EUVIMEDEUVIMED entdecken
ValidierungsstudieVergleichsstudie

Dental midline localization: development and validation of an automated deep learning pipeline

Arda Arısan iD, Gökhan Serhat Duran iD

European Journal of Orthodontics · 02.06.2026 · 48 (4)

DOI: 10.1093/ejo/cjag056 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift European Journal of Orthodontics, online erschienen am 29.07.2026. Verfasst von Arda Arısan und 1 weiteren Autor:innen. Beteiligte Einrichtung: Independent Researcher, Ankara 06510, Turkey. Hauptthemen laut MEDLINE: Deep Learning, Smiling. Die Arbeit nennt 30 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

To develop and validate an automated pipeline for maxillary dental midline localization on posed smile photographs and compare the performance of four convolutional neural network (CNN) backbones. Materials and Methods A total of 221 standardized frontal posed smile photographs were collected. The maxillary dental midline was annotated by two orthodontists across two sessions, and mean coordinates served as the orthodontist-derived reference standard. An automated pipeline including face detection, interpupillary-line rotational normalization, mouth region extraction, and CNN-based keypoint regression was developed. Four CNN models (EfficientNet-B0, ResNet-18, MobileNetV3-Small, and HRNet-W18) were trained and compared using 5-fold stratified cross-validation. Deviation was expressed as the angle between the predicted dental midline and the interpupillary-derived photographic reference line (T-line).

Results

HRNet-W18 achieved the lowest mean angular error (0.63° ± 0.63°) and the highest ≤1° error-threshold accuracy (81.0%). All 4 models exceeded 90% accuracy at the ≤2° threshold. No significant effect of tooth visibility grade on angular error was observed. HRNet-W18 also showed the highest agreement with the reference standard [intraclass correlation coefficient (ICC) = 0.721] and minimal Bland–Altman bias (+0.03°). Post hoc pairwise comparisons showed that HRNet-W18 outperformed all other models across all error metrics.

Limitations

The sample was limited to standardized posed smile photographs from a single center, and generalizability to diverse populations and less controlled conditions remains to be established. Conclusions and Implications The automated pipeline showed high accuracy for dental midline localization on posed smile photographs relative to an orthodontist-derived reference standard. Further validation on larger and more diverse datasets is needed before clinical application.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningSmilingHumansConvolutional Neural NetworksImage Processing, Computer-AssistedPhotography, DentalMaxillaDetection AlgorithmsReproducibility of ResultsAnatomic LandmarksOrthodontistsFace

Stichwörter der Autor:innen

automated detectiondeep learningdental midlinedental midline asymmetry

Autor:innen und Institutionen

  • Independent Researcher, Ankara 06510, Turkey.
  • Department of Orthodontics, Faculty of Dentistry, Çanakkale Onsekiz Mart University, Çanakkale 17100, Turkey.

ORCID-Profile: Arda Arısan, Gökhan Serhat Duran

Zitieren

APA

Arısan, A., & Duran, G. S. (2026). Dental midline localization: development and validation of an automated deep learning pipeline. European Journal of Orthodontics, 48(4). https://doi.org/10.1093/ejo/cjag056

Vancouver

Arısan A, Duran GS. Dental midline localization: development and validation of an automated deep learning pipeline. European Journal of Orthodontics. 2026;48(4). doi:10.1093/ejo/cjag056

BibTeX
@article{Arsan2026,
  author = {Arısan, Arda and Duran, Gökhan Serhat},
  title = {Dental midline localization: development and validation of an automated deep learning pipeline},
  journal = {European Journal of Orthodontics},
  year = {2026},
  volume = {48},
  number = {4},
  doi = {10.1093/ejo/cjag056}
}
Kostenlos starten →