基于锥形束CT图像的下颌牙周骨地形自动深度学习分割
本研究评估基于多阶段分割残差网络(SegResNet)的深度学习模型对III、IV期牙周炎患者锥形束CT图像进行自动分割的性能。模型在10例独立扫描上测试,与半自动分割相比平均DSC为0.9650±0.0097,并将分割时间减少47倍;颊侧一致性较低(ICC=0.7481)。
要点
- 深度学习模型对牙周骨地形分割的平均DSC为0.9650±0.0097,与半自动分割高度一致。
- 近中、远中、舌侧线性测量ICC均高于0.92,颊侧ICC为0.7481。
- 深度学习法较半自动法分割时间减少47倍。
核心结论
- 获取的3D模型可能有助于在传统诊断方法不足时进行精确治疗规划。
- 但需提高模型稳健性以改善牙周区域颊侧的总体可靠性和一致性。
研究设计与样本
- 研究使用70例接受牙周康复患者的预处理锥形束CT扫描进行训练和验证。
- 模型在10例独立于训练数据集的锥形束CT扫描上测试,与半自动分割结果比较。
主要发现
- 深度学习模型平均DSC为0.9650±0.0097,IoU为0.9340±0.0180,HD95为0.4820 mm±0.1269 mm。
- 近中、远中、舌侧线性测量ICC分别为0.9442(p<0.0001)、0.9232(p<0.0001)、0.9598(p<0.0001)。
- 颊侧测量ICC为0.7481(p<0.0001),一致性较低。
- 深度学习方法较半自动方法分割时间减少47倍。
关键数值与推荐
- 分割精度评估指标包括Dice相似系数(DSC)、交并比(IoU)和95百分位Hausdorff距离(HD95)。
- 在四个牙面进行线性牙周测量以评估深度学习分割在牙周区域的有效性。
临床怎么用
- 原文未据此给出推荐。
局限性
- 模型稳健性需提高以改善牙周区域颊侧的总体可靠性和一致性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
OBJECTIVES: This study evaluated the performance of a multi-stage Segmentation Residual Network (SegResNet)-based deep learning (DL) model for the automatic segmentation of cone-beam computed tomography (CBCT) images of patients with stage III and IV periodontitis. METHODS: Seventy pre-processed CBCT scans from patients undergoing periodontal rehabilitation were used for training and validation. The model was tested on 10 CBCT scans independent from the training dataset by comparing results with semi-automatic (SA) segmentations. Segmentation accuracy was assessed using the Dice similarity coefficient (DSC), Intersection over Union (IoU), and Hausdorff distance 95th percentile (HD95). Linear periodontal measurements were performed on four tooth surfaces to assess the validity of the DL segmentation in the periodontal region. RESULTS: The DL model achieved a mean DSC of 0.9650 ± 0.0097, with an IoU of 0.9340 ± 0.0180 and HD95 of 0.4820 mm ± 0.1269 mm, showing strong agreement with SA segmentation. Linear measurements revealed high statistical correlations between the mesial, distal, and lingual surfaces, with intraclass correlation coefficients (ICC) of 0.9442 (p < 0.0001), 0.9232 (p < 0.0001), and 0.9598(p < 0.0001), respectively, while buccal measurements revealed lower consistency, with an ICC of 0.7481 (p < 0.0001). The DL method reduced the segmentation time by 47 times compared to the SA method. CONCLUSIONS: Acquired 3D models may enable precise treatment planning in cases where conventional diagnostic modalities are insufficient. However, the robustness of the model must be increased to improve its general reliability and consistency at the buccal aspect of the periodontal region. CLINICAL SIGNIFICANCE: This study presents a DL model for the CBCT-based segmentation of periodontal defects, demonstrating high accuracy and a 47-fold time reduction compared to SA methods, thus improving the feasibility of 3D diagnostics for advanced periodontitis.
引用
- Palkovics D, Molnar B, Pinter C, et al. Automatic deep learning segmentation of mandibular periodontal bone topography on cone-beam computed tomography images. J Dent. 2025. PMID: 40373868. doi:10.1016/j.jdent.2025.105813
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。