PET image denoising based on denoising diffusion probabilistic model.
PET image denoising based on denoising diffusion probabilistic model.
复制标题
基于去噪扩散概率模型的PET图像去噪。
DOI：
10.1007/s00259-023-06417-8
复制
发表时间：
2024
影响因子：
9.1
通讯作者：
Pan,Tinsu
中科院分区：
文献类型：
--
作者：
Gong,Kuang;Johnson,Keith;ElFakhri,Georges;Li,Quanzheng;Pan,Tinsu
由于各种物理退化因素和有限的接收计数，PET图像质量需要进一步改善。去噪扩散概率模型（DDPM）是一种基于分布学习的模型，它试图通过迭代精化将正态分布转化为特定的数据分布。在这项工作中，我们提出并评估了不同的DDPM为基础的方法PET图像noising.MethodsUnder的DDPM框架，一种方法来执行PET图像去噪是提供PET图像和/或先验图像作为输入。另一种方法是将先前图像作为网络输入与细化步骤中包括的PET图像一起提供，这可以适合不同噪声水平的场景。150脑[F]FDG数据集和140脑[F]MK-6240（成像神经元缠结沉积）数据集被用来评估建议的DDPM为基础的methodsResultsQuantification表明，DDPM为基础的框架与PET信息包括产生更好的结果比非局部均值，Unet和生成对抗网络（GAN）为基础的去噪方法。在模型中添加额外的MR先验有助于实现更好的性能，并进一步降低图像去噪过程中的不确定性。单纯依赖MR先验而忽略PET信息会导致较大的偏倚。区域和表面量化表明，采用MR先验作为网络输入，同时嵌入PET图像作为数据一致性约束在inference. ConclusionDDPM的PET图像去噪是一个灵活的框架，它可以有效地利用先验信息，并实现更好的性能比非局部均值，Unet和基于GAN的去噪方法。
PurposeDue to various physical degradation factors and limited counts received, PET image quality needs further improvements. The denoising diffusion probabilistic model (DDPM) was a distribution learning-based model, which tried to transform a normal distribution into a specific data distribution based on iterative refinements. In this work, we proposed and evaluated different DDPM-based methods for PET image denoising.MethodsUnder the DDPM framework, one way to perform PET image denoising was to provide the PET image and/or the prior image as the input. Another way was to supply the prior image as the network input with the PET image included in the refinement steps, which could fit for scenarios of different noise levels. 150 brain [F]FDG datasets and 140 brain [F]MK-6240 (imaging neurofibrillary tangles deposition) datasets were utilized to evaluate the proposed DDPM-based methods.ResultsQuantification showed that the DDPM-based frameworks with PET information included generated better results than the nonlocal mean, Unet and generative adversarial network (GAN)-based denoising methods. Adding additional MR prior in the model helped achieved better performance and further reduced the uncertainty during image denoising. Solely relying on MR prior while ignoring the PET information resulted in large bias. Regional and surface quantification showed that employing MR prior as the network input while embedding PET image as a data-consistency constraint during inference achieved the best performance.ConclusionDDPM-based PET image denoising is a flexible framework, which can efficiently utilize prior information and achieve better performance than the nonlocal mean, Unet and GAN-based denoising methods.
DOI：
10.1007/11550518_5
发表时间：
2005-08
期刊：
--
影响因子：
--
作者：
Natalia Slesareva;Andrés Bruhn;J. Weickert
通讯作者：
Natalia Slesareva;Andrés Bruhn;J. Weickert
DOI：
--
发表时间：
2003
期刊：
Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429)
影响因子：
--
作者：
Hansung Kim;K. Sohn
通讯作者：
K. Sohn
DOI：
10.1109/tpami.1985.4767615
发表时间：
1985-01-01
影响因子：
23.6
作者：
GRIMSON, WEL
通讯作者：
GRIMSON, WEL