Scholarlink

Objective <p>To develop a deep learning-based fully automated model for estimating the mesiodistal width of teeth in standardized occlusal photographs, enabling accurate and efficient assessment of individual tooth dimensions.</p> Methods <p>The dataset comprised 14,403 teeth, including 12,079 teeth from an internal dataset and 2,328 teeth from an independent external test set. Clinically obtained mesiodistal crown widths derived from three-dimensional (3D) intraoral scans served as reference values. Corresponding mesial and distal keypoints were annotated on two-dimensional (2D) intraoral photographs. A two-stage deep learning framework was developed, consisting of tooth keypoint detection followed by a depth-informed regression model to estimate mesiodistal crown widths. Model performance was evaluated using key metrics, including mean absolute error (MAE), root mean squared error (RMSE), and the coefficient of determination (R²).</p> Results <p>The deep learning model demonstrated high accuracy across 12,079 teeth: MAE = 0.34&#xa0;mm (95% confidence interval [CI]: 0.33–0.34); RMSE = 0.44&#xa0;mm; R² = 0.94. External validation on 2,328 independent teeth demonstrated consistent performance (MAE = 0.33&#xa0;mm, RMSE = 0.42&#xa0;mm).</p> Conclusions <p>Our deep learning approach reliably estimates mesiodistal crown widths from standardized occlusal photographs, demonstrating strong agreement with 3D intraoral scan reference measurements and good clinical reproducibility across independent datasets within the same standardized workflow. Future studies will further investigate its robustness across heterogeneous imaging devices and acquisition conditions.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Automatic estimation of single-tooth width from standardized two-dimensional occlusal photographs using deep learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月9日

查看全文
  • Litong Li,
  • Yulin Shi,
  • Duo Wang,
  • Weixu Li,
  • Tingting Liu,
  • Yuanqing Ma,
  • Meng Cao

摘要

Objective

To develop a deep learning-based fully automated model for estimating the mesiodistal width of teeth in standardized occlusal photographs, enabling accurate and efficient assessment of individual tooth dimensions.

Methods

The dataset comprised 14,403 teeth, including 12,079 teeth from an internal dataset and 2,328 teeth from an independent external test set. Clinically obtained mesiodistal crown widths derived from three-dimensional (3D) intraoral scans served as reference values. Corresponding mesial and distal keypoints were annotated on two-dimensional (2D) intraoral photographs. A two-stage deep learning framework was developed, consisting of tooth keypoint detection followed by a depth-informed regression model to estimate mesiodistal crown widths. Model performance was evaluated using key metrics, including mean absolute error (MAE), root mean squared error (RMSE), and the coefficient of determination (R²).

Results

The deep learning model demonstrated high accuracy across 12,079 teeth: MAE = 0.34 mm (95% confidence interval [CI]: 0.33–0.34); RMSE = 0.44 mm; R² = 0.94. External validation on 2,328 independent teeth demonstrated consistent performance (MAE = 0.33 mm, RMSE = 0.42 mm).

Conclusions

Our deep learning approach reliably estimates mesiodistal crown widths from standardized occlusal photographs, demonstrating strong agreement with 3D intraoral scan reference measurements and good clinical reproducibility across independent datasets within the same standardized workflow. Future studies will further investigate its robustness across heterogeneous imaging devices and acquisition conditions.