OMFS-IMPATH Research Group, Department of Imaging and Pathology, Faculty of Medicine, KU Leuven & Department of Oral and Maxillofacial Surgery, University Hospitals Leuven, Belgium, 3000 Leuven, Belgium; Department of Prosthodontics, Faculty of Dentistry, Tanta University, 31511 Tanta, Egypt.
OMFS-IMPATH Research Group, Department of Imaging and Pathology, Faculty of Medicine, KU Leuven & Department of Oral and Maxillofacial Surgery, University Hospitals Leuven, Belgium, 3000 Leuven, Belgium.
J Dent. 2023 Oct;137:104639. doi: 10.1016/j.jdent.2023.104639. Epub 2023 Jul 28.
To train and validate a cloud-based convolutional neural network (CNN) model for automated segmentation (AS) of dental implant and attached prosthetic crown on cone-beam computed tomography (CBCT) images.
A total dataset of 280 maxillomandibular jawbone CBCT scans was acquired from patients who underwent implant placement with or without coronal restoration. The dataset was randomly divided into three subsets: training set (n = 225), validation set (n = 25) and testing set (n = 30). A CNN model was developed and trained using expert-based semi-automated segmentation (SS) of the implant and attached prosthetic crown as the ground truth. The performance of AS was assessed by comparing with SS and manually corrected automated segmentation referred to as refined-automated segmentation (R-AS). Evaluation metrics included timing, voxel-wise comparison based on confusion matrix and 3D surface differences.
The average time required for AS was 60 times faster (<30 s) than the SS approach. The CNN model was highly effective in segmenting dental implants both with and without coronal restoration, achieving a high dice similarity coefficient score of 0.92±0.02 and 0.91±0.03, respectively. Moreover, the root mean square deviation values were also found to be low (implant only: 0.08±0.09 mm, implant+restoration: 0.11±0.07 mm) when compared with R-AS, implying high AI segmentation accuracy.
The proposed cloud-based deep learning tool demonstrated high performance and time-efficient segmentation of implants on CBCT images.
AI-based segmentation of implants and prosthetic crowns can minimize the negative impact of artifacts and enhance the generalizability of creating dental virtual models. Furthermore, incorporating the suggested tool into existing CNN models specialized for segmenting anatomical structures can improve pre-surgical planning for implants and post-operative assessment of peri‑implant bone levels.
训练和验证一种基于云的卷积神经网络（CNN）模型，用于对锥形束计算机断层扫描（CBCT）图像上的牙科种植体及其附着的修复体进行自动分割（AS）。
从接受种植体植入术的患者中获取了 280 例颌骨 CBCT 扫描的总数据集，这些患者中有或没有进行牙冠修复。数据集被随机分为三个子集：训练集（n=225）、验证集（n=25）和测试集（n=30）。使用基于专家的种植体和附着修复体半自动分割（SS）作为地面实况来开发和训练 CNN 模型。通过与 SS 和手动校正的自动分割（称为细化自动分割（R-AS））进行比较来评估 AS 的性能。评估指标包括时间、基于混淆矩阵的体素级比较和 3D 表面差异。
AS 的平均时间比 SS 方法快 60 倍（<30s）。该 CNN 模型在分割有或没有牙冠修复的种植体方面非常有效，分别获得了 0.92±0.02 和 0.91±0.03 的高骰子相似系数评分。此外，与 R-AS 相比，均方根偏差值也较低（仅种植体：0.08±0.09mm，种植体+修复体：0.11±0.07mm），这意味着 AI 分割具有高精度。
所提出的基于云的深度学习工具在 CBCT 图像上对种植体进行了高效的分割。
基于人工智能的种植体和修复体分割可以最大程度地减少伪影的负面影响，并增强创建牙科虚拟模型的通用性。此外，将建议的工具纳入专门用于分割解剖结构的现有 CNN 模型中，可以改善种植体的术前规划和种植体周围骨水平的术后评估。
