Effective deep learning for oral exfoliative cytology classification

Abstract Objective: The use of sharpness aware minimization (SAM) as an optimizer that achieves high performance for convolutional neural networks (CNNs), is attracting attention in various fields of deep learning. Here, we use deep learning to perform classification diagnosis in oral exfoliative cytology and to analyze performance, using SAM as an optimization algorithm to improve classification accuracy. Methods: Oral exfoliation cytology samples were prepared at a general by oral pathologists. Whole slide images were cut into tiles. CNNs used was VGG16, and SGD and SAM were used as optimizers. Each was analyzed with and without a learning rate scheduler in 300 epochs. The performance metrics used were accuracy, precision, recall, specificity, F1 score, AUC, and statistical and effect size. Results: All optimizers performed better with the rate scheduler. In particular, the SAM effect size had high accuracy (11.2) and AUC (11.0). SAM had the best performance of all models with a learning rate scheduler. (AUC = 0.9328) SAM tended to suppress overfitting compared to SGD. Conclusions: In oral exfoliation cytology classification, CNNs using SAM rate scheduler showed the highest classification performance. These results suggest that SAM can play an important role in primary screening of the oral cytological diagnostic environment.