用Mamba增强UNet+多对比损失，提升CBCT转CT图像质量
GLFC: Unified Global-Local Feature and Contrast Learning with Mamba-Enhanced UNet for Synthetic CT Generation from CBCT
- 在UNet跳跃连接中嵌入Mamba块，同时捕捉全局与局部特征
- 在不同灰度区间计算对比损失，显著改善软组织和骨骼区域质量
- 在SynthRAD2023数据集上SSIM提升至91.50%，优于现有方法
从锥形束计算机断层扫描（CBCT）生成合成计算机断层扫描（sCT）图像可有效提升CBCT图像质量。现有基于卷积神经网络（CNN）和Transformer的sCT生成方法常难以同时有效捕捉全局与局部特征及对比度，影响生成质量。本文提出统一的全局-局部特征与对比学习框架（GLFC）。首先，引入Mamba增强的UNet（MEUNet），将Mamba模块嵌入高分辨率UNet的跳跃连接中，以高效学习全局与局部特征。其次，设计多对比损失（MCL），在不同灰度窗口计算合成损失，提升软组织与骨组织区域的生成质量。在SynthRAD2023数据集上的实验表明，相比原始CBCT，GLFC生成的sCT图像结构相似性（SSIM）从77.91%提升至91.50%，显著优于多个现有方法。代码已开源。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。