GLFC: Unified Global-Local Feature and Contrast Learning with Mamba-Enhanced UNet for Synthetic CT Generation from CBCT
This work addresses image quality improvement in medical imaging for CBCT, but it appears incremental as it builds on existing UNet and contrast learning approaches.
The paper tackles the problem of generating synthetic CT images from CBCT by proposing a GLFC framework, which improves SSIM from 77.91% to 91.50% on the SynthRAD2023 dataset and outperforms existing methods.
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