Bo Shishi, Gao Chengzhi
Department of General Dentistry Ⅱ, Peking University School and Hospital of Stomatology & National Center for Stomatology & National Clinical Research Center for Oral Diseases & National Engineering Research Center of Oral Biomaterials and Digital Medical Devices, Beijing 100081, China.
Department of Dentistry, Peking University People' s Hospital, Beijing 100044, China.
Beijing Da Xue Xue Bao Yi Xue Ban. 2024 Aug 18;56(4):735-740. doi: 10.19723/j.issn.1671-167X.2024.04.030.
To propose a novel neural network to achieve tooth instance segmentation and recognition based on cone-beam computed tomography (CBCT) voxel data.
The proposed methods included three different convolutional neural network models. The architecture was based on the Resnet module and built according to the structure of "Encoder-Decoder" and U-Net. The CBCT image was de-sampled and a fixed-size region of interest (ROI) containing all the teeth was determined. ROI would first through a two-branch "encoder and decoder" structure of the network, the network could predict each voxel in the input data of the spatial embedding. The post-processing algorithm would cluster the prediction results of the relevant spatial location information according to the two-branch network to realize the tooth instance segmentation. The tooth position identification was realized by another U-Net model based on the multi-classification segmentation task. According to the predicted results of the network, the post-processing algorithm would classify the tooth position according to the voting results of each tooth instance segmentation. At the original spatial resolution, a U-Net network model for the fine-tooth segmentation was trained using the region corresponding to each tooth as the input. According to the results of instance segmentation and tooth position identification, the model would process the correspon-ding positions on the high-resolution CBCT images to obtain the high-resolution tooth segmentation results. In this study, CBCT data of 59 cases with simple crown prostheses and implants were collected for manual labeling as the database, and statistical indicators were evaluated for the prediction results of the algorithm. To assess the performance of tooth segmentation and classification, instance similarity coefficient (IDSC) and the average similarity coefficient (ADSC) were calculated.
The experimental results showed that the IDSC was 89.35%, and the ADSC was 84. 74%. After eliminating the data with prostheses artifacts, the database of 43 samples was generated, and the performance of the training network was better, with 90.34% for IDSC and 87.88% for ADSC. The framework achieved excellent performance on tooth segmentation and identification. Voxels near intercuspation surfaces and fuzzy boundaries could be separated into correct instances by this framework.
The results show that this method can not only successfully achieve 3D tooth instance segmentation but also identify all teeth notation numbers accurately, which has clinical practicability.
提出一种新型神经网络，以基于锥束计算机断层扫描（CBCT）体素数据实现牙齿实例分割与识别。
所提出的方法包括三种不同的卷积神经网络模型。该架构基于Resnet模块，并根据“编码器 - 解码器”和U-Net的结构构建。对CBCT图像进行下采样，并确定包含所有牙齿的固定大小的感兴趣区域（ROI）。ROI首先通过网络的双分支“编码器和解码器”结构，该网络可以预测输入数据中每个体素的空间嵌入。后处理算法将根据双分支网络对相关空间位置信息的预测结果进行聚类，以实现牙齿实例分割。牙齿位置识别通过基于多分类分割任务的另一个U-Net模型实现。根据网络的预测结果，后处理算法将根据每个牙齿实例分割的投票结果对牙齿位置进行分类。在原始空间分辨率下，使用每个牙齿对应的区域作为输入来训练用于精细牙齿分割的U-Net网络模型。根据实例分割和牙齿位置识别的结果，该模型将对高分辨率CBCT图像上的相应位置进行处理，以获得高分辨率牙齿分割结果。在本研究中，收集了59例简单冠修复和种植体病例的CBCT数据进行人工标注作为数据库，并对算法的预测结果评估统计指标。为评估牙齿分割和分类的性能，计算了实例相似系数（IDSC）和平均相似系数（ADSC）。
实验结果表明，IDSC为89.35%，ADSC为84.74%。去除带有修复体伪影的数据后，生成了43个样本的数据库，训练网络的性能更好，IDSC为90.34%，ADSC为87.88%。该框架在牙齿分割和识别方面取得了优异的性能。牙尖间表面和模糊边界附近的体素可以通过该框架被分割到正确的实例中。
结果表明，该方法不仅可以成功实现三维牙齿实例分割，还能准确识别所有牙齿的编号，具有临床实用性。
