采用随机掩码比例的掩码潜在 Transformer 以推进氟斑牙诊断
Masked Latent Transformer with the Random Masking Ratio to Advance the Diagnosis of Dental Fluorosis
AI总结：
针对氟斑牙诊断的研究空白，构建首个开源数据集DFID，并提出深度学习模型MLTrMR，通过引入掩码潜在建模方案与辅助损失函数增强病变特征学习，在DFID上达到SOTA。
摘要：
氟斑牙是由长期过量摄入氟化物引起的慢性疾病，会导致牙釉质外观发生改变。它是早期无创诊断地方性氟中毒的重要依据。然而，即使是牙科专业人员也可能无法根据牙齿图像准确区分氟斑牙及其严重程度。目前，在应用深度学习诊断氟斑牙方面仍存在研究空白。因此，我们构建了首个开源氟斑牙图像数据集（DFID），为该领域的深度学习研究奠定基础。为推进氟斑牙诊断，我们提出了一种开创性的深度学习模型，称为具有随机掩码比例的掩码潜在 Transformer（MLTrMR）。MLTrMR 引入了基于 Vision Transformer 的掩码潜在建模方案，以增强氟斑牙病变特征的上下文学习。MLTrMR 由潜在嵌入器、编码器和解码器组成，采用潜在嵌入器从原始图像中提取潜在 token，而由潜在 Transformer（LT）块组成的编码器和解码器分别用于处理未掩码 token 和预测掩码 token。为缓解 Vision Transformer 缺乏归纳偏置可能导致性能下降的问题，LT 块引入潜在 token 以增强对潜在病变特征的学习能力。此外，我们设计了辅助损失函数来约束模型参数更新的方向。MLTrMR 在 DFID 上实现了 80.19% 的准确率、75.79% 的 F1 和 81.28% 的二次加权 kappa，使其达到 SOTA。
英文摘要：
Dental fluorosis is a chronic disease caused by long-term overconsumption of fluoride, which leads to changes in the appearance of tooth enamel. It is an important basis for early non-invasive diagnosis of endemic fluorosis. However, even dental professionals may not be able to accurately distinguish dental fluorosis and its severity based on tooth images. Currently, there is still a gap in research on applying deep learning to diagnosing dental fluorosis. Therefore, we construct the first open-source dental fluorosis image dataset (DFID), laying the foundation for deep learning research in this field. To advance the diagnosis of dental fluorosis, we propose a pioneering deep learning model called masked latent transformer with the random masking ratio (MLTrMR). MLTrMR introduces a mask latent modeling scheme based on Vision Transformer to enhance contextual learning of dental fluorosis lesion characteristics. Consisting of a latent embedder, encoder, and decoder, MLTrMR employs the latent embedder to extract latent tokens from the original image, whereas the encoder and decoder comprising the latent transformer (LT) block are used to process unmasked tokens and predict masked tokens, respectively. To mitigate the lack of inductive bias in Vision Transformer, which may result in performance degradation, the LT block introduces latent tokens to enhance the learning capacity of latent lesion features. Furthermore, we design an auxiliary loss function to constrain the parameter update direction of the model. MLTrMR achieves 80.19% accuracy, 75.79% F1, and 81.28% quadratic weighted kappa on DFID, making it state-of-the-art (SOTA).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
