基于深度学习的三维骨分割方法及用于牙种植规划的缺牙区预测。

Deep learning-based approach for 3D bone segmentation and prediction of missing tooth region for dental implant planning.

机构信息

College of Computer Science and Engineering, Taibah University, 42353, Medina, Saudi Arabia.

Substitutive Dental Sciences Department (Prosthodontics), College of Dentistry, Taibah University, 41311, Al Madinah, Saudi Arabia.

出版信息

Sci Rep. 2024 Jun 16;14(1):13888. doi: 10.1038/s41598-024-64609-0.

DOI:10.1038/s41598-024-64609-0

PMID:38880802

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11180661/

Abstract

Recent studies have shown that dental implants have high long-term survival rates, indicating their effectiveness compared to other treatments. However, there is still a concern regarding treatment failure. Deep learning methods, specifically U-Net models, have been effectively applied to analyze medical and dental images. This study aims to utilize U-Net models to segment bone in regions where teeth are missing in cone-beam computerized tomography (CBCT) scans and predict the positions of implants. The proposed models were applied to a CBCT dataset of Taibah University Dental Hospital (TUDH) patients between 2018 and 2023. They were evaluated using different performance metrics and validated by a domain expert. The experimental results demonstrated outstanding performance in terms of dice, precision, and recall for bone segmentation (0.93, 0.94, and 0.93, respectively) with a low volume error (0.01). The proposed models offer promising automated dental implant planning for dental implantologists.

摘要

最近的研究表明，种植牙具有较高的长期存活率，这表明它们的效果优于其他治疗方法。然而，人们仍然担心治疗失败。深度学习方法，特别是 U-Net 模型，已被有效地应用于医学和牙科图像分析。本研究旨在利用 U-Net 模型对锥形束计算机断层扫描（CBCT）扫描中牙齿缺失区域的骨骼进行分割，并预测种植体的位置。所提出的模型应用于 2018 年至 2023 年期间塔伊巴大学牙科医院（TUDH）患者的 CBCT 数据集。它们使用不同的性能指标进行评估，并由领域专家进行验证。实验结果表明，在骨分割方面，模型具有出色的骰子系数、精确率和召回率（分别为 0.93、0.94 和 0.93），且体积误差较低（0.01）。这些模型为牙科种植专家提供了有前景的自动化牙科种植规划。