Masked latent transformer with random masking ratio to advance the diagnosis of dental fluorosis

Abstract

Dental fluorosis is a chronic condition caused by long-term overconsumption of fluoride, which leads to changes in the appearance of tooth enamel. Diagnosing its severity can be challenging for dental professionals, and limited research on deep learning applications in this field. Therefore, we propose a novel deep learning model, masked latent transformer with random masking ratio (MLTrMR), to advance the diagnosis of dental fluorosis. MLTrMR enhances contextual learning by using a masked latent modeling scheme based on Vision Transformer. It extracts latent tokens from the original image with a latent embedder, processes unmasked tokens with a latent transformer (LT) block, and predicts masked tokens. To improve model performance, we incorporate an auxiliary loss function. MLTrMR achieves state-of-the-art results, with 80.19% accuracy, 75.79% F1 score, and 81.28% quadratic weighted kappa on the first open-source dental fluorosis image dataset (DFID) we constructed. The dataset and code are available at https://github.com/uxhao-o/MLTrMR.