Beyond 2D and CNNs: Future Directions for Deep Learning in Periodontal Diagnostics
Kaijie Meng, Shouyin Lv, Jingping Liu · 2026
Read Beyond 2D and CNNs: Future Directions for Deep Learning in Periodontal Diagnostics by Kaijie Meng, Shouyin Lv, Jingping Liu (2026) 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/PMC13273820.txt.
Description
Meng and colleagues write a 2026 letter to the editor about deep learning in gum disease diagnosis. The letter responds to a study by Valente and colleagues. That study used a YOLOv8l model to read dental images.
The writers praise the model's promise for periodontal diagnosis. Periodontal disease affects the gums and bone around teeth. They also raise concerns about class imbalance in training data. Rare disease stages may be underrepresented, skewing results. The letter points to Vision Transformers as another approach. It also urges combining images with other data types. Three-dimensional scans could add useful detail. The authors close with directions for stronger future studies.
Catalog record
| CREATOR | Kaijie Meng, Shouyin Lv, Jingping Liu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 3510 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |