EUVIMEDEUVIMED entdecken
Crossref

Children's dental panoramic radiograph image segmentation via dual aggregation transformer UNet

Lingxiao Chen, Yaqi Wang, Wen Wu, Zhenyang Zhu, Xiaoyang Mao, Xiaodiao Chen

Medical Physics · 2026

DOI: 10.1002/mp.70202 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Physics, 2026. Verfasst von Lingxiao Chen und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China. Hauptthemen laut MEDLINE: Radiography, Panoramic, Image Processing, Computer-Assisted, Tooth. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 30 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Medical image processing is a critical field in computer vision, aiding in diagnostics and advancing medical research. Specifically, the diagnosis of children's dental conditions often involves the use of panoramic radiographs, which necessitate the segmentation of teeth for accurate diagnosis. However, children's teeth present more complexities than adult teeth due to limited datasets and the substantial changes in size and shape with age, along with the transition period between deciduous and permanent teeth, making segmentation challenging.

Purpose

This paper aims to introduce a medical image segmentation model specifically designed for children's teeth datasets, capable of efficiently and accurately segmenting children's teeth.

Methods

We designed a novel network structure called dual aggregation transformer UNet (DATUnet). The transformer layers aggregate features across spatial and channel dimensions, applying spatial and channel self‐attention mechanisms alternately in transformer blocks. This enhances the ability to extract variable shapes and sizes from children's teeth and address the issues like indistinct images and blurriness. Additionally, we developed a multi‐scale fusion decoder structure that adaptively fuses shallow and deep information processed through the transformer blocks.

Results

Our model, evaluated on a private dataset of children's dental panoramic radiographs, achieved outstanding performance with a pixel accuracy (PA) of 98.02%, Dice coefficient of 93.20%, and Hausdorff distance (HD) of 4.21.

Conclusions

Compared to other methods, our proposed model achieves superior results, reaching the state‐of‐the‐art (SOTA) in this field.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Radiography, PanoramicImage Processing, Computer-AssistedToothHumansChild

Stichwörter der Autor:innen

convolutional neural network (CNN)deep learningdental panoramic radiographmedical image segmentationtransformer

Autor:innen und Institutionen

  • School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China.
  • Communication University of Zhejiang, Electronic Design Automation Technology, Hangzhou, China.
  • School of Computer Science and Technology, Zhejiang University of Water Resources and Electric Power, Hangzhou, China.
  • Department of Computer Science and Engineering, University of Yamanashi, Kofu, Japan.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Chen, L., Wang, Y., Wu, W., Zhu, Z., Mao, X., & Chen, X. (2026). Children's dental panoramic radiograph image segmentation via dual aggregation transformer UNet. Medical Physics. https://doi.org/10.1002/mp.70202

Vancouver

Chen L, Wang Y, Wu W, Zhu Z, Mao X, Chen X. Children's dental panoramic radiograph image segmentation via dual aggregation transformer UNet. Medical Physics. 2026. doi:10.1002/mp.70202

BibTeX
@article{Chen2026,
  author = {Chen, Lingxiao and Wang, Yaqi and Wu, Wen and Zhu, Zhenyang and Mao, Xiaoyang and Chen, Xiaodiao},
  title = {Children's dental panoramic radiograph image segmentation via dual aggregation transformer UNet},
  journal = {Medical Physics},
  year = {2026},
  doi = {10.1002/mp.70202}
}
Kostenlos starten →