Unsupervised deep learning‐based 4DCT deformable image registration and carbon‐ion 4D dose calculation
Medical Physics · 2026
DOI: 10.1002/mp.70387 ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical Physics, 2026. Verfasst von Xiaoyan An und 11 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Modern Physics, Chinese Academy of Sciences, Lanzhou, China. Hauptthemen laut MEDLINE: Four-Dimensional Computed Tomography, Deep Learning, Heavy Ion Radiotherapy, Radiation Dosage. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 25 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Youth Innovation Promotion Association, Chinese Academy of Sciences, Natural Science Foundation of Gansu Province.
Abstract (Originalsprache)
Background
Accurate four‐dimensional dose calculation (4DDC) is essential for carbon‐ion lung radiotherapy and relies on deformable image registration (DIR). However, conventional DIR methods are computationally intensive, hindering the implementation of online adaptive workflows.
Purpose
This study investigates the feasibility and efficacy of unsupervised deep learning‐based DIR models, TransMatch and VoxelMorph, in accelerating clinical lung four‐dimensional computed tomography (4DCT) registration and facilitating accurate carbon‐ion 4D dose calculation.
Methods
A total of 150 clinical lung 4DCT datasets were utilized (120 for training, 20 for validation, and 10 for testing), with a conventional B‐spline method serving as the baseline. Registration accuracy was evaluated using the Mean Absolute Error (MAE), Dice Similarity Coefficient (DSC), 95th percentile Hausdorff Distance (HD95), and Jacobian determinant (| J |). Carbon‐ion 4D dose distributions were accumulated using the generated deformation vector fields (DVFs). Dosimetric impacts on the gross tumor volume (GTV) and organs at risk (OARs) were quantified using Dose‐Volume Histogram (DVH) metrics under a gating with 6× rescanning scenario.
Results
TransMatch and VoxelMorph achieved superior registration accuracy with lower MAE, mean DSC > 0.97, and HD95 < 2.5 mm. In DVF analysis, TransMatch and VoxelMorph showed negligible folding rates (
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Modern Physics, Chinese Academy of Sciences, Lanzhou, China.
- Key Laboratory of Heavy Ion Radiation Biology and Medicine of Chinese Academy of Sciences, Lanzhou, China.
- Key Laboratory of Basic Research on Heavy Ion Radiation Application in Medicine, Lanzhou, Gansu Province, China.
- School of Nuclear Science and Technology, Lanzhou University, Lanzhou, China.
- School of Future Technology, Xi'an Jiaotong University, Xi'an, China.
- University of Chinese Academy of Sciences, Beijing, China.
Förderung
- National Natural Science Foundation of China
- Youth Innovation Promotion Association, Chinese Academy of Sciences
- Natural Science Foundation of Gansu Province
- Youth Innovation Promotion Association of the Chinese Academy of Sciences
Zitieren
APA
An, X., Wang, J., Zhang, J., Liu, Y., Abuduxiku, M., Chai, N., Luo, Y., Wu, W., Hu, Y., Hei, D., Li, Q., & He, P. (2026). Unsupervised deep learning‐based 4DCT deformable image registration and carbon‐ion 4D dose calculation. Medical Physics. https://doi.org/10.1002/mp.70387
Vancouver
An X, Wang J, Zhang J, Liu Y, Abuduxiku M, Chai N, et al. Unsupervised deep learning‐based 4DCT deformable image registration and carbon‐ion 4D dose calculation. Medical Physics. 2026. doi:10.1002/mp.70387
BibTeX
@article{An2026,
author = {An, Xiaoyan and Wang, Jian and Zhang, Jun and Liu, Yinuo and Abuduxiku, Maidina and Chai, Ningning and Luo, Ying and Wu, Wei and Hu, Yang and Hei, Daqian and Li, Qiang and He, Pengbo},
title = {Unsupervised deep learning‐based 4DCT deformable image registration and carbon‐ion 4D dose calculation},
journal = {Medical Physics},
year = {2026},
doi = {10.1002/mp.70387}
}
EUVIMED