Published April 18, 2023 | Version v1
Other Open

Semi-supervised Teeth Segmentation

Authors/Creators

  • 1. College of Media Engineering, Communication University of Zhejiang, China
  • 2. School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China
  • 3. College of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China
  • 4. School of Electronic Engineering and Computer Science, Queen Mary University of London, the United Kingdom
  • 5. Hangzhou Geriatric Stomatology Hospital, Hangzhou Dental Hospital Group, Division of Advanced Prosthetic Dentistry, Tohoku University Graduate School of Dentistry, State Key Laboratory of Oral Diseases, National Clinical Research Center for Oral Diseases, West China Hospital of Stomatology, Sichuan University, China
  • 6. School of Information and Communication Engineering, the University of Electronic Science and Technology of China, China
  • 7. School of Electronic Engineering and Computer Science, Queen Mary University of London, United Kingdom

Description

Computer-aided design (CAD) tools are increasingly popular in modern dental practice, particularly for treatment planning or comprehensive prognosis evaluation. In particular, the 2D panoramic X-ray image is an efficient way for dentists to determine invisible caries, impacted teeth and supernumerary teeth among children. Additionally,
the 3D dental cone-beam computed tomography (CBCT) examination has been widely applied in orthodontics and endodontics due to its low ray quantity. To the best of our knowledge, there is no open-access 2D public dataset for children’s teeth and no open 3D dental CBCT dataset, which limits the development of deep learning algorithms for segmenting teeth and automatically analyzing diseases.

The Semi-TeethSeg challenge will release more than 2,000 labelled panoramic X-ray images and 5,000 labelled CBCT slices to enable researchers to accurately segment teeth regions using deep-learning approaches. To encourage the study of tooth feature representation based on a large amount of raw dental data, we further release unlabelled 2D and 3D dental images including more than 1,000 panoramic X-ray images and 30,000 CBCT slices. Several robust semi-supervised-based tooth segmentation methods will be proposed via the Semi-TeethSeg challenge to facilitate the development of CAD-based dentistry.

Files

Semi-supervisedTeethSegmentation_04-18-2023_10-53-49.pdf

Files (2.7 MB)