Dental caries classification using depthwise separable convolutional neural network for teledentistry system

Abstract

Caries may be halted or reversed in their progression by early detection, better hygiene habits, and coadministered drugs. The major clinical procedures for identifying dental caries are visual-tactile examination and dental radiography. However, due to their location, approximate caries exceedingly difficult to detect and affect the clinical assessment. Incorrect interpretations may also hinder the diagnostic procedure. Computational approaches and technology can be used to help dentists assess caries. Teledentistry has the ability to improve dental health care by providing access to dental care services from a remote location. Teledentistry helps identifying various stages of caries lesions using neural network and devices connected to the internet. This research develops an image classification for teledentistry systems using depthwise separable convolutional neural network. The trainable parameters reduction of depthwise separable convolution (DSC) successfully reduces the computational cost of conventional convolutional neural networks (CNN). As a result, the DSC model is reduced by 91.49% when compared to the traditional CNN model. Several DSC models improve conventional CNN accuracies in the training, validation, evaluation, and testing stages.

Multilabel image analysis on Polyethylene Terephthalate bottle images using PETNet Convolution Architecture

“…While for other classes, the model detects no errors or damage to other classes. The computational time performance of each model used for training is calculated in minutes and for testing in seconds, as can be seen in Figure 8 [28,29,30,31]. The computational time performance of each model used for training is calculated in minutes and for testing in seconds, as can be seen in Figure 8.…”

Touchless palm print recognition system design using Gray Level Co-occurrence Matrix feature with K-Nearest Neighbor classification in MATLAB

“…Referring to the background, this research designs a biometric system model for identity verification through the palm of the hand. The designed system uses K-NN classification [33,34,35,36] and GLCM texture features for feature extraction and MATLAB. Image matching based on the human palm matches the test image taken through the smartphone's IP camera directly with the training image in the dataset.…”

A simplified dental caries segmentation using Half U-Net for a teledentistry system

“…Caries can be caused by improperly consuming foods and drinks containing fructose, sucrose, and glucose, which increase the onset of dental caries. Caries result from a never-ending cycle of demineralization and remineralization [2]. Caries can also be found in black and yellow.…”