Bayesian spatiotemporal segmentation of combined PET-CT data using a bivariate poisson mixture model

Zacharie Irace; Hadj Batatia

Bayesian spatiotemporal segmentation of combined PET-CT data using a bivariate poisson mixture model

Zacharie Irace
, Hadj Batatia

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper presents an unsupervised algorithm for the joint segmentation of 4-D PET-CT images. The proposed method is based on a bivariate-Poisson mixture model to represent the bimodal data. A Bayesian framework is developed to label the voxels as well as jointly estimate the parameters of the mixture model. A generalized four-dimensional Potts-Markov Random Field (MRF) has been incorporated into the method to represent the spatio-temporal coherence of the mixture components. The method is successfully applied to 4-D registered PET-CT data of a patient with lung cancer. Results show that the proposed model fits accurately the data and allows the segmentation of different tissues and the identification of tumors in temporal series.

Original language	English
Title of host publication	2014 22nd European Signal Processing Conference (EUSIPCO)
Publisher	IEEE
Pages	2095-2099
Number of pages	5
ISBN (Electronic)	9780992862619
Publication status	Published - 13 Nov 2014
Event	22nd European Signal Processing Conference 2014 - Lisbon, Portugal Duration: 1 Sept 2014 → 5 Sept 2014

Publication series

Name	European Signal Processing Conference
ISSN (Print)	2219-5491
ISSN (Electronic)	2076-1465

Conference

Conference	22nd European Signal Processing Conference 2014
Abbreviated title	EUSIPCO 2014
Country/Territory	Portugal
City	Lisbon
Period	1/09/14 → 5/09/14

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

4-D segmentation
bivariate Poisson distribution
data fusion
multimodality
PET-CT

ASJC Scopus subject areas

Signal Processing
Electrical and Electronic Engineering

Cite this

@inproceedings{e3adeb188b524ff2be17a931b470e148,

title = "Bayesian spatiotemporal segmentation of combined PET-CT data using a bivariate poisson mixture model",

abstract = "This paper presents an unsupervised algorithm for the joint segmentation of 4-D PET-CT images. The proposed method is based on a bivariate-Poisson mixture model to represent the bimodal data. A Bayesian framework is developed to label the voxels as well as jointly estimate the parameters of the mixture model. A generalized four-dimensional Potts-Markov Random Field (MRF) has been incorporated into the method to represent the spatio-temporal coherence of the mixture components. The method is successfully applied to 4-D registered PET-CT data of a patient with lung cancer. Results show that the proposed model fits accurately the data and allows the segmentation of different tissues and the identification of tumors in temporal series.",

keywords = "4-D segmentation, bivariate Poisson distribution, data fusion, multimodality, PET-CT",

author = "Zacharie Irace and Hadj Batatia",

year = "2014",

month = nov,

day = "13",

language = "English",

series = "European Signal Processing Conference",

publisher = "IEEE",

pages = "2095--2099",

booktitle = "2014 22nd European Signal Processing Conference (EUSIPCO)",

address = "United States",

note = "22nd European Signal Processing Conference 2014, EUSIPCO 2014 ; Conference date: 01-09-2014 Through 05-09-2014",

}

TY - GEN

T1 - Bayesian spatiotemporal segmentation of combined PET-CT data using a bivariate poisson mixture model

AU - Irace, Zacharie

AU - Batatia, Hadj

PY - 2014/11/13

Y1 - 2014/11/13

N2 - This paper presents an unsupervised algorithm for the joint segmentation of 4-D PET-CT images. The proposed method is based on a bivariate-Poisson mixture model to represent the bimodal data. A Bayesian framework is developed to label the voxels as well as jointly estimate the parameters of the mixture model. A generalized four-dimensional Potts-Markov Random Field (MRF) has been incorporated into the method to represent the spatio-temporal coherence of the mixture components. The method is successfully applied to 4-D registered PET-CT data of a patient with lung cancer. Results show that the proposed model fits accurately the data and allows the segmentation of different tissues and the identification of tumors in temporal series.

AB - This paper presents an unsupervised algorithm for the joint segmentation of 4-D PET-CT images. The proposed method is based on a bivariate-Poisson mixture model to represent the bimodal data. A Bayesian framework is developed to label the voxels as well as jointly estimate the parameters of the mixture model. A generalized four-dimensional Potts-Markov Random Field (MRF) has been incorporated into the method to represent the spatio-temporal coherence of the mixture components. The method is successfully applied to 4-D registered PET-CT data of a patient with lung cancer. Results show that the proposed model fits accurately the data and allows the segmentation of different tissues and the identification of tumors in temporal series.

KW - 4-D segmentation

KW - bivariate Poisson distribution

KW - data fusion

KW - multimodality

KW - PET-CT

UR - https://www.scopus.com/pages/publications/84911931009

M3 - Conference contribution

AN - SCOPUS:84911931009

T3 - European Signal Processing Conference

SP - 2095

EP - 2099

BT - 2014 22nd European Signal Processing Conference (EUSIPCO)

PB - IEEE

T2 - 22nd European Signal Processing Conference 2014

Y2 - 1 September 2014 through 5 September 2014

ER -

Bayesian spatiotemporal segmentation of combined PET-CT data using a bivariate poisson mixture model

Abstract

Publication series

Conference

UN SDGs

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this