论文信息 - MULTIPLE NONNEGATIVE-MATRIX FACTORIZATION OF DYNAMIC PET IMAGES

MULTIPLE NONNEGATIVE-MATRIX FACTORIZATION OF DYNAMIC PET IMAGES

We propose an extension of nonnegative matrix factorization (NMF) to multilayer network model for dynamic myocardial PET image analysis. NMF has been previously applied to the analysis and shown to successfully extract three cardiac components and time-activity curve from the image sequences. Here we apply triple nonnegative-matrix factorization to the dynamic PET images of dog and show details of cardiac components. We think of the multiple nonnegative-matrix factorization as a model that can learn a hierarchical-parts representation.

[1] Eric Kandel,et al. Biology of the mind. , 2006, Newsweek.

[2] H. Sebastian Seung,et al. Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[3] David I. Perrett,et al. Neurophysiology of shape processing , 1993, Image Vis. Comput..

[4] 최승진. Non-negative matrix factorization of dynamic images in nuclear medicine , 2001 .

[5] Stan Z. Li,et al. Learning spatially localized, parts-based representation , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[6] H. Sebastian Seung,et al. Learning Generative Models with the Up-Propagation Algorithm , 1997, NIPS.

[7] Jack E. Houston,et al. The Use of Principle Components Analysis , 1989 .

[8] Daniel D. Lee,et al. APPLICATION OF NON-NEGATIVE MATRIX FACTORIZATION TO DYNAMIC POSITRON EMISSION TOMOGRAPHY , 2001 .

[9] D. Barber. The use of principal components in the quantitative analysis of gamma camera dynamic studies. , 1980, Physics in medicine and biology.