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.
| Original language | English (US) |
|---|---|
| Article number | 6868314 |
| Pages (from-to) | 61-71 |
| Number of pages | 11 |
| Journal | IEEE Transactions on Medical Imaging |
| Volume | 34 |
| Issue number | 1 |
| DOIs | |
| State | Published - Jan 1 2015 |
Fingerprint
Keywords
- Expectation maximization (EM)
- image prior
- image reconstruction
- kernel method
- positron emission tomography (PET)
ASJC Scopus subject areas
- Electrical and Electronic Engineering
- Computer Science Applications
- Radiological and Ultrasound Technology
- Software
Cite this
PET image reconstruction using kernel method. / Wang, Guobao; Qi, Jinyi.
In: IEEE Transactions on Medical Imaging, Vol. 34, No. 1, 6868314, 01.01.2015, p. 61-71.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - PET image reconstruction using kernel method
AU - Wang, Guobao
AU - Qi, Jinyi
PY - 2015/1/1
Y1 - 2015/1/1
N2 - 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.
AB - 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.
KW - Expectation maximization (EM)
KW - image prior
KW - image reconstruction
KW - kernel method
KW - positron emission tomography (PET)
UR - http://www.scopus.com/inward/record.url?scp=84920141881&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84920141881&partnerID=8YFLogxK
U2 - 10.1109/TMI.2014.2343916
DO - 10.1109/TMI.2014.2343916
M3 - Article
VL - 34
SP - 61
EP - 71
JO - IEEE Transactions on Medical Imaging
JF - IEEE Transactions on Medical Imaging
SN - 0278-0062
IS - 1
M1 - 6868314
ER -