Name
Abstract | ||
|---|---|---|
Image reconstruction from low-count positron emission tomography (PET) projection data is challenging because the inverse problem is ill-posed. Prior information can be used to improve image quality. Inspired by the kernel methods in machine learning, this paper proposes a kernel based method that models PET image intensity in each pixel as a function of a set of features obtained from prior information. The kernel-based image model is incorporated into the forward model of PET projection data and the coefficients can be readily estimated by the maximum likelihood (ML) or penalized likelihood image reconstruction. A kernelized expectation-maximization algorithm is presented to obtain the ML estimate. Computer simulations show that the proposed approach can achieve better bias versus variance trade-off and higher contrast recovery for dynamic PET image reconstruction than the conventional maximum likelihood method with and without post-reconstruction denoising. Compared with other regularization-based methods, the kernel method is easier to implement and provides better image quality for low-count data. Application of the proposed kernel method to a 4-D dynamic PET patient dataset showed promising results. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/TMI.2014.2343916 | IEEE Transactions on Medical Imaging |
Keywords | DocType | Volume |
maximum likelihood image reconstruction,ml estimate,kernel-based image model,expectation-maximisation algorithm,ml image reconstruction,image quality,penalized likelihood image reconstruction,post-reconstruction denoising,low-count positron emission tomography projection data,pet image pixel intensity model,learning (artificial intelligence),bias-variance trade-off,maximum likelihood estimation,operating system kernels,coefficient estimation,4d dynamic pet patient dataset,signal-noise ratio,contrast recovery,kernel based image model,image denoising,kernelized expectation-maximization algorithm,pet projection data forward model,image reconstruction,pet image intensity modeling,low count pet projection data,positron emission tomography (pet),feature extraction,kernel based method,forward model,inverse problem,positron emission tomography,dynamic pet image reconstruction,prior information,ill posed inverse problem,image prior,kernel method application,machine learning,computer simulation,pet projection data model,kernel method,expectation maximization (em),regularization-based method,medical image processing,pixel intensity modeling,kernel,noise reduction,signal to noise ratio,sparse matrices,learning artificial intelligence,mathematical model,signal noise ratio | Conference | 34 |
Issue | ISSN | ISBN |
1 | 1558-254X | 978-1-4673-6456-0 |
Citations | PageRank | References |
12 | 0.65 | 16 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Guobao Wang | 1 | 86 | 12.68 |
| Jinyi Qi | 2 | 284 | 35.82 |