ICA separation of functional components from dynamic cardiac PET data

Author

Magadán-Méndez, M. ; Kivimäki, A. ; Ruotsalainen, U.

Author_Institution

Graduate Sch. for Inf. Sci., Tampere Univ. of Technol., Finland

Volume

4

fYear

2003

fDate

19-25 Oct. 2003

Firstpage

2618

Abstract

The aim of this study was to improve detection of different heart tissues, and specially their boundaries, in H₂^{1 5}O PET (positron emission tomography) heart images. This problem was considered as a blind source separation problem. In order to solve it we applied ICA (independent component analysis) on dynamic image data and measured projection profiles (sinograms). The testing was based on two kinds of data: a simple dynamic numerical phantom and human heart data acquired during resting state. The sensitivity of ICA to noise was examined on phantom data, where ICA seemed to be less sensitive to noise on sinogram data than on image data. On cardiac rest data, the results were in line with the results on phantom data.

Keywords

biological tissues; blind source separation; cardiology; image segmentation; independent component analysis; medical image processing; noise; numerical analysis; phantoms; positron emission tomography; radioactive tracers; H₂¹⁵O PET heart images; ICA; blind source separation problem; cardiac rest data; dynamic image data; dynamic numerical phantom; heart tissue detection; human heart data; image segmentation; independent component analysis; noise separation; positron emission tomography; projection profiles; resting state; sinograms; tissue boundaries; Blind source separation; Heart; Humans; Image segmentation; Imaging phantoms; Independent component analysis; Muscles; Pharmaceutical technology; Positron emission tomography; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Nuclear Science Symposium Conference Record, 2003 IEEE

ISSN

1082-3654

Print_ISBN

0-7803-8257-9

Type

conf

DOI

10.1109/NSSMIC.2003.1352426

Filename

1352426