Automatic segmentation and landmark detection of 3D CBCT images using semi supervised learning for assisting orthognathic surgery planning
Abstract Patients with abnormal relative position of the upper and lower jaws (the main part of the facial bones) require orthognathic surgery to improve the occlusal relationship and facial appearance. However, in addition to the retraction and protrusion of the maxillomandibular advancement, these...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-03-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-93317-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849774762746707968 |
|---|---|
| author | Haomin Tang Shu Liu Yongxin Shi Jin Wei Juxiang Peng Hongchao Feng |
| author_facet | Haomin Tang Shu Liu Yongxin Shi Jin Wei Juxiang Peng Hongchao Feng |
| author_sort | Haomin Tang |
| collection | DOAJ |
| description | Abstract Patients with abnormal relative position of the upper and lower jaws (the main part of the facial bones) require orthognathic surgery to improve the occlusal relationship and facial appearance. However, in addition to the retraction and protrusion of the maxillomandibular advancement, these patients may also develop asymmetry. This study aims to use a semi-supervised learning method to demonstrate the maxillary and mandible retraction, protrudation and asymmetry of patients before orthognathic surgery through automatic segmentation of 3D cone beam computed tomography (CBCT) images and landmark detection, so as to provide help for the preoperative planning of orthognathic surgery. Among them, the dice of the semi-supervised algorithm adopted in this study reached 93.41 and 96.89% in maxillary and mandibular segmentation tasks, and the average error of landmark detection tasks reached 1.908 ± 1.166 mm, both of which were superior to the full-supervised algorithm with the same data volume annotation. Therefore, we propose that the method can be applied in a clinical setting to assist surgeons in preoperative planning for orthognathic surgery. |
| format | Article |
| id | doaj-art-2377dfe4132a4eae9dd02a7a8ee1ccb1 |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-2377dfe4132a4eae9dd02a7a8ee1ccb12025-08-20T03:01:37ZengNature PortfolioScientific Reports2045-23222025-03-0115111510.1038/s41598-025-93317-6Automatic segmentation and landmark detection of 3D CBCT images using semi supervised learning for assisting orthognathic surgery planningHaomin Tang0Shu Liu1Yongxin Shi2Jin Wei3Juxiang Peng4Hongchao Feng5College of Medicine, Guizhou UniversityDepartment of Orthodontics, Guiyang Hospital of StomatologySchool of Stomatology, Zunyi Medical UniversityDepartment of Oral and Maxillofacial Surgery, Guiyang Hospital of StomatologyDepartment of Orthodontics, Guiyang Hospital of StomatologyDepartment of Oral and Maxillofacial Surgery, Guiyang Hospital of StomatologyAbstract Patients with abnormal relative position of the upper and lower jaws (the main part of the facial bones) require orthognathic surgery to improve the occlusal relationship and facial appearance. However, in addition to the retraction and protrusion of the maxillomandibular advancement, these patients may also develop asymmetry. This study aims to use a semi-supervised learning method to demonstrate the maxillary and mandible retraction, protrudation and asymmetry of patients before orthognathic surgery through automatic segmentation of 3D cone beam computed tomography (CBCT) images and landmark detection, so as to provide help for the preoperative planning of orthognathic surgery. Among them, the dice of the semi-supervised algorithm adopted in this study reached 93.41 and 96.89% in maxillary and mandibular segmentation tasks, and the average error of landmark detection tasks reached 1.908 ± 1.166 mm, both of which were superior to the full-supervised algorithm with the same data volume annotation. Therefore, we propose that the method can be applied in a clinical setting to assist surgeons in preoperative planning for orthognathic surgery.https://doi.org/10.1038/s41598-025-93317-6Upper and lower jawsOrthognathic surgerySemi-supervised learningAutomatic segmentationAutomatic landmark detection3D CBCT |
| spellingShingle | Haomin Tang Shu Liu Yongxin Shi Jin Wei Juxiang Peng Hongchao Feng Automatic segmentation and landmark detection of 3D CBCT images using semi supervised learning for assisting orthognathic surgery planning Scientific Reports Upper and lower jaws Orthognathic surgery Semi-supervised learning Automatic segmentation Automatic landmark detection 3D CBCT |
| title | Automatic segmentation and landmark detection of 3D CBCT images using semi supervised learning for assisting orthognathic surgery planning |
| title_full | Automatic segmentation and landmark detection of 3D CBCT images using semi supervised learning for assisting orthognathic surgery planning |
| title_fullStr | Automatic segmentation and landmark detection of 3D CBCT images using semi supervised learning for assisting orthognathic surgery planning |
| title_full_unstemmed | Automatic segmentation and landmark detection of 3D CBCT images using semi supervised learning for assisting orthognathic surgery planning |
| title_short | Automatic segmentation and landmark detection of 3D CBCT images using semi supervised learning for assisting orthognathic surgery planning |
| title_sort | automatic segmentation and landmark detection of 3d cbct images using semi supervised learning for assisting orthognathic surgery planning |
| topic | Upper and lower jaws Orthognathic surgery Semi-supervised learning Automatic segmentation Automatic landmark detection 3D CBCT |
| url | https://doi.org/10.1038/s41598-025-93317-6 |
| work_keys_str_mv | AT haomintang automaticsegmentationandlandmarkdetectionof3dcbctimagesusingsemisupervisedlearningforassistingorthognathicsurgeryplanning AT shuliu automaticsegmentationandlandmarkdetectionof3dcbctimagesusingsemisupervisedlearningforassistingorthognathicsurgeryplanning AT yongxinshi automaticsegmentationandlandmarkdetectionof3dcbctimagesusingsemisupervisedlearningforassistingorthognathicsurgeryplanning AT jinwei automaticsegmentationandlandmarkdetectionof3dcbctimagesusingsemisupervisedlearningforassistingorthognathicsurgeryplanning AT juxiangpeng automaticsegmentationandlandmarkdetectionof3dcbctimagesusingsemisupervisedlearningforassistingorthognathicsurgeryplanning AT hongchaofeng automaticsegmentationandlandmarkdetectionof3dcbctimagesusingsemisupervisedlearningforassistingorthognathicsurgeryplanning |