Artificial intelligence accurately detects white spot lesions including fluorosis: Study

Artificial intelligence (AI) encompasses a broad spectrum of emerging technologies that continue to influence daily life. The evolution of AI makes the analysis of big data possible, which provides reliable information and improves the decision-making process.

Haitham Askar and associates from the Department of Oral Diagnostics, Digital Health and Health Services Research, Charité - Universitätsmedizin Berlin, Germany conducted this pilot study to apply deep learning to detect white spot lesions in dental photographs.

Using 434 photographic images of 51 patients, a dataset of 2781 cropped tooth segments was generated. Pixelwise annotations of sound enamel as well as fluorotic, carious or other types of hypomineralized lesions were generated by experts and assessed by an independent second reviewer.

The union of the reviewed annotations were used to segment the hard tissues (region-of-interest, ROI) of each image. SqueezeNet was employed for modelling. The authors trained models to detect (1) any white spot lesions, (2) fluorotic lesions and (3) other-than-fluorotic lesions. Modeling was performed on both the cropped and the ROI images and using ten-times repeated five-fold cross-validation. Feature visualization was applied to visualize salient areas.

The findings showed -

a. Lesion prevalence was 37 %; the majority of lesions (24 %) were fluorotic.

b. None of the metrics differed significantly between the models trained on cropped and ROI imagery (p > 0.05/t-test).

c. Mean accuracies ranged between 0.81−0.84, without significant differences between models trained to detect any, fluorotic or other-than-fluorotic lesions (p > 0.05).

d. Specificities were 0.85−0.86; sensitivities were lower (0.58−0.66).

e. Models to detect any lesions showed positive/negative predictive values (PPV/NPV) between 0.77−0.80, those to detect fluorotic lesions 0.67 (PPV) to 0.86 (NPV), and those to detect other-than-fluorotic lesions 0.46 (PPV) to 0.93 (NPV).

f. Light reflections were the main reason for false positive detections.

Hence, the authors concluded that "Deep learning showed satisfying accuracy to detect white spot lesions, particularly fluorosis. Some models showed limited stability given the small sample available."