Adaptive rectification based adversarial network with spectrum constraint for high-quality PET image synthesis
2022-04
发表期刊MEDICAL IMAGE ANALYSIS (IF:10.7[JCR-2023],11.9[5-Year])
ISSN1361-8415
EISSN1361-8423
卷号77
发表状态已发表
DOI10.1016/j.media.2021.102335
摘要

Positron emission tomography (PET) is a typical nuclear imaging technique, which can provide crucial functional information for early brain disease diagnosis. Generally, clinically acceptable PET images are obtained by injecting a standard-dose radioactive tracer into human body, while on the other hand the cumulative radiation exposure inevitably raises concerns about potential health risks. However, reducing the tracer dose will increase the noise and artifacts of the reconstructed PET image. For the purpose of acquiring high-quality PET images while reducing radiation exposure, in this paper, we innovatively present an adaptive rectification based generative adversarial network with spectrum constraint, named AR-GAN, which uses low-dose PET (LPET) image to synthesize standard-dose PET (SPET) image of high-quality. Specifically, considering the existing differences between the synthesized SPET image by traditional GAN and the real SPET image, an adaptive rectification network (AR-Net) is devised to estimate the residual between the preliminarily predicted image and the real SPET image, based on the hypothesis that a more realistic rectified image can be obtained by incorporating both the residual and the preliminarily predicted PET image. Moreover, to address the issue of high-frequency distortions in the output image, we employ a spectral regularization term in the training optimization objective to constrain the consistency of the synthesized image and the real image in the frequency domain, which further preserves the high-frequency detailed information and improves synthesis performance. Validations on both the phantom dataset and the clinical dataset show that the proposed AR-GAN can estimate SPET images from LPET images effectively and outperform other state-of-the-art image synthesis approaches. © 2021 Elsevier B.V.

关键词Diagnosis Frequency domain analysis Generative adversarial networks Health risks Image enhancement Positrons Adaptive rectification Generative adversarial network High quality Images synthesis Low dose PET images Positron emission tomography Radiation Exposure Spectra's Spectrum constraint
收录类别SCIE ; EI
语种英语
出版者Elsevier B.V.
EI入藏号20220111415522
EI主题词Positron emission tomography
EI分类号461.6 Medicine and Pharmacology ; 461.7 Health Care ; 723.4 Artificial Intelligence ; 921.3 Mathematical Transformations
原始文献类型Journal article (JA)
引用统计
正在获取...
文献类型期刊论文
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/200614
专题生物医学工程学院_PI研究组_沈定刚组
通讯作者Wang, Yan; Shen, Dinggang
作者单位
1.School of Computer Science, Sichuan University, China;
2.School of Electrical and Information Engineering, University of Sydney, Australia;
3.School of Computer Science, Chengdu University of Information Technology, China;
4.School of Biomedical Engineering, ShanghaiTech University, China;
5.Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, China
通讯作者单位生物医学工程学院
推荐引用方式
GB/T 7714
Luo, Yanmei,Zhou, Luping,Zhan, Bo,et al. Adaptive rectification based adversarial network with spectrum constraint for high-quality PET image synthesis[J]. MEDICAL IMAGE ANALYSIS,2022,77.
APA Luo, Yanmei.,Zhou, Luping.,Zhan, Bo.,Fei, Yuchen.,Zhou, Jiliu.,...&Shen, Dinggang.(2022).Adaptive rectification based adversarial network with spectrum constraint for high-quality PET image synthesis.MEDICAL IMAGE ANALYSIS,77.
MLA Luo, Yanmei,et al."Adaptive rectification based adversarial network with spectrum constraint for high-quality PET image synthesis".MEDICAL IMAGE ANALYSIS 77(2022).
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Luo, Yanmei]的文章
[Zhou, Luping]的文章
[Zhan, Bo]的文章
百度学术
百度学术中相似的文章
[Luo, Yanmei]的文章
[Zhou, Luping]的文章
[Zhan, Bo]的文章
必应学术
必应学术中相似的文章
[Luo, Yanmei]的文章
[Zhou, Luping]的文章
[Zhan, Bo]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。