Accuracy of an articulated head-and-neck motion model using deep learning-based instance segmentation of skeletal bones in CT scans for image registration in radiotherapy

Knowing about anatomical deformations in patient images is crucial for adaptive image-guided radiation therapy. Biomechanical models ensure biofidelity in deformable image registration, but manual contouring limits their clinical use. We investigate the application of automatically generated contour...

Full description

Saved in:
Bibliographic Details
Main Authors: Alexandra Walter, Cornelius J. Bauer, Ama Katseena Yawson, Philipp Hoegen-Saßmannshausen, Sebastian Adeberg, Jürgen Debus, Oliver Jäkel, Martin Frank, Kristina Giske
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Series:Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/21681163.2025.2455752
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832585143946051584
author Alexandra Walter
Cornelius J. Bauer
Ama Katseena Yawson
Philipp Hoegen-Saßmannshausen
Sebastian Adeberg
Jürgen Debus
Oliver Jäkel
Martin Frank
Kristina Giske
author_facet Alexandra Walter
Cornelius J. Bauer
Ama Katseena Yawson
Philipp Hoegen-Saßmannshausen
Sebastian Adeberg
Jürgen Debus
Oliver Jäkel
Martin Frank
Kristina Giske
author_sort Alexandra Walter
collection DOAJ
description Knowing about anatomical deformations in patient images is crucial for adaptive image-guided radiation therapy. Biomechanical models ensure biofidelity in deformable image registration, but manual contouring limits their clinical use. We investigate the application of automatically generated contours for a biomechanical registration model in head and neck cancer treatment. For that, we automatically generate individual bone segmentations on planning CT scans examining a custom-trained nnU-Net model and the ready-trained TotalSegmentator model. Both sets of segmentations are evaluated using DICE, Hausdorff Distance and surface DICE. We investigate their impact on the build-up of the biomechanical articulated skeleton model by deviations in joint positioning and CT-CT registration accuracy using target registration error (TRE). The custom-trained model achieves 1.51 ± 0.26 mm TRE, with no significant difference in registration accuracy. While the TotalSegmentator does not provide all structures needed for the complete biomechanical model build-up. Overall, deep learning–based automatic bone segmentation can replace manual contouring in this model, matching its performance.
format Article
id doaj-art-9a44d996b80646578cba0afb9b5d363f
institution Kabale University
issn 2168-1163
2168-1171
language English
publishDate 2025-12-01
publisher Taylor & Francis Group
record_format Article
series Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization
spelling doaj-art-9a44d996b80646578cba0afb9b5d363f2025-01-27T00:23:21ZengTaylor & Francis GroupComputer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization2168-11632168-11712025-12-0113110.1080/21681163.2025.2455752Accuracy of an articulated head-and-neck motion model using deep learning-based instance segmentation of skeletal bones in CT scans for image registration in radiotherapyAlexandra Walter0Cornelius J. Bauer1Ama Katseena Yawson2Philipp Hoegen-Saßmannshausen3Sebastian Adeberg4Jürgen Debus5Oliver Jäkel6Martin Frank7Kristina Giske8Division of Medical Physics in Radiation Oncology, German Cancer Research Center (DKFZ), Heidelberg, GermanyDivision of Medical Physics in Radiation Oncology, German Cancer Research Center (DKFZ), Heidelberg, GermanyDivision of Medical Physics in Radiation Oncology, German Cancer Research Center (DKFZ), Heidelberg, GermanyDivision of Medical Physics in Radiation Oncology, German Cancer Research Center (DKFZ), Heidelberg, GermanyDepartment of Radiation Oncology, UKGM Marburg, Marburg, GermanyDepartment of Radiation Oncology, Heidelberg University Hospital, Heidelberg, GermanyDivision of Medical Physics in Radiation Oncology, German Cancer Research Center (DKFZ), Heidelberg, GermanyScientific Computing Center, Karlsruhe Institute of Technology (KIT), Karlsruhe, GermanyDivision of Medical Physics in Radiation Oncology, German Cancer Research Center (DKFZ), Heidelberg, GermanyKnowing about anatomical deformations in patient images is crucial for adaptive image-guided radiation therapy. Biomechanical models ensure biofidelity in deformable image registration, but manual contouring limits their clinical use. We investigate the application of automatically generated contours for a biomechanical registration model in head and neck cancer treatment. For that, we automatically generate individual bone segmentations on planning CT scans examining a custom-trained nnU-Net model and the ready-trained TotalSegmentator model. Both sets of segmentations are evaluated using DICE, Hausdorff Distance and surface DICE. We investigate their impact on the build-up of the biomechanical articulated skeleton model by deviations in joint positioning and CT-CT registration accuracy using target registration error (TRE). The custom-trained model achieves 1.51 ± 0.26 mm TRE, with no significant difference in registration accuracy. While the TotalSegmentator does not provide all structures needed for the complete biomechanical model build-up. Overall, deep learning–based automatic bone segmentation can replace manual contouring in this model, matching its performance.https://www.tandfonline.com/doi/10.1080/21681163.2025.2455752Biomechanical modellingbiofidelityimage registrationhead and neck cancermedical image segmentation
spellingShingle Alexandra Walter
Cornelius J. Bauer
Ama Katseena Yawson
Philipp Hoegen-Saßmannshausen
Sebastian Adeberg
Jürgen Debus
Oliver Jäkel
Martin Frank
Kristina Giske
Accuracy of an articulated head-and-neck motion model using deep learning-based instance segmentation of skeletal bones in CT scans for image registration in radiotherapy
Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization
Biomechanical modelling
biofidelity
image registration
head and neck cancer
medical image segmentation
title Accuracy of an articulated head-and-neck motion model using deep learning-based instance segmentation of skeletal bones in CT scans for image registration in radiotherapy
title_full Accuracy of an articulated head-and-neck motion model using deep learning-based instance segmentation of skeletal bones in CT scans for image registration in radiotherapy
title_fullStr Accuracy of an articulated head-and-neck motion model using deep learning-based instance segmentation of skeletal bones in CT scans for image registration in radiotherapy
title_full_unstemmed Accuracy of an articulated head-and-neck motion model using deep learning-based instance segmentation of skeletal bones in CT scans for image registration in radiotherapy
title_short Accuracy of an articulated head-and-neck motion model using deep learning-based instance segmentation of skeletal bones in CT scans for image registration in radiotherapy
title_sort accuracy of an articulated head and neck motion model using deep learning based instance segmentation of skeletal bones in ct scans for image registration in radiotherapy
topic Biomechanical modelling
biofidelity
image registration
head and neck cancer
medical image segmentation
url https://www.tandfonline.com/doi/10.1080/21681163.2025.2455752
work_keys_str_mv AT alexandrawalter accuracyofanarticulatedheadandneckmotionmodelusingdeeplearningbasedinstancesegmentationofskeletalbonesinctscansforimageregistrationinradiotherapy
AT corneliusjbauer accuracyofanarticulatedheadandneckmotionmodelusingdeeplearningbasedinstancesegmentationofskeletalbonesinctscansforimageregistrationinradiotherapy
AT amakatseenayawson accuracyofanarticulatedheadandneckmotionmodelusingdeeplearningbasedinstancesegmentationofskeletalbonesinctscansforimageregistrationinradiotherapy
AT philipphoegensaßmannshausen accuracyofanarticulatedheadandneckmotionmodelusingdeeplearningbasedinstancesegmentationofskeletalbonesinctscansforimageregistrationinradiotherapy
AT sebastianadeberg accuracyofanarticulatedheadandneckmotionmodelusingdeeplearningbasedinstancesegmentationofskeletalbonesinctscansforimageregistrationinradiotherapy
AT jurgendebus accuracyofanarticulatedheadandneckmotionmodelusingdeeplearningbasedinstancesegmentationofskeletalbonesinctscansforimageregistrationinradiotherapy
AT oliverjakel accuracyofanarticulatedheadandneckmotionmodelusingdeeplearningbasedinstancesegmentationofskeletalbonesinctscansforimageregistrationinradiotherapy
AT martinfrank accuracyofanarticulatedheadandneckmotionmodelusingdeeplearningbasedinstancesegmentationofskeletalbonesinctscansforimageregistrationinradiotherapy
AT kristinagiske accuracyofanarticulatedheadandneckmotionmodelusingdeeplearningbasedinstancesegmentationofskeletalbonesinctscansforimageregistrationinradiotherapy