Restoration of missing regions in limited field of view computer tomography using an image- and sinogram-based conditional generative adversarial network model
BJR|Artificial Intelligence · 23.01.2026 · 3 (1)
DOI: 10.1093/bjrai/ubag010 ↗Kurz gefasst
Fachartikel in der Zeitschrift BJR|Artificial Intelligence, online erschienen am 04.05.2026. Verfasst von Hideaki Hirashima und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiation Oncology and Image-Applied Therapy, Graduate School of Medicine, Kyoto University, Sakyo-ku, Kyoto 606-8507, Japan. Die Arbeit nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: JSPS KAKENHI.
Abstract (Originalsprache)
Objectives
This study aimed to restore missing regions from the limited field of view (FOV) using image- and sinogram-based conditional GAN (cGAN) models. Methods cGANs are deep learning frameworks that generate realistic data via a competitive neural network process. We used planning CT (pCT) datasets from 96 patients: 64 for training, 16 for validation, and 16 for internal testing. Two cGAN models (image-based and sinogram-based) were developed to generate body contour outside the FOV. Next, 23 cone-beam CT (CBCT) datasets were evaluated as an external test group.
Results
In pCT internal test datasets, the median values for mean absolute error (MAE), root mean square error (RMSE), and structural similarity index measure (SSIM) for each model were as follows: image-based model—101.73 HU for MAE, 39.26 HU for RMSE, and 0.83 for SSIM; sinogram-based model—16.91 HU for MAE, 23.19 HU for RMSE, and 0.91 for SSIM. In CBCT external test datasets, the sinogram-based model outperformed the image-based model with a median MAE of 73.32 HU versus 180.72 HU, a median RMSE of 37.02 HU versus 43.42 HU, and a median SSIM of 0.75 versus 0.63. The sinogram-based model demonstrated significant improvements in MAE, RMSE, and SSIM (P < .05).
Conclusions
The sinogram-based cGAN model exhibits considerable potential for restoring missing regions outside the FOV, outperforming the image-based model in accuracy metrics. Advances in knowledge This model offers a novel approach to accurately predict missing regions from a limited FOV, enhancing continuity of the body contour while accommodating patient-specific variations.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiation Oncology and Image-Applied Therapy, Graduate School of Medicine, Kyoto University, Sakyo-ku, Kyoto 606-8507, Japan.
- Department of Advanced Medical Physics, Graduate School of Medicine, Kyoto University, Sakyo-ku, Kyoto 606-8507, Japan.
- Department of Biomedical Engineering and Intelligence, Graduate School of Medicine, Kyoto University, Sakyo-ku, Kyoto 606-8507, Japan.
ORCID-Profile: Hideaki Hirashima, Takashi Mizowaki, Mitsuhiro Nakamura
Förderung
- JSPS KAKENHI
Zitieren
APA
Hirashima, H., Arimoto, K., Onishi, T., Nakao, M., Mizowaki, T., & Nakamura, M. (2026). Restoration of missing regions in limited field of view computer tomography using an image- and sinogram-based conditional generative adversarial network model. BJR|Artificial Intelligence, 3(1). https://doi.org/10.1093/bjrai/ubag010
Vancouver
Hirashima H, Arimoto K, Onishi T, Nakao M, Mizowaki T, Nakamura M. Restoration of missing regions in limited field of view computer tomography using an image- and sinogram-based conditional generative adversarial network model. BJR|Artificial Intelligence. 2026;3(1). doi:10.1093/bjrai/ubag010
BibTeX
@article{Hirashima2026,
author = {Hirashima, Hideaki and Arimoto, Kohei and Onishi, Takao and Nakao, Megumi and Mizowaki, Takashi and Nakamura, Mitsuhiro},
title = {Restoration of missing regions in limited field of view computer tomography using an image- and sinogram-based conditional generative adversarial network model},
journal = {BJR|Artificial Intelligence},
year = {2026},
volume = {3},
number = {1},
doi = {10.1093/bjrai/ubag010}
}
EUVIMED