GaryNico517 / TSG-GCN

Topology structure-guided graph convolutional network for pediatric teeth segmentation

Individual Graph Representation Learning for Pediatric Tooth Segmentation from Dental CBCT

By Yusheng Liu^a([e-mail]), Shu Zhang^b, Xiyi Wu^a, Tao Yang^a, Yuchen Pei^a, Huayan Guo^e, Yuxian Jiang^a, Zhien Feng^c, Wen Xiao^d, Yu-Ping Wang^e, and Lisheng Wang^a([e-mail])

a.Department of Automation, Shanghai Jiao Tong University, Shanghai 200240, People’s Republic of China.
b.Department of Pediatric Dentistry, Beijing Stomatological Hospital, Capital Medical University, Beijing 100050, China.
c.Department of Oral and Maxillofacial-Head and Neck Oncology, Beijing Stomatological Hospital, Capital Medical University, Beijing 100050, China.
d.Department of Pediatric Dentistry, Shanghai Ninth People’s Hospital, Shanghai 200011, China.
e.Department of Dentistry, Shanghai East Hospital Affiliated to Tongji University, Shanghai 200120, China.
f.The Biomedical Engineering Department, Tulane University, New Orleans, LA 70118 USA.

Introduction:

This repository is for our TMI submitting paper 'Individual Graph Representation Learning for Pediatric Tooth Segmentation from Dental CBCT'.

Supplemental Weight:

nnUNet-based

The training weights are for 1) Quadrant-wise Localization as well as 2) Tooth Segmentation on Quadrant-wise Data.
The dataset used for training is a publicly available teeth dataset, containing:
a) 76 CBCT images come from https://github.com/ErdanC/Tooth-and-alveolar-bone-segmentation-from-CBCT/
b) 63 CBCT images come from https://ditto.ing.unimore.it/toothfairy2/
You can easliy download the weights from https://drive.google.com/drive/folders/1-Kkm0C5huUZu_T04ciR5hRTn7G6lZbpd?usp=drive_link

More code will be uploaded soon.