Model-Based Segmentation of Multimodal Images

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Citation (Scopus)

Abstract

This paper proposes a model-based method for intensity-based segmentation of images acquired from multiple modalities. Pixel intensity within a modality image is represented by a univariate Gaussian distribution mixture in which the components correspond to different segments. The proposed Multi-Modality Expectation-Maximization (MMEM) algorithm then estimates the probability of each segment along with parameters of the Gaussian distributions for each modality by maximum likelihood using the Expectation-Maximization (EM) algorithm. Multimodal images are simultaneously involved in the iterative parameter estimation step. Pixel classes are determined by maximising a posteriori probability contributed from all multimodal images. Experimental results show that the method exploits and fuses complementary information of multimodal images. Segmentation can thus be more precise than when using single-modality images.
LanguageEnglish
Title of host publicationComputer Analysis of Images and Patterns
Pages604-611
Volume4673
DOIs
Publication statusPublished - 18 Aug 2007

Fingerprint

Gaussian distribution
Pixels
Electric fuses
Parameter estimation
Maximum likelihood

Cite this

Hong, X., McClean, S., Scotney, B., & Morrow, P. (2007). Model-Based Segmentation of Multimodal Images. In Computer Analysis of Images and Patterns (Vol. 4673, pp. 604-611) https://doi.org/10.1007/978-3-540-74272-2_75
Hong, Xin ; McClean, Sally ; Scotney, Bryan ; Morrow, Philip. / Model-Based Segmentation of Multimodal Images. Computer Analysis of Images and Patterns. Vol. 4673 2007. pp. 604-611
@inbook{946b219912c649c780c0d1c604692c2c,
title = "Model-Based Segmentation of Multimodal Images",
abstract = "This paper proposes a model-based method for intensity-based segmentation of images acquired from multiple modalities. Pixel intensity within a modality image is represented by a univariate Gaussian distribution mixture in which the components correspond to different segments. The proposed Multi-Modality Expectation-Maximization (MMEM) algorithm then estimates the probability of each segment along with parameters of the Gaussian distributions for each modality by maximum likelihood using the Expectation-Maximization (EM) algorithm. Multimodal images are simultaneously involved in the iterative parameter estimation step. Pixel classes are determined by maximising a posteriori probability contributed from all multimodal images. Experimental results show that the method exploits and fuses complementary information of multimodal images. Segmentation can thus be more precise than when using single-modality images.",
author = "Xin Hong and Sally McClean and Bryan Scotney and Philip Morrow",
year = "2007",
month = "8",
day = "18",
doi = "10.1007/978-3-540-74272-2_75",
language = "English",
isbn = "978-3-540-74271-5",
volume = "4673",
pages = "604--611",
booktitle = "Computer Analysis of Images and Patterns",

}

Hong, X, McClean, S, Scotney, B & Morrow, P 2007, Model-Based Segmentation of Multimodal Images. in Computer Analysis of Images and Patterns. vol. 4673, pp. 604-611. https://doi.org/10.1007/978-3-540-74272-2_75

Model-Based Segmentation of Multimodal Images. / Hong, Xin; McClean, Sally; Scotney, Bryan; Morrow, Philip.

Computer Analysis of Images and Patterns. Vol. 4673 2007. p. 604-611.

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - Model-Based Segmentation of Multimodal Images

AU - Hong, Xin

AU - McClean, Sally

AU - Scotney, Bryan

AU - Morrow, Philip

PY - 2007/8/18

Y1 - 2007/8/18

N2 - This paper proposes a model-based method for intensity-based segmentation of images acquired from multiple modalities. Pixel intensity within a modality image is represented by a univariate Gaussian distribution mixture in which the components correspond to different segments. The proposed Multi-Modality Expectation-Maximization (MMEM) algorithm then estimates the probability of each segment along with parameters of the Gaussian distributions for each modality by maximum likelihood using the Expectation-Maximization (EM) algorithm. Multimodal images are simultaneously involved in the iterative parameter estimation step. Pixel classes are determined by maximising a posteriori probability contributed from all multimodal images. Experimental results show that the method exploits and fuses complementary information of multimodal images. Segmentation can thus be more precise than when using single-modality images.

AB - This paper proposes a model-based method for intensity-based segmentation of images acquired from multiple modalities. Pixel intensity within a modality image is represented by a univariate Gaussian distribution mixture in which the components correspond to different segments. The proposed Multi-Modality Expectation-Maximization (MMEM) algorithm then estimates the probability of each segment along with parameters of the Gaussian distributions for each modality by maximum likelihood using the Expectation-Maximization (EM) algorithm. Multimodal images are simultaneously involved in the iterative parameter estimation step. Pixel classes are determined by maximising a posteriori probability contributed from all multimodal images. Experimental results show that the method exploits and fuses complementary information of multimodal images. Segmentation can thus be more precise than when using single-modality images.

U2 - 10.1007/978-3-540-74272-2_75

DO - 10.1007/978-3-540-74272-2_75

M3 - Chapter

SN - 978-3-540-74271-5

VL - 4673

SP - 604

EP - 611

BT - Computer Analysis of Images and Patterns

ER -

Hong X, McClean S, Scotney B, Morrow P. Model-Based Segmentation of Multimodal Images. In Computer Analysis of Images and Patterns. Vol. 4673. 2007. p. 604-611 https://doi.org/10.1007/978-3-540-74272-2_75