A method for shape analysis and segmentation in MRI

Nathan Faggian; Zhaolin Chen; Leigh Johnston; Oh Se-Hong; Zang Hee Cho; Gary Egan

doi:10.1109/DICTA.2008.71

A method for shape analysis and segmentation in MRI

Nathan Faggian
, Zhaolin Chen
, Leigh Johnston
, Oh Se-Hong
, Zang Hee Cho
, Gary Egan

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

2 Citations (Scopus)

Abstract

Morphometry of Human Magnetic Resonance Images (MRI) is the process of measuring structural variations that occur in the brain. Morphometrics provide a mechanism to monitor and relate structural changes of anatomy to the onset or progression of a disease. It is therefor a very important area of research, specifically since MRI sequences are non-invasive and can be acquired in-vivo. This paper addresses two sub-problems in the area of MRI morphometry: 1) shape analysis and 2) semi-automated segmentation. Firstly the paper presents a method of analysing for group differences between 2D contours. The theoretical underpinning is derived from the field of content-based image retrieval, specifically to solve contour correspondences. Secondly the paper uses these correspondences to train a deformable model to automatically segment structures. This is achieved using a modified active appearance model fitting algorithm.

Original language	English
Title of host publication	Proceedings - Digital Image Computing
Subtitle of host publication	Techniques and Applications, DICTA 2008
Pages	335-342
Number of pages	8
DOIs	https://doi.org/10.1109/DICTA.2008.71
Publication status	Published - 1 Dec 2008
Externally published	Yes
Event	Digital Image Computing Techniques and Applications 2008 - Rydges Lakeside Canberra, Canberra, Australia Duration: 1 Dec 2008 → 3 Dec 2008 Conference number: 10th http://dicta2008.rsise.anu.edu.au/ https://ieeexplore.ieee.org/xpl/conhome/4699977/proceeding (Proceedings)

Conference

Conference	Digital Image Computing Techniques and Applications 2008
Abbreviated title	DICTA 2008
Country/Territory	Australia
City	Canberra
Period	1/12/08 → 3/12/08
Other	DICTA is the main Australian conference on machine vision, image processing and related areas.In 2007, it had approximately 80 papers with 110 delegates. Since its establishment, DICTA has been a biannual meeting. In 2008, it will turn into an annual conference. It is the conference of the Australian Pattern Recognition Society.
Internet address	http://dicta2008.rsise.anu.edu.au/ https://ieeexplore.ieee.org/xpl/conhome/4699977/proceeding (Proceedings)

UN SDGs

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

SDG 3 Good Health and Well-being

Access to Document

10.1109/DICTA.2008.71

Cite this

@inproceedings{07bb3788489d453eb323457cbface16c,

title = "A method for shape analysis and segmentation in MRI",

abstract = "Morphometry of Human Magnetic Resonance Images (MRI) is the process of measuring structural variations that occur in the brain. Morphometrics provide a mechanism to monitor and relate structural changes of anatomy to the onset or progression of a disease. It is therefor a very important area of research, specifically since MRI sequences are non-invasive and can be acquired in-vivo. This paper addresses two sub-problems in the area of MRI morphometry: 1) shape analysis and 2) semi-automated segmentation. Firstly the paper presents a method of analysing for group differences between 2D contours. The theoretical underpinning is derived from the field of content-based image retrieval, specifically to solve contour correspondences. Secondly the paper uses these correspondences to train a deformable model to automatically segment structures. This is achieved using a modified active appearance model fitting algorithm.",

author = "Nathan Faggian and Zhaolin Chen and Leigh Johnston and Oh Se-Hong and Cho, \{Zang Hee\} and Gary Egan",

year = "2008",

month = dec,

day = "1",

doi = "10.1109/DICTA.2008.71",

language = "English",

isbn = "9780769534565",

pages = "335--342",

booktitle = "Proceedings - Digital Image Computing",

note = "Digital Image Computing Techniques and Applications 2008, DICTA 2008 ; Conference date: 01-12-2008 Through 03-12-2008",

url = "http://dicta2008.rsise.anu.edu.au/, https://ieeexplore.ieee.org/xpl/conhome/4699977/proceeding",

}

Faggian, N, Chen, Z, Johnston, L, Se-Hong, O, Cho, ZH & Egan, G 2008, A method for shape analysis and segmentation in MRI. in Proceedings - Digital Image Computing: Techniques and Applications, DICTA 2008., 4700040, pp. 335-342, Digital Image Computing Techniques and Applications 2008, Canberra, Australian Capital Territory, Australia, 1/12/08. https://doi.org/10.1109/DICTA.2008.71

TY - GEN

T1 - A method for shape analysis and segmentation in MRI

AU - Faggian, Nathan

AU - Chen, Zhaolin

AU - Johnston, Leigh

AU - Se-Hong, Oh

AU - Cho, Zang Hee

AU - Egan, Gary

N1 - Conference code: 10th

PY - 2008/12/1

Y1 - 2008/12/1

N2 - Morphometry of Human Magnetic Resonance Images (MRI) is the process of measuring structural variations that occur in the brain. Morphometrics provide a mechanism to monitor and relate structural changes of anatomy to the onset or progression of a disease. It is therefor a very important area of research, specifically since MRI sequences are non-invasive and can be acquired in-vivo. This paper addresses two sub-problems in the area of MRI morphometry: 1) shape analysis and 2) semi-automated segmentation. Firstly the paper presents a method of analysing for group differences between 2D contours. The theoretical underpinning is derived from the field of content-based image retrieval, specifically to solve contour correspondences. Secondly the paper uses these correspondences to train a deformable model to automatically segment structures. This is achieved using a modified active appearance model fitting algorithm.

AB - Morphometry of Human Magnetic Resonance Images (MRI) is the process of measuring structural variations that occur in the brain. Morphometrics provide a mechanism to monitor and relate structural changes of anatomy to the onset or progression of a disease. It is therefor a very important area of research, specifically since MRI sequences are non-invasive and can be acquired in-vivo. This paper addresses two sub-problems in the area of MRI morphometry: 1) shape analysis and 2) semi-automated segmentation. Firstly the paper presents a method of analysing for group differences between 2D contours. The theoretical underpinning is derived from the field of content-based image retrieval, specifically to solve contour correspondences. Secondly the paper uses these correspondences to train a deformable model to automatically segment structures. This is achieved using a modified active appearance model fitting algorithm.

UR - https://www.scopus.com/pages/publications/67549140269

U2 - 10.1109/DICTA.2008.71

DO - 10.1109/DICTA.2008.71

M3 - Conference Paper

AN - SCOPUS:67549140269

SN - 9780769534565

SP - 335

EP - 342

BT - Proceedings - Digital Image Computing

T2 - Digital Image Computing Techniques and Applications 2008

Y2 - 1 December 2008 through 3 December 2008

ER -

A method for shape analysis and segmentation in MRI

Abstract

Conference

UN SDGs

Access to Document

Other files and links

Cite this