摘要
目的：本试点研究调查是否可以使用深度学习从口内扫描图像预测由T-Scan测量的咬合力分布。方法：分析了26名受试者的配对口内扫描和T-Scan图像。质量控制后，数据在受试者层面随机划分为训练集（n=18）、验证集（n=4）和独立测试集（n=4；8对图像）。训练五种深度学习架构（U-Net, ResNet-UNet, Vision Transformer, CNN-Attention, Pix2Pix）以从咬合扫描图像预测T-Scan力图。结构相似性指数（SSIM）预定义为主要终点。使用非参数统计比较（Friedman检验结合Holm校正的Wilcoxon事后分析）和Bootstrap置信区间。结果：模型间的SSIM存在显著差异（χ² = 19.3, p = 0.00069）。CNN-Attention实现了最高的结构相似性（平均SSIM 0.501 ± 0.030），显著优于U-Net、Vision Transformer和ResNet-UNet（调整后p < 0.05），但与Pix2Pix无显著差异。Pix2Pix显示出最低的平均绝对误差（0.237 ± 0.018），表明在像素级强度近似方面表现更佳。验证曲线揭示了不同的优化行为，对抗训练显示出后期的SSIM改进。结论：在此试点数据集中，深度学习模型能够从口内扫描图像近似T-Scan咬合力图。这些发现表明人工智能可能有助于从形态学口内扫描数据中估计功能性咬合力分布。需要更大规模的数据集研究来验证其临床适用性。临床意义：从口内扫描计算预测功能性咬合力图可能是数字牙科工作流程中整合形态和功能数据的未来步骤，但在临床应用前需要更大的验证研究。
原文摘要
OBJECTIVES: This pilot study investigated whether occlusal force distribution measured by T-Scan can be predicted from intraoral scan images using deep learning.
METHODS: Paired intraoral scan and T-Scan images from 26 subjects were analyzed. Following quality control, data were randomly partitioned at the subject level into training (n = 18), validation (n = 4), and independent test (n = 4; 8 image pairs) sets. Five deep learning architectures (U-Net, ResNet-UNet, Vision Transformer, CNN-Attention, and Pix2Pix) were trained to predict T-Scan force maps from occlusal scan images. Structural Similarity Index (SSIM) was predefined as the primary endpoint. Nonparametric statistical comparisons (Friedman test with Holm-corrected Wilcoxon post hoc analysis) and bootstrap confidence intervals were used.
RESULTS: A significant difference in SSIM was observed among models (χ² = 19.3, p = 0.00069). CNN-Attention achieved the highest structural similarity (mean SSIM 0.501 ± 0.030), significantly outperforming U-Net, Vision Transformer, and ResNet-UNet (adjusted p < 0.05), while not differing significantly from Pix2Pix. Pix2Pix demonstrated the lowest mean absolute error (0.237 ± 0.018), indicating superior pixel-level intensity approximation. Validation curves revealed distinct optimization behaviors, with adversarial training showing late-stage improvements in SSIM.
CONCLUSIONS: Deep learning models approximated T-Scan occlusal force maps from intraoral scan images in this pilot dataset. These findings suggest that artificial intelligence may help estimate functional occlusal force distribution from morphological intraoral scan data. Further studies with larger datasets are required to validate clinical applicability.
CLINICAL SIGNIFICANCE: Computational prediction of functional occlusal force maps from intraoral scans may represent a future step toward integrating morphological and functional data within digital dentistry workflows; however, larger validation studies are required before clinical application.
出处
Clinical oral investigations 2026;30(8). DOI: 10.1007/s00784-026-06994-6.
本页仅收录摘要与出处，不存储全文（合规要求）。