Neural Network-Based PET Image Reconstruction

Y. Kosugi; M. Sase; Y. Suganami; N. Uemoto; T. Momose; J. Nishikawa

doi:10.1055/s-0038-1636869

Methods of Information in Medicine, Inhaltsverzeichnis

Methods Inf Med 1997; 36(04/05): 329-331
DOI: 10.1055/s-0038-1636869

Original Article

Schattauer GmbH

Neural Network-Based PET Image Reconstruction

Autoren

Y. Kosugi

¹Tokyo Institute of Technology, Yokohama, Japan
M. Sase

²University of Tokyo, School of Medicine, Tokyo, Japan
Y. Suganami

¹Tokyo Institute of Technology, Yokohama, Japan
N. Uemoto

¹Tokyo Institute of Technology, Yokohama, Japan
T. Momose

²University of Tokyo, School of Medicine, Tokyo, Japan
J. Nishikawa

²University of Tokyo, School of Medicine, Tokyo, Japan

Abstract

Abstract:

In PET image analysis, conventional deconvolution alone will not give sufficient information for a precise study of a localized brain function. In the deconvolution process, which is a type of inverse problem, it is important to confine the solution space by incorporating a priori knowledge such as the tissue distribution given by MR images as well as smoothness in the blood flow distribution profile. An MR-embedded neural-network model is described to reduce the partial volume effect in the restoration of blood flow profiles from PET images.

Keywords:

Neural Networks - Positron Emission Tomography - Inverse Problem - Regularization

Volltext

Referenzen

REFERENCES
1 Sase M, Kinoshita N, Kosugi Y. A neural network for fusing the MR information into PET images to improve spatial resolution. Proc IEEE Int Conf on Image Processing 1994; 908-11.
2 Kosugi Y, Sase M, Suganami Y, Momose T, Nishikawa J. Dissolution of partial volume effect in PET by an inversion technique with the MR-embedded neural network model. Proc Brain PET 1995; 95: S-35.
3 Kosugi Y, Suganami Y, Uemoto N. et al. CCE-based index selection for neuro assisted MR-image segmentation. Proc IEEE Int Conf Image Processing. 1996
4 Craig IJD, Brown JC. Inverse Problems in Astronomy. Adam Hilger; 1986