Cover Image

Enhancing U-Net-based Pseudo-CT generation from MRI using CT-guided bone segmentation for radiation treatment planning in head & neck cancer patients

Objective. This study investigates the effects of various training protocols on enhancing the precision of MRI-only Pseudo-CT generation for radiation treatment planning and adaptation in head & neck cancer patients. It specifically tackles the challenge of differentiating bone from air, a limit...

Full description

Saved in:
Bibliographic Details
Main Authors: Yawson, Ama Katseena (Author) , Sallem, Habiba (Author) , Seidensaal, Katharina (Author) , Welzel, Thomas (Author) , Klüter, Sebastian (Author) , Paul, Katharina (Author) , Dorsch, Stefan (Author) , Beyer, Cedric (Author) , Debus, Jürgen (Author) , Jäkel, Oliver (Author) , Bauer, Julia (Author) , Giske, Kristina (Author)
Format: Article (Journal)
Language:English
Published: 12 February 2025
In: Physics in medicine and biology
Year: 2025, Volume: 70, Issue: 4, Pages: 1-14
ISSN:1361-6560
DOI:10.1088/1361-6560/adb124
Online Access:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1088/1361-6560/adb124
Verlag, lizenzpflichtig, Volltext: https://dx.doi.org/10.1088/1361-6560/adb124
Get full text
Author Notes:Ama Katseena Yawson, Habiba Sallem, Katharina Seidensaal, Thomas Welzel, Sebastian Klüter, Katharina Maria Paul, Stefan Dorsch, Cedric Beyer, Jürgen Debus, Oliver Jäkel, Julia Bauer and Kristina Giske
Description
Summary:Objective. This study investigates the effects of various training protocols on enhancing the precision of MRI-only Pseudo-CT generation for radiation treatment planning and adaptation in head & neck cancer patients. It specifically tackles the challenge of differentiating bone from air, a limitation that frequently results in substantial deviations in the representation of bony structures on Pseudo-CT images. Approach. The study included 25 patients, utilizing pre-treatment MRI-CT image pairs. Five cases were randomly selected for testing, with the remaining 20 used for model training and validation. A 3D U-Net deep learning model was employed, trained on patches of size 643 with an overlap of 323. MRI scans were acquired using the Dixon gradient echo (GRE) technique, and various contrasts were explored to improve Pseudo-CT accuracy, including in-phase, water-only, and combined water-only and fat-only images. Additionally, bone extraction from the fat-only image was integrated as an additional channel to better capture bone structures on Pseudo-CTs. The evaluation involved both image quality and dosimetric metrics. Main results. The generated Pseudo-CTs were compared with their corresponding registered target CTs. The mean absolute error (MAE) and peak signal-to-noise ratio (PSNR) for the base model using combined water-only and fat-only images were 19.20 ± 5.30 HU and 57.24 ± 1.44 dB, respectively. Following the integration of an additional channel using a CT-guided bone segmentation, the model’s performance improved, achieving MAE and PSNR of 18.32 ± 5.51 HU and 57.82 ± 1.31 dB, respectively. The measured results are statistically significant, with a p-value 0.05. The dosimetric assessment confirmed that radiation treatment planning on Pseudo-CT achieved accuracy comparable to conventional CT. Significance. This study demonstrates improved accuracy in bone representation on Pseudo-CTs achieved through a combination of water-only, fat-only and extracted bone images; thus, enhancing feasibility of MRI-based simulation for radiation treatment planning.
Item Description:Gesehen am 28.07.2025
Physical Description:Online Resource
ISSN:1361-6560
DOI:10.1088/1361-6560/adb124

Similar Items