PPFM: Image Denoising in Photon-Counting CT Using Single-Step Posterior Sampling Poisson Flow Generative Models

IF 4.6 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING IEEE Transactions on Radiation and Plasma Medical Sciences Pub Date : 2024-06-11 DOI:10.1109/TRPMS.2024.3410092
Dennis Hein;Staffan Holmin;Timothy Szczykutowicz;Jonathan S. Maltz;Mats Danielsson;Ge Wang;Mats Persson
{"title":"PPFM: Image Denoising in Photon-Counting CT Using Single-Step Posterior Sampling Poisson Flow Generative Models","authors":"Dennis Hein;Staffan Holmin;Timothy Szczykutowicz;Jonathan S. Maltz;Mats Danielsson;Ge Wang;Mats Persson","doi":"10.1109/TRPMS.2024.3410092","DOIUrl":null,"url":null,"abstract":"Diffusion and Poisson flow models have shown impressive performance in a wide range of generative tasks, including low-dose CT (LDCT) image denoising. However, one limitation in general, and for clinical applications in particular, is slow sampling. Due to their iterative nature, the number of function evaluations (NFEs) required is usually on the order of \n<inline-formula> <tex-math>$10-10^{3}$ </tex-math></inline-formula>\n, both for conditional and unconditional generation. In this article, we present posterior sampling Poisson flow generative models (PPFMs), a novel image denoising technique for low-dose and photon-counting CT that produces excellent image quality whilst keeping NFE = 1. Updating the training and sampling processes of Poisson flow generative models (PFGMs)++, we learn a conditional generator which defines a trajectory between the prior noise distribution and the posterior distribution of interest. We additionally hijack and regularize the sampling process to achieve NFE = 1. Our results shed light on the benefits of the PFGM++ framework compared to diffusion models. In addition, PPFM is shown to perform favorably compared to current state-of-the-art diffusion-style models with NFE = 1, consistency models, as well as popular deep learning and nondeep learning-based image denoising techniques, on clinical LDCT images and clinical images from a prototype photon-counting CT system.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":null,"pages":null},"PeriodicalIF":4.6000,"publicationDate":"2024-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10554640","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Radiation and Plasma Medical Sciences","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10554640/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0

Abstract

Diffusion and Poisson flow models have shown impressive performance in a wide range of generative tasks, including low-dose CT (LDCT) image denoising. However, one limitation in general, and for clinical applications in particular, is slow sampling. Due to their iterative nature, the number of function evaluations (NFEs) required is usually on the order of $10-10^{3}$ , both for conditional and unconditional generation. In this article, we present posterior sampling Poisson flow generative models (PPFMs), a novel image denoising technique for low-dose and photon-counting CT that produces excellent image quality whilst keeping NFE = 1. Updating the training and sampling processes of Poisson flow generative models (PFGMs)++, we learn a conditional generator which defines a trajectory between the prior noise distribution and the posterior distribution of interest. We additionally hijack and regularize the sampling process to achieve NFE = 1. Our results shed light on the benefits of the PFGM++ framework compared to diffusion models. In addition, PPFM is shown to perform favorably compared to current state-of-the-art diffusion-style models with NFE = 1, consistency models, as well as popular deep learning and nondeep learning-based image denoising techniques, on clinical LDCT images and clinical images from a prototype photon-counting CT system.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
PPFM:使用单步后向采样泊松流生成模型对光子计数 CT 中的图像去噪
在包括低剂量 CT(LDCT)图像去噪在内的各种生成任务中,扩散和泊松流模型都表现出令人印象深刻的性能。然而,一般来说,特别是在临床应用中,它们的一个局限性是采样速度较慢。由于其迭代性质,无论是有条件生成还是无条件生成,所需的函数评估(NFE)次数通常在 10-10^{3}$ 之间。在本文中,我们介绍了后验采样泊松流生成模型(PPFMs),这是一种用于低剂量和光子计数 CT 的新型图像去噪技术,能在保持 NFE = 1 的情况下生成出色的图像质量。通过更新泊松流生成模型(PFGMs)++ 的训练和采样过程,我们学习了一个条件生成器,它定义了先验噪声分布和后验相关分布之间的轨迹。我们还对采样过程进行了劫持和正则化处理,以实现 NFE = 1。我们的研究结果阐明了 PFGM++ 框架与扩散模型相比的优势。此外,在临床 LDCT 图像和来自原型光子计数 CT 系统的临床图像上,PPFM 与当前最先进的扩散型模型(NFE = 1)、一致性模型以及流行的基于深度学习和非深度学习的图像去噪技术相比,表现出色。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
IEEE Transactions on Radiation and Plasma Medical Sciences
IEEE Transactions on Radiation and Plasma Medical Sciences RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING-
CiteScore
8.00
自引率
18.20%
发文量
109
期刊最新文献
Affiliate Plan of the IEEE Nuclear and Plasma Sciences Society Table of Contents Introducing IEEE Collabratec IEEE Transactions on Radiation and Plasma Medical Sciences Publication Information Member Get-a-Member (MGM) Program
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1