GLFC: Unified Global-Local Feature and Contrast Learning with Mamba-Enhanced UNet for Synthetic CT Generation from CBCT

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhou, Xianhao, Wu, Jianghao, Zhao, Huangxuan, Chen, Lei, Zhang, Shaoting, Wang, Guotai
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929671176716288
author Zhou, Xianhao
Wu, Jianghao
Zhao, Huangxuan
Chen, Lei
Zhang, Shaoting
Wang, Guotai
author_facet Zhou, Xianhao
Wu, Jianghao
Zhao, Huangxuan
Chen, Lei
Zhang, Shaoting
Wang, Guotai
contents Generating synthetic Computed Tomography (CT) images from Cone Beam Computed Tomography (CBCT) is desirable for improving the image quality of CBCT. Existing synthetic CT (sCT) generation methods using Convolutional Neural Networks (CNN) and Transformers often face difficulties in effectively capturing both global and local features and contrasts for high-quality sCT generation. In this work, we propose a Global-Local Feature and Contrast learning (GLFC) framework for sCT generation. First, a Mamba-Enhanced UNet (MEUNet) is introduced by integrating Mamba blocks into the skip connections of a high-resolution UNet for effective global and local feature learning. Second, we propose a Multiple Contrast Loss (MCL) that calculates synthetic loss at different intensity windows to improve quality for both soft tissues and bone regions. Experiments on the SynthRAD2023 dataset demonstrate that GLFC improved the SSIM of sCT from 77.91% to 91.50% compared with the original CBCT, and significantly outperformed several existing methods for sCT generation. The code is available at https://github.com/HiLab-git/GLFC
format Preprint
id arxiv_https___arxiv_org_abs_2501_02992
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GLFC: Unified Global-Local Feature and Contrast Learning with Mamba-Enhanced UNet for Synthetic CT Generation from CBCT
Zhou, Xianhao
Wu, Jianghao
Zhao, Huangxuan
Chen, Lei
Zhang, Shaoting
Wang, Guotai
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Generating synthetic Computed Tomography (CT) images from Cone Beam Computed Tomography (CBCT) is desirable for improving the image quality of CBCT. Existing synthetic CT (sCT) generation methods using Convolutional Neural Networks (CNN) and Transformers often face difficulties in effectively capturing both global and local features and contrasts for high-quality sCT generation. In this work, we propose a Global-Local Feature and Contrast learning (GLFC) framework for sCT generation. First, a Mamba-Enhanced UNet (MEUNet) is introduced by integrating Mamba blocks into the skip connections of a high-resolution UNet for effective global and local feature learning. Second, we propose a Multiple Contrast Loss (MCL) that calculates synthetic loss at different intensity windows to improve quality for both soft tissues and bone regions. Experiments on the SynthRAD2023 dataset demonstrate that GLFC improved the SSIM of sCT from 77.91% to 91.50% compared with the original CBCT, and significantly outperformed several existing methods for sCT generation. The code is available at https://github.com/HiLab-git/GLFC
title GLFC: Unified Global-Local Feature and Contrast Learning with Mamba-Enhanced UNet for Synthetic CT Generation from CBCT
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.02992