation (20%) sets and processed using Azure Machine Learning. Model performance was assessed using mean Average Precision (mAP), precision, recall, and inference time. Automated zone measurements were compared with manual readings using CLSI standards. Results Faster R-CNN with ResNet-101 achieved the highest mAP (0.962) and recall (0.972), excelling in detecting small zones. ResNet-50 offered balanced performance with lower computational demands. RetinaNet, though efficient, showed recall variability at higher thresholds. Automated measurements correlated strongly with manual readings, achieving 99% accuracy for susceptibility classification. Conclusion Faster R-CNN with ResNet-101 excels in accuracy-critical applications, while RetinaNet offers efficient, real-time alternatives. These findings demonstrate the potential of AI-driven automation to improve antibiotic susceptibility testing in clinical microbiology.