摘要
由于正电子发射型计算机断层显像(PET)噪声较大,现有图像降噪效果不理想,提出了一种结合残差U-Net神经网络和深度图像先验(DIP)的PET图像降噪。在U-Net网络中引入残差学习,提高网络表达能力和收敛速度;提出一种无训练数据的DIP算法,将神经网络解释为图像的参数化,利用图像噪声参数化后呈现高阻抗的特性将其去除,达到降噪的目的;在BrainWeb脑部图像数据集上进行实验,并对实验结果进行了对比分析。分析结果表明,所提方法能够得到边缘清晰且平滑的图像,在不同噪声等级和时间帧中,其去噪效果均优于其他对比方法,可获得高质量的图像。
Due to the high noise of Positron Emission Tomography(PET),the existing image denoising effect is not ideal.Therefore,a new method combining residual U-Net neural network and Deep Image Prior(DIP)is proposed.Firstly,residual learning is introduced into the U-Net network to improve the network expression ability and convergence speed.Then,a DIP algorithm without training data is proposed.The neural network is interpreted as the parameterization of the image,and the noise is removed by using the high impedance characteristics of the parameterized noise to achieve the purpose of noise reduction.Finally,the real data obtained from the brains of living monkeys injected with 18 f-2-fluorodeoxyglucose(18 F-FDG)were used for simulation analysis.The results show that the proposed method can get a clear and smooth image.In different noise levels and time frames,the denoising effect of the proposed method is better than other contrast methods,and can obtain high-quality images.
作者
黄兴
杨瑞梅
HUANG Xing;YANG Ruimei(College of Big Data and Software,College of Mobile Telecommunications,Chongqing University of Posts and Telecom,Hechuan 401520,China;College of Big Data and Intelligent Engineering,College of Foreign Business and Trade,Chongqing Normal University,Hechuan 401520,China)
出处
《光学技术》
CAS
CSCD
北大核心
2021年第2期209-216,共8页
Optical Technique
基金
重庆市教育委员会科学技术研究项目(KJQN201902002)。
