• Transfer learning for DL-based...

Treffer: Transfer learning for DL-based Synthetic CT after reconstruction algorithm upgrade in a proton therapy clinic

Title:
Transfer learning for DL-based Synthetic CT after reconstruction algorithm upgrade in a proton therapy clinic
Authors:
Galapon, Arthur, Wagenaar, Dirk, Langendijk, Johannes Albertus, Both, Stefan
Source:
Galapon, A, Wagenaar, D, Langendijk, J A & Both, S 2025, 'Transfer learning for DL-based Synthetic CT after reconstruction algorithm upgrade in a proton therapy clinic', Medical Physics, vol. 52, no. 7, e17937. https://doi.org/10.1002/mp.17937
Publication Year:
2025
Collection:
University of Groningen research database
Subject Terms:
Image Processing, Computer-Assisted/methods, Humans, Proton Therapy, Deep Learning, Tomography, X-Ray Computed, Head and Neck Neoplasms/diagnostic imaging
Document Type:
Fachzeitschrift article in journal/newspaper
File Description:
application/pdf
Language:
English
Relation:
info:eu-repo/semantics/altIdentifier/pmid/40660869; info:eu-repo/semantics/altIdentifier/hdl/https://hdl.handle.net/11370/dd81f84b-9ab5-4f48-bb8d-3d2813555e71; info:eu-repo/semantics/altIdentifier/pissn/0094-2405
DOI:
10.1002/mp.17937
Availability:
https://hdl.handle.net/11370/dd81f84b-9ab5-4f48-bb8d-3d2813555e71
https://research.rug.nl/en/publications/dd81f84b-9ab5-4f48-bb8d-3d2813555e71
https://doi.org/10.1002/mp.17937
https://pure.rug.nl/ws/files/1351772067/Medical_Physics_-_2025_-_Galapon_-_Transfer_learning_for_DL_based_Synthetic_CT_after_reconstruction_algorithm_upgrade_in_a.pdf
Rights:
info:eu-repo/semantics/openAccess ; http://creativecommons.org/licenses/by-nc/4.0/
Accession Number:
edsbas.7B37D897
Database:
BASE

Weitere Informationen

BACKGROUND: Synthetic computed tomography (sCT) images generated using deep learning (DL) methods enable the use of on-board CBCT imaging systems for online adaptive proton therapy workflows. However, DL models are susceptible to data drifts, such as changes in the quality of the CBCT images due to software upgrades. PURPOSE: This study aims to assess the effectiveness of transfer learning strategies in addressing changes in the input image quality and to evaluate the sustainability of potential sCT-dependent workflows following CBCT software upgrades. METHOD: Transfer learning strategies were utilized to re-train two existing DL-based sCT models (DCNN and cycleGAN). A dataset comprised 69 head and neck (HNC) patients with paired CBCT-CT images acquired after an image reconstruction software upgrade were used for this study. 60 patients were used for training and validation, and the remaining 9 were reserved for testing. To assess the efficacy of transfer learning strategies, several transfer learning models (TL-models) were trained using various subsets of data, ranging from 5 to 40 image pairs. Additionally, a post-upgrade sCT (New(PU)) model was trained utilizing the complete set of 60 patients to benchmark the TL-models to a post-upgrade-trained model. The synthetic CTs generated from the test set were evaluated using established image quality metrics. Furthermore, dosimetric accuracy was assessed using the patient's clinical treatment plan and our existing clinical NTCP models. RESULTS: Comparison of the average mean absolute error (MAE) between the baseline pre- and post-upgrade (PU) models shows no significant difference. The baseline model exhibited an average MAE of 81.46 ± 49.0 HU and 86.25 ± 14.49 HU for DCNN and cycleGAN, respectively. The TL-05 model demonstrated an average MAE of 69.85 ± 5.9 HU and 95.0 ± 10.95 HU, while the post-upgrade new model had an average MAE of 74.4 ± 12.42 HU and 65.32 ± 10.36 HU for DCNN and cycleGAN, respectively. Additionally, dosimetric quantities showed no significant ...