An attention-based transfer learning model for diagnosing subluxation in temporomandibular joint panoramic radiographs

Yasin Sancar, Isil Karabey Aksakalli, Ozlem Sokmen, Hande Barin, Kubra Torenek-Agirman · 2025

Read An attention-based transfer learning model for diagnosing subluxation in temporomandibular joint panoramic radiographs by Yasin Sancar, Isil Karabey Aksakalli, Ozlem Sokmen, Hande Barin, Kubra Torenek-Agirman (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-12789688.txt.

Description

Yasin Sancar and four co-authors teach a computer model to spot jaw joint slippage on dental X-rays in a 2025 paper. The joint sits just in front of the ear, and its partial dislocation can cause pain and clicking.

The team built a public set of 3,425 labelled panoramic images of the joint. They trained seven ready-made image models on it and compared the results. The best base model was then given an attention feature, which lets it weigh the most telling parts of the image. The upgraded model reached about 91 percent accuracy across all measures. It beat every base model on the combined score. The authors offer the system as support for dentists making diagnoses.

Catalog record

CREATORYasin Sancar, Isil Karabey Aksakalli, Ozlem Sokmen, Hande Barin, Kubra Torenek-Agirman
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE41 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC12789688

Browse the full library · About the Tower of Babel