EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A deep learning framework for the localization of landmarks on the lateral semi circular canals

Zhixuan Wei iD, Sudanthi Wijewickrema iD, Bridget Copson, Jean-Marc Gerard, Stephen O'Leary

PLOS One · 12.05.2026 · 21 (5) · e0348976

DOI: 10.1371/journal.pone.0348976 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 12.05.2026. Verfasst von Zhixuan Wei und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Surgery (Otolarynglogy), University of Melbourne, Melbourne, Australia. Hauptthemen laut MEDLINE: Deep Learning, Semicircular Canals, Tomography, X-Ray Computed, Temporal Bone. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper introduces a Deep Learning (DL) framework to localize landmark coordinates within the semicircular canals in Computed Tomography (CT) scans of the temporal bone. These landmarks can be consistently defined across patients and imaging modalities and as such can serve as a means of forming a common coordinate system. We propose a DL based framework for automating the landmark selection process. We establish the accuracy of the methods using Bone Beam CT scans of the temporal bone of 20 patients and landmarks selected by 3 human experts as the ground truth. We show that the error rates are similar to the levels of variation in landmark selection achieved by human experts. We further validated the method on CT scans from 14 additional patients, demonstrating that the accuracy remains within clinically acceptable parameters.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningSemicircular CanalsTomography, X-Ray ComputedTemporal BoneAnatomic LandmarksHumansImage Processing, Computer-Assisted

Autor:innen und Institutionen

  • Department of Surgery (Otolarynglogy), University of Melbourne, Melbourne, Australia.
  • Australian Centre for Artificial Intelligence in Medical Innovation, La Trobe University, Melbourne, Australia.
  • Department of Radiology, St Vincent's Hospital, Melbourne, Australia.
  • Department of Otology, Royal Victorian Eye & Ear Hospital, Melbourne, Australia.

ORCID-Profile: Zhixuan Wei, Sudanthi Wijewickrema

Zitieren

APA

Wei, Z., Wijewickrema, S., Copson, B., Gerard, J. M., & O'Leary, S. (2026). A deep learning framework for the localization of landmarks on the lateral semi circular canals. PLOS One, 21(5), e0348976. https://doi.org/10.1371/journal.pone.0348976

Vancouver

Wei Z, Wijewickrema S, Copson B, Gerard JM, O'Leary S. A deep learning framework for the localization of landmarks on the lateral semi circular canals. PLOS One. 2026;21(5):e0348976. doi:10.1371/journal.pone.0348976

BibTeX
@article{Wei2026,
  author = {Wei, Zhixuan and Wijewickrema, Sudanthi and Copson, Bridget and Gerard, Jean-Marc and O'Leary, Stephen},
  title = {A deep learning framework for the localization of landmarks on the lateral semi circular canals},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {5},
  pages = {e0348976},
  doi = {10.1371/journal.pone.0348976}
}
Kostenlos starten →