Saved in:
Bibliographic Details
Main Authors: Reuter, Konrad, Thaysen, Lennart, Doruk, Bilkay, Latus, Sarah, Holst, Brigitte, Becker, Benjamin, Eggert, Dennis, Betz, Christian, Hoffmann, Anna-Sophie, Schlaefer, Alexander
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.07199
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917071185510400
author Reuter, Konrad
Thaysen, Lennart
Doruk, Bilkay
Latus, Sarah
Holst, Brigitte
Becker, Benjamin
Eggert, Dennis
Betz, Christian
Hoffmann, Anna-Sophie
Schlaefer, Alexander
author_facet Reuter, Konrad
Thaysen, Lennart
Doruk, Bilkay
Latus, Sarah
Holst, Brigitte
Becker, Benjamin
Eggert, Dennis
Betz, Christian
Hoffmann, Anna-Sophie
Schlaefer, Alexander
contents 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 of 0.506mm for the Keros, 4.516° for the Gera and 0.802mm / 0.777mm for the TMS classification.
format Preprint
id arxiv_https___arxiv_org_abs_2511_07199
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Automated Estimation of Anatomical Risk Metrics for Endoscopic Sinus Surgery Using Deep Learning
Reuter, Konrad
Thaysen, Lennart
Doruk, Bilkay
Latus, Sarah
Holst, Brigitte
Becker, Benjamin
Eggert, Dennis
Betz, Christian
Hoffmann, Anna-Sophie
Schlaefer, Alexander
Computer Vision and Pattern Recognition
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 of 0.506mm for the Keros, 4.516° for the Gera and 0.802mm / 0.777mm for the TMS classification.
title Automated Estimation of Anatomical Risk Metrics for Endoscopic Sinus Surgery Using Deep Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.07199