Deep learning-based 3D automatic segmentation of impacted canines in CBCT scans
Türkan Ünal, Alican Kuran, Ibrahim Tevfik Gulsen, Fatma Nur Kızılay, Emine Gulsen, Semanur Özüdoğru, Kadir Gördeli, Ozer Celik, Mehmet Uğurlu, İbrahim Şevki Bayrakdar, Kaan Orhan · 2025
Read Deep learning-based 3D automatic segmentation of impacted canines in CBCT scans by Türkan Ünal, Alican Kuran, Ibrahim Tevfik Gulsen, Fatma Nur Kızılay, Emine Gulsen, Semanur Özüdoğru, Kadir Gördeli, Ozer Celik, Mehmet Uğurlu, İbrahim Şevki Bayrakdar, Kaan Orhan (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12723826.txt.
Description
Türkan Ünal and co-authors built a deep learning tool to outline trapped canine teeth in three-dimensional dental scans in 2025. Trapped canines are a common problem in jaw and face practice. Cone beam scans show them in detail, but hand outlining is slow and varies between readers.
The team gathered one hundred fifty-nine scans and marked the teeth with web-based software. They trained a well-known medical image network for many rounds at a low learning rate. The model found and outlined the teeth well, with strong recall and solid overlap scores against hand marks. Such a tool could speed planning for treatment of trapped teeth.
Catalog record
| CREATOR | Türkan Ünal, Alican Kuran, Ibrahim Tevfik Gulsen, Fatma Nur Kızılay, Emine Gulsen, Semanur Özüdoğru, Kadir Gördeli, Ozer Celik, Mehmet Uğurlu, İbrahim Şevki Bayrakdar, Kaan Orhan |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 42 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |