TUHH Open Research
Help
New user? Click here to register.Have you forgotten your password?
Communities & Collections
Publications
Research Data
People
Institutions
Projects
  1. Home
  2. Publications
  3. Publication References
  4. Automated estimation of anatomical risk metrics for endoscopic sinus surgery using deep learning

Automated estimation of anatomical risk metrics for endoscopic sinus surgery using deep learning

Publikationstyp
Conference Paper
Date Issued
2026-04-02
Sprache
English
Author(s)
Reuter, Konrad
Medizintechnische und Intelligente Systeme E-1
Thaysen, Lennart
Medizintechnische und Intelligente Systeme E-1
Doruk, Bilkay
Latus, Sarah
Medizintechnische und Intelligente Systeme E-1
Holst, Brigitte
Becker, Benjamin Tobias
Eggert, Dennis
Betz, Christian Stephan
Hoffmann, Anna Sophie
Schlaefer, Alexander
Medizintechnische und Intelligente Systeme E-1
Editor(s)
Thomas M. Deserno
Axel Wismüller
TORE-URI
https://hdl.handle.net/11420/63196
First published in
Proceedings of SPIE
Number in series
13926
Citation
SPIE Medical Imaging 2026
Contribution to Conference
SPIE Medical Imaging 2026
Publisher DOI
10.1117/12.3087376
Scopus ID
2-s2.0-105041255162
Publisher
SPIE
Endoscopic sinus surgery requires careful preoperative assessment of the skull base anatomy to minimize risks such as cerebrospinal fluid leakage. Anatomical risk scores like the Keros, Gera and Thailand-Malaysia-Singapore score offer a standardized approach but require time-consuming manual measurements on coronal CT or CBCT scans. We propose an automated deep learning pipeline that estimates these risk scores by localizing key anatomical landmarks via heatmap regression. We compare a direct approach to a specialized global-to-local learning strategy and find mean absolute errors on the relevant anatomical measurements as low as 0.506 mm for the Keros, 4.516° for the Gera and 0.802 mm/0.777 mm for the TMS classification, each corresponding to the best-performing model for the respective measurement.
DDC Class
620: Engineering
Funding(s)
Centre of Excellence of Al for Sustainable Living and Working
TUHH
Weiterführende Links
  • Contact
  • Send Feedback
  • Cookie settings
  • Privacy policy
  • Impress
DSpace Software

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science
Design by effective webwork GmbH

  • Deutsche NationalbibliothekDeutsche Nationalbibliothek
  • ORCiD Member OrganizationORCiD Member Organization
  • DataCiteDataCite
  • Re3DataRe3Data
  • OpenDOAROpenDOAR
  • OpenAireOpenAire
  • BASE Bielefeld Academic Search EngineBASE Bielefeld Academic Search Engine
Feedback