CBCT-to-CT synthesis using a hybrid U-Net diffusion model based on transformers and information bottleneck theory

Abstract Cone-beam computed tomography (CBCT) scans are widely used for real time monitoring and patient positioning corrections in image-guided radiation therapy (IGRT), enhancing the precision of radiation treatment. However, compared to high-quality computed tomography (CT) images, CBCT images su...

Full description

Saved in:
Bibliographic Details
Main Authors: Can Hu, Ning Cao, Xiuhan Li, Yang He, Han Zhou
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-92094-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849392315972452352
author Can Hu
Ning Cao
Xiuhan Li
Yang He
Han Zhou
author_facet Can Hu
Ning Cao
Xiuhan Li
Yang He
Han Zhou
author_sort Can Hu
collection DOAJ
description Abstract Cone-beam computed tomography (CBCT) scans are widely used for real time monitoring and patient positioning corrections in image-guided radiation therapy (IGRT), enhancing the precision of radiation treatment. However, compared to high-quality computed tomography (CT) images, CBCT images suffer from severe artifacts and noise, which significantly hinder their application in IGRT. Therefore, synthesizing CBCT images into CT-like quality has become a critical necessity. In this study, we propose a hybrid U-Net diffusion model (HUDiff) based on Vision Transformer (ViT) and the information bottleneck theory to improve CBCT image quality. First, to address the limitations of the original U-Net in diffusion models, which primarily retain and transfer only local feature information, we introduce a ViT-based U-Net framework. By leveraging the self-attention mechanism, our model automatically focuses on different regions of the image during generation, aiming to better capture global features. Second, we incorporate a variational information bottleneck module at the base of the U-Net. This module filters out redundant and irrelevant information while compressing essential input data, thereby enabling more efficient summarization and better feature extraction. Finally, a dynamic modulation factor is introduced to balance the contributions of the main network and skip connections, optimizing the reverse denoising process in the diffusion model. We conducted extensive experiments on private Brain and Head & Neck datasets. The results, evaluated from multiple perspectives, demonstrate that our model outperforms state-of-the-art methods, validating its clinical applicability and robustness. In future clinical practice, our model has the potential to assist clinicians in formulating more precise radiation therapy plans.
format Article
id doaj-art-3db2385809ef4a1db9b8b16f5bf01983
institution Kabale University
issn 2045-2322
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-3db2385809ef4a1db9b8b16f5bf019832025-08-20T03:40:48ZengNature PortfolioScientific Reports2045-23222025-03-0115112110.1038/s41598-025-92094-6CBCT-to-CT synthesis using a hybrid U-Net diffusion model based on transformers and information bottleneck theoryCan Hu0Ning Cao1Xiuhan Li2Yang He3Han Zhou4School of Computer and Software, Hohai UniversitySchool of Computer and Software, Hohai UniversitySchool of Computer and Software, Hohai UniversitySchool of Computer and Software, Hohai UniversityDepartment of Radiation Oncology, The Fourth Affiliated Hospital of Nanjing Medical UniversityAbstract Cone-beam computed tomography (CBCT) scans are widely used for real time monitoring and patient positioning corrections in image-guided radiation therapy (IGRT), enhancing the precision of radiation treatment. However, compared to high-quality computed tomography (CT) images, CBCT images suffer from severe artifacts and noise, which significantly hinder their application in IGRT. Therefore, synthesizing CBCT images into CT-like quality has become a critical necessity. In this study, we propose a hybrid U-Net diffusion model (HUDiff) based on Vision Transformer (ViT) and the information bottleneck theory to improve CBCT image quality. First, to address the limitations of the original U-Net in diffusion models, which primarily retain and transfer only local feature information, we introduce a ViT-based U-Net framework. By leveraging the self-attention mechanism, our model automatically focuses on different regions of the image during generation, aiming to better capture global features. Second, we incorporate a variational information bottleneck module at the base of the U-Net. This module filters out redundant and irrelevant information while compressing essential input data, thereby enabling more efficient summarization and better feature extraction. Finally, a dynamic modulation factor is introduced to balance the contributions of the main network and skip connections, optimizing the reverse denoising process in the diffusion model. We conducted extensive experiments on private Brain and Head & Neck datasets. The results, evaluated from multiple perspectives, demonstrate that our model outperforms state-of-the-art methods, validating its clinical applicability and robustness. In future clinical practice, our model has the potential to assist clinicians in formulating more precise radiation therapy plans.https://doi.org/10.1038/s41598-025-92094-6
spellingShingle Can Hu
Ning Cao
Xiuhan Li
Yang He
Han Zhou
CBCT-to-CT synthesis using a hybrid U-Net diffusion model based on transformers and information bottleneck theory
Scientific Reports
title CBCT-to-CT synthesis using a hybrid U-Net diffusion model based on transformers and information bottleneck theory
title_full CBCT-to-CT synthesis using a hybrid U-Net diffusion model based on transformers and information bottleneck theory
title_fullStr CBCT-to-CT synthesis using a hybrid U-Net diffusion model based on transformers and information bottleneck theory
title_full_unstemmed CBCT-to-CT synthesis using a hybrid U-Net diffusion model based on transformers and information bottleneck theory
title_short CBCT-to-CT synthesis using a hybrid U-Net diffusion model based on transformers and information bottleneck theory
title_sort cbct to ct synthesis using a hybrid u net diffusion model based on transformers and information bottleneck theory
url https://doi.org/10.1038/s41598-025-92094-6
work_keys_str_mv AT canhu cbcttoctsynthesisusingahybridunetdiffusionmodelbasedontransformersandinformationbottlenecktheory
AT ningcao cbcttoctsynthesisusingahybridunetdiffusionmodelbasedontransformersandinformationbottlenecktheory
AT xiuhanli cbcttoctsynthesisusingahybridunetdiffusionmodelbasedontransformersandinformationbottlenecktheory
AT yanghe cbcttoctsynthesisusingahybridunetdiffusionmodelbasedontransformersandinformationbottlenecktheory
AT hanzhou cbcttoctsynthesisusingahybridunetdiffusionmodelbasedontransformersandinformationbottlenecktheory