Rekik Ahmed, Ben-Hamadou Achraf, Smaoui Oussama, Bouzguenda Firas, Pujades Sergi, Boyer Edmond
Digital Research Center of Sfax, Technopark of Sfax, Sakiet Ezzit, 3021 Sfax, Tunisia; ISSAT, Gafsa university, Sidi Ahmed Zarrouk University Campus, 2112 Gafsa, Tunisia; Laboratory of Signals, systeMs, aRtificial Intelligence and neTworkS, Technopark of Sfax, Sakiet Ezzit, 3021 Sfax, Tunisia.
Digital Research Center of Sfax, Technopark of Sfax, Sakiet Ezzit, 3021 Sfax, Tunisia; Laboratory of Signals, systeMs, aRtificial Intelligence and neTworkS, Technopark of Sfax, Sakiet Ezzit, 3021 Sfax, Tunisia.
Comput Biol Med. 2025 Feb;185:109535. doi: 10.1016/j.compbiomed.2024.109535. Epub 2024 Dec 20.
This study introduces a novel deep learning approach for 3D teeth scan segmentation and labeling, designed to enhance accuracy in computer-aided design (CAD) systems. Our method is organized into three key stages: coarse localization, fine teeth segmentation, and labeling. In the teeth localization stage, we employ a Mask-RCNN model to detect teeth in a rendered three-channel 2D representation of the input scan. For fine teeth segmentation, each detected tooth mesh is isomorphically mapped to a 2D harmonic parameter space and segmented with a Mask-RCNN model for precise crown delineation. Finally, for labeling, we propose a graph neural network that captures both the 3D shape and spatial distribution of the teeth, along with a new data augmentation technique to simulate missing teeth and teeth position variation during training. The method is evaluated using three key metrics: Teeth Localization Accuracy (TLA), Teeth Segmentation Accuracy (TSA), and Teeth Identification Rate (TIR). We tested our approach on the Teeth3DS dataset, consisting of 1800 intraoral 3D scans, and achieved a TLA of 98.45%, TSA of 98.17%, and TIR of 97.61%, outperforming existing state-of-the-art techniques. These results suggest that our approach significantly enhances the precision and reliability of automatic teeth segmentation and labeling in dental CAD applications. Link to the project page: https://crns-smartvision.github.io/tseglab.
本研究介绍了一种用于3D牙齿扫描分割和标记的新型深度学习方法，旨在提高计算机辅助设计（CAD）系统的准确性。我们的方法分为三个关键阶段：粗略定位、精细牙齿分割和标记。在牙齿定位阶段，我们使用Mask-RCNN模型在输入扫描的渲染三通道二维表示中检测牙齿。对于精细牙齿分割，将每个检测到的牙齿网格同构映射到二维谐波参数空间，并用Mask-RCNN模型进行分割以精确勾勒牙冠轮廓。最后，对于标记，我们提出了一种图神经网络，它可以捕捉牙齿的三维形状和空间分布，以及一种新的数据增强技术，用于在训练期间模拟缺失牙齿和牙齿位置变化。该方法使用三个关键指标进行评估：牙齿定位准确率（TLA）、牙齿分割准确率（TSA）和牙齿识别率（TIR）。我们在由1800次口腔内3D扫描组成的Teeth3DS数据集上测试了我们的方法，获得了98.45%的TLA、98.17%的TSA和97.61%的TIR，优于现有的最先进技术。这些结果表明，我们的方法显著提高了牙科CAD应用中自动牙齿分割和标记的精度和可靠性。项目页面链接：https://crns-smartvision.github.io/tseglab 。
