Enhanced Pediatric Dental Segmentation Using a Custom SegUNet with VGG19 Backbone on Panoramic Radiographs

TL;DR

Pediatric dental segmentation is challenging due to small teeth and variable anatomy, exacerbated by data scarcity. The authors propose a custom SegUNet with a pre-trained VGG19 backbone and apply it to the Children’s Dental Panoramic Radiographs Dataset, achieving state-of-the-art accuracy (≈97.5%), Dice (≈92.5%), and IoU (≈91.5%), signaling strong generalization across diverse pediatric dental structures. Key contributions include first integration of SegUNet with a VGG19 backbone on this dataset and demonstration of improved feature extraction enabling precise segmentation for automated diagnostics. The work establishes a new benchmark for pediatric dental segmentation and highlights potential for clinical deployment, while noting dataset size as a limitation and suggesting future exploration of ViT-based approaches and transfer learning.

Abstract

Pediatric dental segmentation is critical in dental diagnostics, presenting unique challenges due to variations in dental structures and the lower number of pediatric X-ray images. This study proposes a custom SegUNet model with a VGG19 backbone, designed explicitly for pediatric dental segmentation and applied to the Children's Dental Panoramic Radiographs dataset. The SegUNet architecture with a VGG19 backbone has been employed on this dataset for the first time, achieving state-of-the-art performance. The model reached an accuracy of 97.53%, a dice coefficient of 92.49%, and an intersection over union (IOU) of 91.46%, setting a new benchmark for this dataset. These results demonstrate the effectiveness of the VGG19 backbone in enhancing feature extraction and improving segmentation precision. Comprehensive evaluations across metrics, including precision, recall, and specificity, indicate the robustness of this approach. The model's ability to generalize across diverse dental structures makes it a valuable tool for clinical applications in pediatric dental care. It offers a reliable and efficient solution for automated dental diagnostics.

Figures (5)

• Figure 1: Sample dental panoramic radiograph and mask from Children's Dental Panoramic Radiographs Dataset
• Figure 2: Complete workflow of combining children's radiographs, training the custom SegUNet with VGG19 backbone, and testing on pediatric dental X-rays for segmentation
• Figure 3: Proposed custom SegUNet model architecture
• Figure 4: Train and validation accuracy curves for the experiments listed on Table \ref{['table2']}
• Figure 5: Normalized confusion matrices for the experiments listed in Table \ref{['table2']}