Geometry-biased transformer for dental caries detection in panoramic X-ray images

Journal Article (2026)
Author(s)

Nima Esmi (University Medical Center Groningen, Khazar University)

Koosha Refahi (University of Guilan)

Asadollah Shahbahrami (Khazar University, University of Guilan)

Negar Khosravifard (Dental Sciences Research Center (GUMS))

Georgi Gaydadjiev (TU Delft - Computer Engineering)

DOI related publication
https://doi.org/10.1007/s00521-026-11939-x Final published version
More Info
expand_more
Publication Year
2026
Language
English
Journal title
Neural Computing and Applications
Issue number
6
Volume number
38
Article number
186
Downloads counter
3
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Panoramic X-ray images are essential for dental caries detection, yet they inherently suffer from geometric distortions that complicate accurate early diagnosis. To address this, we propose a Geometry-Biased transformer that explicitly models spherical geometry. Our approach integrates equirectangular relative position embedding, distance-based attention scoring, and equirectangular-aware attention rearrangement to significantly enhance spatial feature representation. This enables the model to effectively capture both local caries lesions and global dental arch structures despite distortions. We rigorously evaluated our model primarily on a hospital-scale dataset, achieving a high accuracy of 94.90% and an AUC of 0.9603. Furthermore, extensive comparative analyses across diverse publicly available dental image datasets demonstrate the superior generalization and competitive performance of our method. Our findings highlight that geometry-aware transformers offer a robust and automated tool, revolutionizing high-precision dental caries detection and potentially other medical imaging diagnostics.

Files

S00521-026-11939-x.pdf
(pdf | 1.87 Mb)
Taverne
warning

File under embargo until 21-09-2026