arXiv 2604.237182026-04-26cs.CV

龋齿DETR：基于牙齿结构的先验和病变感知动态损失细化的DETR基于龋齿检测

Caries DETR: Tooth Structure-aware Prior and Lesion-aware Dynamic Loss Refinement for DETR Based Caries Detection

College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机科学与软件工程学院）；School of Artificial Intelligence, Shenzhen University（深圳大学人工智能学院）；Department of Stomatology, Shenzhen University General Hospital（深圳大学附属医院口腔科）

Xuefen Liu, Xinquan Yang, Mianjie Zheng, Kun Tang, Xuguang Li, Xiaoqi Guo, Linlin Shen, He Meng

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出Caries-DETR，通过牙齿结构感知查询初始化和病变感知动态损失细化，提升内窥镜图像中龋齿检测的性能，实验表明其在AlphaDent和DentalAI数据集上表现优异。

摘要：

作为内窥镜影像中微妙、低对比度的病变，现有深度学习模型在早期龋齿检测中面临重大挑战。尽管最近的基于Transformer的检测器在自然图像中表现出色，但它们往往无法捕捉到对牙科龋齿检测至关重要的领域特定解剖先验。本文提出Caries-DETR，一种专门用于内窥镜图像中龋齿检测的Transformer框架。设计了牙齿结构感知查询初始化（TSQI），利用大规模内窥镜照片预训练和结构感知分支（SPB）整合高频结构先验，引导模型聚焦于解剖学上重要的病变区域。此外，设计了病变感知动态损失细化（LDLR），通过基于病变大小、解剖相关性和预测质量的自适应损失再加权实现质量驱动的硬矿化，优化对细微病变的检测。在两个公开数据集（即AlphaDent和DentalAI）上的广泛实验表明，Caries-DETR在现有方法上实现了最先进的性能，并表现出良好的泛化能力和鲁棒性。代码和数据见https://github.com/XuefenLiu-SZU/Caries-DETR。

英文摘要：

As dental caries appear as subtle, low-contrast lesions in intraoral imaging, existing deep learning models face significant challenges in the early detection of caries. While recent Transformer-based detectors have shown promising results in natural images, they often fail to capture the domain-specific anatomical priors crucial for dental caries detection. In this paper, we propose Caries-DETR, a specialized Transformer framework for caries detection in intraoral images. A Tooth Structure-aware Query Initialization (TSQI) is designed, leveraging large-scale intraoral photograph pre-training and a structure perception branch (SPB) to integrate high-frequency structural priors, guiding the model to focus on anatomically significant lesion areas. Furthermore, we design a Lesion-aware Dynamic Loss Refinement (LDLR) to implement quality-driven hard mining through adaptive loss reweighting based on lesion size, anatomical relevance, and prediction quality, optimizing detection for subtle lesions. Extensive experiments on two public datasets (i.e., AlphaDent and DentalAI) demonstrate that Caries-DETR achieves a state-of-the-art performance compared to existing methods and exhibits good generalization and robustness. Code and data at https://github.com/XuefenLiu-SZU/Caries-DETR}{https://github.com/XuefenLiu-SZU/Caries-DETR.

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。