Neural Network-Based PET Image Reconstruction

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

• 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