文献速递牙体牙髓病

从微型CT到根尖片:迁移学习用于三维根管形态识别

Transfer Learning From Micro-CT to Periapical Radiographs for Three-Dimensional Root Canal Morphological Identification.
PubMed 文献 · Int Endod J · 2026-02-23

本研究以融合根下颌第二磨牙为模型,将微型CT隐含解剖特征通过迁移学习迁移至临床模拟根尖片,评估多模态迁移学习对根管三维形态识别的可行性与效果。结果显示,虚拟X线片预训练CNN在三分类任务中平均准确率69.68%,显著高于ImageNet预训练模型和牙髓住院医师,且Grad-CAM显示其注意力更集中于根结构;二分类任务中各组无显著差异。

要点

  • 微型CT虚拟X线片预训练可提升CNN对复杂根管形态的分类准确率。
  • 迁移学习收益在需提取复杂形态特征的多分类任务中更大。
  • 简化二分类后迁移学习优势消失,各组准确率无显著差异。

核心结论

  • 微型CT虚拟X线片提取的隐含三维特征可通过迁移学习有效迁移至临床模拟根尖片,提升CNN可解释性与诊断精度。

研究设计与样本

  • 以融合根下颌第二磨牙为模型,用高分辨率微型CT生成虚拟X线片,并从离体下颌骨获取临床模拟根尖片。
  • 根管按微型CT分类为融合型、对称型和非对称型,训练VGG19、ResNet18、ResNet50和EfficientNet-b5四种CNN。
  • 设置三种训练条件:临床模拟根尖片+ImageNet预训练、虚拟X线片+ImageNet预训练、临床模拟根尖片+虚拟X线片预训练。
  • 使用Grad-CAM可视化解释模型注意力,并与四名牙髓住院医师比较。
  • 另将对称型和非对称型合并为「分离」组,生成二分类任务以降低任务复杂度。

主要发现

  • 三分类任务中,虚拟X线片预训练CNN平均准确率69.68%(95% CI: 64.61%-74.76%),显著高于ImageNet预训练模型64.36%(95% CI: 61.12%-67.61%)和牙髓住院医师61.17%(95% CI: 56.09%-66.25%)(p < 0.05)。
  • Grad-CAM显示虚拟X线片预训练模型注意力集中于根结构,而ImageNet预训练网络注意力弥散或错位。
  • 二分类任务中,虚拟X线片预训练CNN准确率79.79%(95% CI: 73.30%-86.27%),ImageNet预训练模型73.41%(95% CI: 67.54%-79.27%),住院医师76.60%(95% CI: 69.28%-83.91%),组间无显著差异(p > 0.05)。
  • 迁移学习后整体诊断平衡改善,表明跨类别特征表征更好。

临床怎么用

  • 对需精细形态识别的复杂根管分类任务,可优先采用微型CT虚拟X线片预训练CNN以提升准确率。
  • 在简化二分类场景中,迁移学习未必优于常规预训练或住院医师判断,需结合任务复杂度选择模型。

局限性

  • 研究为离体实验,采用临床模拟根尖片而非真实临床病例。
  • 样本仅限融合根下颌第二磨牙,结论外推至其他牙位需谨慎。

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

AIM: This study investigated the transfer of implicit anatomical features from micro-CT to periapical radiographs using fused-rooted mandibular second molars (MSMs) as a model. The objective was to evaluate the feasibility and effectiveness of multimodal transfer learning for the three-dimensional (3D) morphological identification of root canals, and to examine how task complexity influences transfer performance. METHODOLOGY: Fused-rooted MSMs were scanned using high-resolution micro-CT to generate virtual radiographs. Clinically simulated periapical radiographs (CSPRs) were obtained from ex vivo mandibles to reproduce realistic clinical conditions. Based on micro-CT classification, root canals were divided into merging, symmetrical and asymmetrical types. Four convolutional neural network (CNN) architectures (VGG19, ResNet18, ResNet50 and EfficientNet-b5) were trained under three conditions: (1) CSPRs with ImageNet-pretrained CNNs, (2) virtual radiographs with ImageNet-pretrained CNNs, and (3) CSPRs with CNNs pretrained on virtual radiographs. Grad-CAM visualisation was used to interpret model attention, and results were compared with those of four endodontic residents. To reduce task complexity, symmetrical and asymmetrical types were later merged into a "separating" group to generate a two-class classification task. RESULTS: In the three-class task, CNNs pretrained on virtual radiographs achieved an average accuracy of 69.68% (95% CI: 64.61%-74.76%), significantly higher than ImageNet-pretrained models (64.36%, 95% CI: 61.12%-67.61%) and endodontic residents (61.17%, 95% CI: 56.09%-66.25%) (p < 0.05). Grad-CAM visualisation revealed that virtual radiograph-pretrained models concentrated attention on root structures, whereas ImageNet-pretrained networks showed diffuse or misplaced focus. In the two-class task, accuracies were 79.79% (95% CI: 73.30%-86.27%) for CNNs pretrained on virtual radiographs, 73.41% (95% CI: 67.54%-79.27%) for ImageNet-pretrained models and 76.60% (95% CI: 69.28%-83.91%) for residents, with no significant differences (p > 0.05). The overall diagnostic balance improved following transfer learning, indicating better feature representation across classes. CONCLUSIONS: Implicit 3D features extracted from micro-CT-based virtual radiographs can be effectively transferred to CSPRs through transfer learning. This approach enhances CNN interpretability and diagnostic precision in identifying root canal morphology. The benefits of transfer learning are greater for complex, multi-class tasks that require the extraction of intricate morphological features, whereas its effect diminishes in simplified binary classifications. These findings provide a theoretical and experimental foundation for applying multimodal transfer learning to clinical dental imaging.

来源:Int Endod J,查看原文。版权归原作者所有。

引用

  1. Wu W, Hu J, Shen B, et al. Transfer Learning From Micro-CT to Periapical Radiographs for Three-Dimensional Root Canal Morphological Identification. Int Endod J. 2026. PMID: 41731328. doi:10.1111/iej.70124

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。