文献速递口腔修复与种植口腔颌面外科

人工智能在牙种植体放射影像中检测与分割修复体垂直不密合:一项横断面分析

Artificial Intelligence in Detecting and Segmenting Vertical Misfit of Prosthesis in Radiographic Images of Dental Implants: A Cross-Sectional Analysis.
PubMed 文献 · Clin Oral Implants Res · 2025-01-22

本研究利用根尖片评估ResNet-50和U-Net模型检测与分割种植冠垂直不密合的表现,共纳入638张影像,以两位专家分类为参考、手动标注不密合区域,70%用于训练、30%用于验证与测试,并与五名全科牙医比较。结果显示AI与牙医间kappa值为0.93–0.98,ResNet-50准确率92.7%、精确率87.5%,牙医平均准确率93.3%、精确率89.6%,AI与牙医平均表现指标间无显著差异(p > 0.05)。结论认为AI可在根尖片上检测和分割种植修复冠垂直不密合,表现与临床医生相当。

要点

  • AI与牙医判断种植冠垂直不密合的kappa值为0.93–0.98,一致性极好。
  • ResNet-50准确率92.7%、精确率87.5%,牙医平均准确率93.3%、精确率89.6%。
  • AI与牙医平均表现指标间无显著差异(p > 0.05)。

核心结论

  • AI可在根尖片上检测和分割种植修复冠垂直不密合,表现与临床医生相当。

研究设计与样本

  • 横断面分析,共收集638张种植冠根尖片,由两位专家依据垂直不密合存在与否分类作为参考组,并对不密合区域手动标注。
  • 数据集70%用于训练、30%用于验证和测试,训练ResNet-50和U-Net深度学习模型,五名全科牙医对测试图像分类为「不密合」或「密合」。

主要发现

  • 牙医与AI间kappa值为0.93–0.98,一致性极好。
  • ResNet-50准确率92.7%、精确率87.5%,牙医平均准确率93.3%、精确率89.6%。
  • AI敏感度90.3%、特异度93.8%,牙医敏感度90.1%、特异度95.1%。
  • ResNet-50的Dice系数为88.9%,牙医为89.5%;U-Net损失0.01、准确率0.98。
  • 牙医与AI平均表现指标间无显著差异(p > 0.05)。

关键数值与推荐

  • 以两位专家分类为参考标准,AI与牙医间kappa值0.93–0.98。
  • ResNet-50准确率92.7%、精确率87.5%、敏感度90.3%、特异度93.8%、Dice系数88.9%。
  • 牙医平均准确率93.3%、精确率89.6%、敏感度90.1%、特异度95.1%、Dice系数89.5%。
  • U-Net损失0.01、准确率0.98;牙医与AI平均表现指标比较p > 0.05。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

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

OBJECTIVE: This study evaluated ResNet-50 and U-Net models for detecting and segmenting vertical misfit in dental implant crowns using periapical radiographic images. METHODS: Periapical radiographs of dental implant crowns were classified by two experts based on the presence of vertical misfit (reference group). The misfit area was manually annotated in images exhibiting vertical misfit. The resulting datasets were utilized to train the ResNet-50 and U-Net deep learning models. Then, 70% of the images were allocated for training, while the remaining 30% were used for validation and testing. Five general dentists categorized the testing images as "misfit" or "fit." Inter-rater reliability with Cohen's kappa index and performance metrics were calculated. The average performance metrics of dentists and artificial intelligence (AI) were compared using the paired-samples t test. RESULTS: A total of 638 radiographs were collected. The kappa values between dentists and AI ranged from 0.93 to 0.98, indicating perfect agreement. The ResNet-50 model achieved accuracy and precision of 92.7% and 87.5%, respectively, whereas dentists had a mean accuracy of 93.3% and precision of 89.6%. The sensitivity and specificity for AI were 90.3% and 93.8%, respectively, compared to 90.1% and 95.1% for dentists. The Dice coefficient yielded 88.9% for the ResNet-50 and 89.5% among the dentists. The U-Net algorithm produced a loss of 0.01 and an accuracy of 0.98. No significant difference was found between the average performance metrics of dentists and AI (p > 0.05). CONCLUSION: AI can detect and segment vertical misfit of implant prosthetic crowns in periapical radiographs, comparable to clinician performance.

来源:Clin Oral Implants Res,查看原文。版权归原作者所有。

引用

  1. Fasih P, Yari A, Kamali Hakim L, et al. Artificial Intelligence in Detecting and Segmenting Vertical Misfit of Prosthesis in Radiographic Images of Dental Implants: A Cross-Sectional Analysis. Clin Oral Implants Res. 2025. PMID: 39840554. doi:10.1111/clr.14406

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。