Pretražite po imenu i prezimenu autora, mentora, urednika, prevoditelja

Napredna pretraga

Pregled bibliografske jedinice broj: 1023070

Iterative Algorithms for Gaussian Mixture Model Estimation in 2D PET Imaging


Tafro, Azra; Seršić, Damir
Iterative Algorithms for Gaussian Mixture Model Estimation in 2D PET Imaging // Proceedings of the 11th International Symposium on Image and Signal Processing and Analysis / Lončarić, Sven ; Bregović, Robert ; Carli, Marco ; Subašić, Marko (ur.).
Zagreb: University of Zagreb, 2019. str. 93-99 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


CROSBI ID: 1023070 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Iterative Algorithms for Gaussian Mixture Model Estimation in 2D PET Imaging

Autori
Tafro, Azra ; Seršić, Damir

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the 11th International Symposium on Image and Signal Processing and Analysis / Lončarić, Sven ; Bregović, Robert ; Carli, Marco ; Subašić, Marko - Zagreb : University of Zagreb, 2019, 93-99

ISBN
978-1-7281-3140-5

Skup
ISPA 2019 - 11th International Symposium on Image and Signal Processing and Analysis

Mjesto i datum
Dubrovnik, Hrvatska, 23.-25.9

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
positron emission tomography, Gaussian mixture models, expectation-maximization (EM) algorithm, image segmentation

Sažetak
In positron emission tomography (PET) the original measurement consists of pairs of gamma rays emitted from a radioactive substance forming a line, captured within a given plane (2D) or volume (3D). Traditional image reconstruction methods estimate intensity values in pixels or voxels on some predefined grid. In this paper, we investigate reconstruction of PET images directly from the lines of response, using a probabilistic Gaussian mixture model (GMM) for the underlying originals. Parameters are estimated by solving an overdetermined system of equations obtained directly from measurements. Experiments are performed on artificial data, using an iterative process resembling the expectation-maximization algorithm. Reconstruction is performed using several variations of the algorithm, which are compared by measuring the structural similarity index of the graphic representation of underlying distributions. The proposed segmentation method relies on the statistical properties of GMMs and appears to be robust, giving new insight and a new approach to traditional problems on real data.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo, Biotehnologija u biomedicini (prirodno područje, biomedicina i zdravstvo, biotehničko područje)



POVEZANOST RADA


Projekti:
HRZZ-IP-2014-09-2625 - Iznad Nyquistove granice (BeyondLimit) (Seršić, Damir, HRZZ - 2014-09) ( POIROT)

Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb,
Šumarski fakultet, Zagreb

Profili:

Avatar Url Azra Tafro (autor)

Avatar Url Damir Seršić (autor)

Citiraj ovu publikaciju

Tafro, Azra; Seršić, Damir
Iterative Algorithms for Gaussian Mixture Model Estimation in 2D PET Imaging // Proceedings of the 11th International Symposium on Image and Signal Processing and Analysis / Lončarić, Sven ; Bregović, Robert ; Carli, Marco ; Subašić, Marko (ur.).
Zagreb: University of Zagreb, 2019. str. 93-99 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
Tafro, A. & Seršić, D. (2019) Iterative Algorithms for Gaussian Mixture Model Estimation in 2D PET Imaging. U: Lončarić, S., Bregović, R., Carli, M. & Subašić, M. (ur.)Proceedings of the 11th International Symposium on Image and Signal Processing and Analysis.
@article{article, year = {2019}, pages = {93-99}, keywords = {positron emission tomography, Gaussian mixture models, expectation-maximization (EM) algorithm, image segmentation}, isbn = {978-1-7281-3140-5}, title = {Iterative Algorithms for Gaussian Mixture Model Estimation in 2D PET Imaging}, keyword = {positron emission tomography, Gaussian mixture models, expectation-maximization (EM) algorithm, image segmentation}, publisher = {University of Zagreb}, publisherplace = {Dubrovnik, Hrvatska} }




Contrast
Increase Font
Decrease Font
Dyslexic Font