文献速递口腔颌面外科口腔正畸

基于CBCT多视图二维切片的双层深度学习模型评估埋伏牙根骨粘连的诊断性能

[Diagnostic performance of a dual-stage deep learning model based on cone beam CT-derived multi-view two-dimensional slices for assessing ankylosed impacted teeth].
PubMed 文献 · Zhonghua Kou Qiang Yi Xue Za Zhi · 2026-01-01

回顾性纳入432例埋伏牙患者的600颗目标牙及约2.2万张CBCT派生二维切片,构建切片级分类与病灶级检测双层深度学习模型。独立验证集中,切片级分类模型ROC-AUC为0.850,阈值0.5时灵敏度36.8%、特异度96.4%;病灶级检测模型IoU 0.5时AP为0.582。模型可为埋伏牙根骨粘连提供概率提示和定位证据,具有阅片辅助应用前景。

要点

  • 切片级分类模型ROC-AUC为0.850,阈值0.5时灵敏度36.8%、特异度96.4%。
  • 病灶级检测模型在IoU 0.5时平均准确率为0.582。
  • 剔除困难样本挖掘后PR-AUC从0.439降至0.373。

核心结论

  • 基于CBCT派生多视图二维切片的双层深度学习模型可为埋伏牙根骨粘连提供概率提示和定位证据,具有作为阅片辅助工具的应用前景。

研究设计与样本

  • 回顾性纳入2023年1月至2025年6月西安交通大学口腔医院正畸科收治的行CBCT检查的埋伏牙患者432例,共600颗目标牙。
  • 从CBCT数据派生约2.2万张二维切片,由2名口腔颌面影像学住院医师及以上职称医师独立判读,意见不一致时由1名主任医师仲裁,形成影像学参考标准。
  • 以目标牙为分配单元按4∶1比例划分训练集和独立验证集。
  • 构建双层深度学习模型:第一层为切片级分类模型判断单张切片是否存在根骨粘连征象并输出概率;第二层为病灶级检测模型定位可疑根骨粘连病灶。

主要发现

  • 独立验证集中,切片级分类模型受试者操作特征曲线下面积为0.850,精准率-召回率曲线下面积为0.439,布里尔分数为0.071。
  • 阈值为0.5时切片级分类模型灵敏度为36.8%,特异度为96.4%。
  • 病灶级检测模型交并比为0.5时的平均准确率为0.582。
  • 消融实验提示剔除困难样本挖掘模块后,精准率-召回率曲线下面积从0.439降至0.373。

关键数值与推荐

  • 切片级分类模型ROC-AUC为0.850,PR-AUC为0.439,Brier分数为0.071。
  • 阈值0.5时灵敏度36.8%、特异度96.4%。
  • 病灶级检测模型IoU 0.5时AP为0.582。
  • 剔除困难样本挖掘后PR-AUC从0.439降至0.373。

临床怎么用

  • 模型可输出切片级根骨粘连概率提示,辅助判断埋伏牙是否存在根骨粘连征象。
  • 病灶级检测模型可在目标牙周围区域定位可疑根骨粘连病灶,为阅片提供定位证据。

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

Objective: To develop and validate a dual-layer deep learning model based on cone-beam CT (CBCT)-derived multi-view two-dimensional (2D) slices for the assisted assessment of ankylosed impacted teeth. Methods: The CBCT images of 432 patients with impacted teeth were collected at the Hospital of Stomatology, Xi'an Jiaotong University from January 2023 to June 2025, comprising 600 target teeth and approximately 22 000 derived multi-view 2D slices. Imaging reference standards were established by two experienced oral and maxillofacial residents, with adjudication by a professor in cases of disagreement. Data were split into training and validation sets at a 4∶1 ratio by target tooth. A two-stage deep learning model was developed, including a slice-level classifier for predicting dentoalveolar ankylosis and a lesion-level detector for localizing suspicious ankylotic regions. Model performance was evaluated using area under the receiver operating characteristic curve (ROC-AUC), (PR-AUC), sensitivity, specificity, Brier score, average precision (AP) at intersection over union (IoU) 0.5, and ablation analysis. Results: In the validation set, the slice-level classification model achieved an area under the receiver operating characteristic curve of 0.850, an area under the precision-recall curve of 0.439, and a Brier score of 0.071. At a threshold of 0.5, the sensitivity and specificity were 36.8% and 96.4%, respectively. The lesion-level detection model achieved an average precision of 0.582 at an intersection-over-union threshold of 0.5. Ablation experiments showed that eliminating hard example mining significantly decreased positive recall and overall model performance with an increase in the area under the precision-recall curve from 0.439 to 0.373. Conclusions: The proposed model can provide probabilistic cues and lesion localization evidence for ankylosed impacted teeth, showing potential as an auxiliary tool for radiographic interpretation. 目的: 构建并验证基于锥形束CT派生多视图二维切片的双层深度学习模型,辅助评估埋伏牙牙根-牙槽骨粘连(简称根骨粘连)的效果。 方法: 回顾性纳入2023年1月至2025年6月西安交通大学口腔医院正畸科收治并行锥形束CT检查的埋伏牙患者432例,共600颗需评估牙根-牙槽骨关系的埋伏牙作为目标牙。从锥形束CT数据中派生出约2.2万张二维切片,由2名口腔颌面影像学住院医师及以上职称医师独立判读,意见不一致时由1名主任医师仲裁,形成影像学参考标准。以目标牙为分配单元按4∶1比例划分训练集和独立验证集。构建双层深度学习模型:第一层为切片级分类模型,用于判断单张二维切片是否存在根骨粘连征象并输出根骨粘连概率;第二层为病灶级检测模型,用于在目标牙周围区域定位可疑根骨粘连病灶并形成辅助提示。采用受试者操作特征曲线下面积、精准率-召回率曲线下面积、灵敏度、特异度和布里尔分数评价模型切片级分类性能;采用交并比为0.5时的平均准确率评价模型病灶级检测性能;并通过消融实验分析困难样本挖掘等策略对模型性能的影响。 结果: 独立验证集中,切片级分类模型的受试者操作特征曲线下面积为0.850,精准率-召回率曲线下面积为0.439,布里尔分数为0.071;阈值为0.5时灵敏度为36.8%,特异度为96.4%;病灶级检测模型交并比为0.5时的平均准确率为0.582。消融实验提示,剔除困难样本挖掘模块后,精准率-召回率曲线下面积从0.439降至0.373。 结论: 基于锥形束CT派生多视图二维切片的双层深度学习模型可为埋伏牙根骨粘连提供概率提示和定位证据,具有作为阅片辅助工具的应用前景。.

来源:Zhonghua Kou Qiang Yi Xue Za Zhi,查看原文。版权归原作者所有。

引用

  1. Wu GL, Lu Z, Du TJ, et al. [Diagnostic performance of a dual-stage deep learning model based on cone beam CT-derived multi-view two-dimensional slices for assessing ankylosed impacted teeth]. Zhonghua Kou Qiang Yi Xue Za Zhi. 2026. PMID: 42532535. doi:10.3760/cma.j.cn112144-20260304-00148

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。