Noise suppression in photon-counting computed tomography using unsupervised Poisson flow generative models  

作　　者：Dennis Hein Staffan Holmin Timothy Szczykutowicz Jonathan S.Maltz Mats Danielsson Ge Wang Mats Persson 

机构地区：[1]Department of Physics,KTH Royal Institute of Technology,Stockholm 1142,Sweden [2]MedTechLabs,Karolinska University Hospital,Stockholm 17164,Sweden [3]Department of Clinical Neuroscience,Karolinska Institutet,Stockholm 17164,Sweden [4]Department of Neuroradiology,Karolinska University Hospital,Stockholm 17164,Sweden [5]Department of Radiology,School of Medicine and Public Health,University of Wisconsin,Madison,WI 53705,United States [6]GE HealthCare,Waukesha,WI 53188,United States [7]Department of Biomedical Engineering,School of Engineering,Biomedical Imaging Center,Center for Biotechnology and Interdisciplinary Studies,Rensselaer Polytechnic Institute,Troy,NY 12180,United States

出　　处：《Visual Computing for Industry,Biomedicine,and Art》2024年第1期98-111,共14页工医艺的可视计算(英文)

基　　金：supported by MedTechLabs,GE HealthCare,the Swedish Research council,No.2021-05103;the Göran Gustafsson foundation,No.2114.

摘　　要：Deep learning(DL)has proven to be important for computed tomography(CT)image denoising.However,such models are usually trained under supervision,requiring paired data that may be difficult to obtain in practice.Diffusion models offer unsupervised means of solving a wide range of inverse problems via posterior sampling.In particular,using the estimated unconditional score function of the prior distribution,obtained via unsupervised learning,one can sample from the desired posterior via hijacking and regularization.However,due to the iterative solvers used,the number of function evaluations(NFE)required may be orders of magnitudes larger than for single-step samplers.In this paper,we present a novel image denoising technique for photon-counting CT by extending the unsupervised approach to inverse problem solving to the case of Poisson flow generative models(PFGM)++.By hijacking and regularizing the sampling process we obtain a single-step sampler,that is NFE=1.Our proposed method incorporates posterior sampling using diffusion models as a special case.We demonstrate that the added robustness afforded by the PFGM++framework yields significant performance gains.Our results indicate competitive performance compared to popular supervised,including state-of-the-art diffusion-style models with NFE=1(consistency models),unsupervised,and non-DL-based image denoising techniques,on clinical low-dose CT data and clinical images from a prototype photon-counting CT system developed by GE HealthCare.

关 键 词：Deep learning Photon-counting CT DENOISING Diffusion models Poisson flow generative models 

分 类 号：TP1[自动化与计算机技术—控制理论与控制工程]