Development and evaluation of deep learning for screening dental caries from oral photographs

Abstract

Objectives To develop and evaluate the performance of a deep learning system based on convolutional neural network (ConvNet) to detect dental caries from oral photographs. Methods 3,932 oral photographs obtained from 625 volunteers with consumer cameras were included for the development and evaluation of the model. A deep ConvNet was developed by adapting from Single Shot MultiBox Detector. The hard negative mining algorithm was applied to automatically train the model. The model was evaluated for: (i) classification accuracy for telling the existence of dental caries from a photograph and (ii) localization accuracy for locations of predicted dental caries. Results The system exhibited a classification area under the curve (AUC) of 85.65% (95% confidence interval: 82.48% to 88.71%). The model also achieved an image‐wise sensitivity of 81.90%, and a box‐wise sensitivity of 64.60% at a high‐sensitivity operating point. The hard negative mining algorithm significantly boosted both classification (p < .001) and localization (p < .001) performance of the model by reducing false‐positive predictions. Conclusions The deep learning model is promising to detect dental caries on oral photographs captured with consumer cameras. It can be useful for enabling the preliminary and cost‐effective screening of dental caries among large populations.

Deep learning convolutional neural network algorithms for the early detection and diagnosis of dental caries on periapical radiographs: A systematic review

“…Another promising result of DNN-based caries diagnosis was reported by Zhang et al 14 in 2020. A relatively large dataset of 3,932 photos from patients 14 to 60 years old was examined with ConvNet.…”

“…Zhang et al 14 in 2020 developed a ConvNet model for dental caries images taken from phone and manual cameras. In total, 2,507 images were used for the training dataset, and 1,125 others were used for the testing dataset.…”

Machine learning in dental, oral and craniofacial imaging: a review of recent progress

“…Zhang X et al developed ConvNet, which is based on CNN, to identify dental caries from oral images captured with consumer cameras. The result showed that the image-wise sensitivity is good ( Zhang et al, 2020 ). At present, more studies have been conducted on the possibility and accuracy of AI-assisted detection of dental caries, but there are few studies on AI-assisted prediction of the occurrence of dental caries.…”

Automatized Detection and Categorization of Fissure Sealants from Intraoral Digital Photographs Using Artificial Intelligence

“…By contrast, there have been few attempts to apply AI technology to assess clinical images, which can be interpreted as a machine-readable equivalent for visual inspection. This study is the first report of automatic detection and categorization of dental caries [ 10 , 11 , 12 , 13 ] or dental plaque [ 14 ] from clinical photographs. When considering the broad spectrum of pathological findings on dental hard tissue, e.g., caries, erosion or developmental disorders, as well as dental interventions, e.g., sealants, dental restorations or prosthodontic measures, it is evident that CNNs need to be trained separately for each of the aforementioned categories.…”