Optimization methods for deep neural networks classifying OCT images to detect dental caries

摘要

Dental caries are common chronic infectious oral diseases affecting most teenagers and adults worldwide. Opticalcoherence tomography (OCT) has been studied extensively for the detection of early carious lesions. Deep learningtechniques are a rapidly emerging new area of biomedical research and have yielded impressive results in diagnosis andprediction in the field of oral radiology. Deep learning models particularly deep convolutional neural networks (CNN)can be employed along with OCT imaging system to more accurately identify early dental caries. In this work, afterOCT data acquisition, data augmentation was performed to obtain a large amount of training data in order to effectivelylearn, where collection of such training data is often expensive and laborious. For the backpropagation process, sevenoptimization methods, namely Adadelta, AdaGrad, Adam, AdaMax, Nadam, RMSProp, and Stochastic Gradient Descent(SGD) were utilized to improve the accuracy of a CNN classifier for diagnosing dental caries. In this study, 75% of thedata were utilized for training and 25% for testing. The diagnostic accuracy, sensitivity, specificity, positive predictivevalue, negative predictive value, and receiver operating characteristic (ROC) curve were calculated for detection anddiagnostic performance of the deep CNN algorithm. This study highlighted the performance of various optimizationmethods for deep CNN models with OCT images to detect dental caries.