波谱学杂志

• •    

扩散张量图像去噪算法研究进展

杨黎明,王远军*   

  1. 上海理工大学 医学影像技术研究所,上海 200093

  • 收稿日期:2023-10-20 修回日期:2024-01-04 出版日期:2024-01-05 在线发表日期:2024-01-05
  • 通讯作者: 王远军 E-mail:yjusst@126.com

Research Progress of Denoising Algorithms for Diffusion Tensor Images

YANG Liming, WANG Yuanjun*   

  1. Institute of Medical Imaging Technology, University of Shanghai for Science and Technology, Shanghai 200093, China
  • Received:2023-10-20 Revised:2024-01-04 Published:2024-01-05 Online:2024-01-05
  • Contact: WANG Yuanjun E-mail:yjusst@126.com

摘要: 扩散张量成像是研究组织大脑微结构与白质纤维束分布的重要手段,然而受扩散加权信号衰减与长回波时间的影响,扩散张量图像存在严重的低信噪比问题.因此,有效的去噪技术在提高图像质量方面发挥着重要的作用.本文首先阐述了扩散张量成像的原理及噪声类型;其次论述了经典的扩散张量图像去噪算法,包括基于传统图像处理方法与基于深度学习方法,并着重探讨了扩散张量图像去噪的研究现状及不足;接着介绍了去噪评估标准及常用的公开数据集;然后讨论分析了文中提及的扩散张量图像去噪方法;最后总结并对该领域未来的研究方向进行了展望.

关键词: 扩散张量成像, 扩散加权成像, 图像去噪, 深度学习, 生成模型

Abstract: Diffusion tensor imaging is an important technique to study tissue brain microstructure and the distribution of white matter fiber tracts, however, affected by the diffusion-weighted signal attenuation and long echo time, diffusion tensor images suffer from serious low signal-to-noise ratio problem. Therefore, efficient denoising techniques are crucial for enhancing image quality. This paper firstly describes the principle of diffusion tensor imaging and the types of noise, discusses the classical diffusion tensor images denoising algorithms. The content focuses on the current research status and shortcomings of diffusion tensor images denoising from the perspectives of traditional image processing-based and deep learning-based. The denoising evaluation criteria and commonly used public datasets are also introduced. Then, the paper discusses and analyzes the diffusion tensor images denoising methods mentioned. Finally, summarizes and outlines the future research directions in this field. 

Key words: Diffusion tensor imaging, diffusion weighted imaging, image denoising, deep learning, generative model

中图分类号: