Deep learning for caries lesion detection in near-infrared light transillumination images: A pilot study. (January 2020)

• Record Type: Journal Article
• Authors: Schwendicke, Falk; Elhennawy, Karim; Paris, Sebastian; Friebertshäuser, Philipp; Krois, Joachim
• Is Part Of: Journal of dentistry. Volume 92(2020:Jan.)
• Publication Date: 2020-01
• Subjects: Artificial intelligence -- Caries -- Diagnostics -- Digital imaging/radiology -- Mathematical modeling; Dentistry -- Periodicals; Dentistry -- Periodicals; Dentisterie -- Périodiques; Electronic journals; 617.6005
• DOI: 10.1016/j.jdent.2019.103260
• Languages: English
• ISSNs: 0300-5712

Abstract

Abstract: Objectives: In this pilot study, we applied deep convolutional neural networks (CNNs) to detect caries lesions in Near-Infrared-Light Transillumination (NILT) images. Methods: 226 extracted posterior permanent human teeth (113 premolars, 113 molars) were allocated to groups of 2 + 2 teeth, and mounted in a pilot-tested diagnostic model in a dummy head. NILT images of single-tooth-segments were generated using DIAGNOcam (KaVo, Biberach). For each segment (on average 435 × 407 × 3 pixels), occlusal and/or proximal caries lesions were annotated by two experienced dentists using an in-house developed digital annotation tool. The pixel-based annotations were translated into binary class levels. We trained two state-of-the-art CNNs (Resnet18, Resnext50) and validated them via 10-fold cross validation. During the training process, we applied data augmentation (random resizing, rotations and flipping) and one-cycle-learning rate policy, setting the minimum and maximum learning rates to 10 −5 and 10 -3, respectively. Metrics for model performance were the area-under-the-receiver-operating-characteristics-curve (AUC), sensitivity, specificity, and positive/negative predictive values (PPV/NPV). Feature visualization was additionally applied to assess if the CNNs built on features dentists would also use. Results: The tooth-level prevalence of caries lesions was 41%. The two models performed similar on predicting caries on tooth segments of NILT images. The marginal better model with respect to AUC was Resnext50, where we retrained the last 9 network layers, using the Adam optimizer, a learning rate of 0.5 × 10 −4, and a batch size of 10. The mean (95% CI) AUC was 0.74 (0.66-0.82). Sensitivity and specificity were 0.59 (0.47-0.70) and 0.76 (0.68-0.84) respectively. The resulting PPV was 0.63 (0.51-0.74), the NPV 0.73 (0.65-0.80). Visual inspection of model predictions found the model to be sensitive to areas affected by caries lesions. Conclusions: A moderately deep CNN trained on a limited amount of NILT image data showed satisfying discriminatory ability to detect caries lesions. Clinical significance: CNNs may be useful to assist NILT-based caries detection. This could be especially relevant in non-conventional dental settings, like schools, care homes or rural outpost centers.