Development and Clinical Application of a Deep Learning-Based Endometrial Cancer Cytology Supporting Model

BackgroundThe global rise in endometrial cancer, including in Japan, and the shortage of pathologists and cytotechnologists has increased the diagnostic burden, emphasizing the need for AI-based diagnostic support model using deep learning. This study aims to advance an existing AI-supported endometrial cytology model for clinical application. MethodsWe compared two datasets--one annotated for both benign and malignant clusters, and one for malignant only--using YOLOv5x and YOLOv7 models evaluated by mAP. We also assessed the correlation between AI diagnostic accuracy and the level of difficulty perceived by human diagnosticians using the Two One-Sided Tests (TOST) procedure. Additionally, we applied Grad-CAM to visualize and enhance the interpretability of the AI models decision-making process. ResultsThe YOLOv5x model with both benign and malignant annotations achieved the highest malignant mAP at 0.798 compared to Yolov7. The TOST analysis showed no significant difference in perceived diagnostic difficulty between cases that were correctly and incorrectly diagnosed by the AI model, indicating consistent AI accuracy regardless of case difficulty. Grad-CAM visualizations clarified the AI models decision-making basis; in some cases, the model appeared to focus on regions different from those typically attended to by human diagnosticians. ConclusionThe AI support model showed high and consistent accuracy in endometrial cytology, regardless of diagnostic difficulty as perceived by human diagnosticians. Grad-CAM visualizations revealed diagnostic patterns, with AI occasionally focusing on regions different from those emphasized by human diagnosticians. This study advances the real-time, microscope-integrated AI system toward clinical application.