[论文解读] Teeth3DS+: An Extended Benchmark for Intraoral 3D Scans Analysis

Achraf Ben-Hamadou, Neifar, Nour+6 more|arXiv (Cornell University)|Oct 12, 2022

Dental Radiography and Imaging被引用 20

一句话总结

Teeth3DS+ 提供一个公开可用的1800个口内3D扫描（23999个带注释的牙齿）的基准，用于牙齿分割和标注，附带详细的注释流程和MICCAI 2022挑战用例。

ABSTRACT

Intraoral 3D scanning is now widely adopted in modern dentistry and plays a central role in supporting key tasks such as tooth segmentation, detection, labeling, and dental landmark identification. Accurate analysis of these scans is essential for orthodontic and restorative treatment planning, as it enables automated workflows and minimizes the need for manual intervention. However, the development of robust learning-based solutions remains challenging due to the limited availability of high-quality public datasets and standardized benchmarks. This article presents Teeth3DS+, an extended public benchmark dedicated to intraoral 3D scan analysis. Developed in the context of the MICCAI 3DTeethSeg and 3DTeethLand challenges, Teeth3DS+ supports multiple fundamental tasks, including tooth detection, segmentation, labeling, 3D modeling, and dental landmark identification. The dataset consists of rigorously curated intraoral scans acquired using state-of-the-art scanners and validated by experienced orthodontists and dental surgeons. In addition to the data, Teeth3DS+ provides standardized data splits and evaluation protocols to enable fair and reproducible comparison of methods, with the goal of fostering progress in learning-based analysis of 3D dental scans. Detailed instructions for accessing the dataset are available at https://crns-smartvision.github.io/teeth3ds

研究动机与目标

• 通过提供一个大规模、公开可用的口内3D牙齿数据集，促进自动化CAD工具开发以用于正畸规划。
• 在真实的 IOS 数据上实现牙齿检测、分割和标注方法的公平评估。
• 从口内扫描支持牙列的3D建模与重建等更广泛的任务。

提出的方法

• 使用三种IOS设备（Primescan、Trios3、iTero Element 2 Plus）收集900名患者的口内扫描（上颌与下颌）。
• 使用包括预处理、姿态归一化、牙齿裁剪、通过谐参数化进行UV映射、边界的反向传播，以及临床验证在内的八步注释流程。
• 提供训练/测试划分（1200个扫描用于训练，600个用于测试），并以JSON格式给出真实标签和实例。
• 将扫描对齐到咬合平面并将数据居中，以提高牙齿可见性和姿态归一化。
• 使用国际牙科联盟（FDI）编号对牙齿进行标注，并由正畸医师/口腔外科医师进行临床验证。
• 分享数据处理和验证指标的代码，并将数据托管在 Figshare 上。

实验结果

研究问题

• RQ1 自动化方法是否能够在3D口内扫描中准确定位、分割和标注单个牙齿？

主要发现

• 不同方法的定位准确率范围为45.3%到96.58%。
• 牙齿分割准确率范围为81.26%到98.59%。
• 牙齿识别（标注）率范围为68.36%到91%。
• 数据集包含1800个扫描，来自900名患者，总共有23999颗牙齿（16004个用于训练，7995个用于测试）。
• 上颌和下颌的牙齿数量分布相当，便于进行平衡评估。