Improved generation of probabilistic atlases for the expectation maximization classification

Jyrki Lötjönen; Robin Wolz; Juha Koikkalainen; Lennart Thurfjell; Roger Lundqvist; Gunhild Waldemar; Hilkka Soininen; Daniel Rueckert

doi:10.1109/ISBI.2011.5872765

Improved generation of probabilistic atlases for the expectation maximization classification

Jyrki Lötjönen, Robin Wolz, Juha Koikkalainen, Lennart Thurfjell, Roger Lundqvist, Gunhild Waldemar, Hilkka Soininen, Daniel Rueckert

VTT Technical Research Centre of Finland

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

8 Citations (Scopus)

Abstract

Probabilistic atlases present prior knowledge about the spatial distribution of various structures or tissues in a population, used commonly in segmentation. We propose three methods for generating probabilistic atlases: 1) the atlases are constructed in a template space using dense non-rigid transformations and transformed to the space of unseen data, 2) as the method 1 but atlas selection is performed in addition, and 3) the atlases are constructed directly in the space of the unseen data. The methods were evaluated in the segmentation of hippocampus from 340 ADNI cases. When comparing with manual segmentations, the Dice similarity indices were 0.84, 0.85 and 0.87 and the correlation coefficients for the volumes were 0.84, 0.92 and 0.96 for the three methods tested. Our results show clearly the importance of probabilistic atlases in segmentation.

Original language	English
Title of host publication	2011 IEEE International Symposium on Biomedical Imaging
Subtitle of host publication	From Nano to Macro
Place of Publication	Piscataway
Publisher	IEEE Institute of Electrical and Electronic Engineers
Pages	1839-1842
ISBN (Electronic)	978-1-4244-4128-0
ISBN (Print)	978-1-4244-4127-3
DOIs	https://doi.org/10.1109/ISBI.2011.5872765
Publication status	Published - 2011
MoE publication type	A4 Article in a conference publication
Event	8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2011 - Chicago, IL, United States Duration: 30 Mar 2011 → 2 Apr 2011

Conference

Conference	8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2011
Abbreviated title	ISBI 2011
Country/Territory	United States
City	Chicago, IL
Period	30/03/11 → 2/04/11

Keywords

segmentation
atlas
brain

Access to Document

10.1109/ISBI.2011.5872765

Cite this

Lötjönen, J., Wolz, R., Koikkalainen, J., Thurfjell, L., Lundqvist, R., Waldemar, G., Soininen, H., & Rueckert, D. (2011). Improved generation of probabilistic atlases for the expectation maximization classification. In 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro (pp. 1839-1842). IEEE Institute of Electrical and Electronic Engineers. https://doi.org/10.1109/ISBI.2011.5872765

@inproceedings{143edcbe5d944867834a23a8356cd8f5,

title = "Improved generation of probabilistic atlases for the expectation maximization classification",

abstract = "Probabilistic atlases present prior knowledge about the spatial distribution of various structures or tissues in a population, used commonly in segmentation. We propose three methods for generating probabilistic atlases: 1) the atlases are constructed in a template space using dense non-rigid transformations and transformed to the space of unseen data, 2) as the method 1 but atlas selection is performed in addition, and 3) the atlases are constructed directly in the space of the unseen data. The methods were evaluated in the segmentation of hippocampus from 340 ADNI cases. When comparing with manual segmentations, the Dice similarity indices were 0.84, 0.85 and 0.87 and the correlation coefficients for the volumes were 0.84, 0.92 and 0.96 for the three methods tested. Our results show clearly the importance of probabilistic atlases in segmentation.",

keywords = "segmentation, atlas, brain",

author = "Jyrki L{\"o}tj{\"o}nen and Robin Wolz and Juha Koikkalainen and Lennart Thurfjell and Roger Lundqvist and Gunhild Waldemar and Hilkka Soininen and Daniel Rueckert",

note = "Project code: 18493 Project code: 71992; 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2011, ISBI 2011 ; Conference date: 30-03-2011 Through 02-04-2011",

year = "2011",

doi = "10.1109/ISBI.2011.5872765",

language = "English",

isbn = "978-1-4244-4127-3",

pages = "1839--1842",

booktitle = "2011 IEEE International Symposium on Biomedical Imaging",

publisher = "IEEE Institute of Electrical and Electronic Engineers",

address = "United States",

}

Lötjönen, J, Wolz, R, Koikkalainen, J, Thurfjell, L, Lundqvist, R, Waldemar, G, Soininen, H & Rueckert, D 2011, Improved generation of probabilistic atlases for the expectation maximization classification. in 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro. IEEE Institute of Electrical and Electronic Engineers, Piscataway, pp. 1839-1842, 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2011, Chicago, IL, United States, 30/03/11. https://doi.org/10.1109/ISBI.2011.5872765

Improved generation of probabilistic atlases for the expectation maximization classification. / Lötjönen, Jyrki; Wolz, Robin; Koikkalainen, Juha et al.
2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro. Piscataway: IEEE Institute of Electrical and Electronic Engineers, 2011. p. 1839-1842.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Improved generation of probabilistic atlases for the expectation maximization classification

AU - Lötjönen, Jyrki

AU - Wolz, Robin

AU - Koikkalainen, Juha

AU - Thurfjell, Lennart

AU - Lundqvist, Roger

AU - Waldemar, Gunhild

AU - Soininen, Hilkka

AU - Rueckert, Daniel

N1 - Project code: 18493 Project code: 71992

PY - 2011

Y1 - 2011

N2 - Probabilistic atlases present prior knowledge about the spatial distribution of various structures or tissues in a population, used commonly in segmentation. We propose three methods for generating probabilistic atlases: 1) the atlases are constructed in a template space using dense non-rigid transformations and transformed to the space of unseen data, 2) as the method 1 but atlas selection is performed in addition, and 3) the atlases are constructed directly in the space of the unseen data. The methods were evaluated in the segmentation of hippocampus from 340 ADNI cases. When comparing with manual segmentations, the Dice similarity indices were 0.84, 0.85 and 0.87 and the correlation coefficients for the volumes were 0.84, 0.92 and 0.96 for the three methods tested. Our results show clearly the importance of probabilistic atlases in segmentation.

AB - Probabilistic atlases present prior knowledge about the spatial distribution of various structures or tissues in a population, used commonly in segmentation. We propose three methods for generating probabilistic atlases: 1) the atlases are constructed in a template space using dense non-rigid transformations and transformed to the space of unseen data, 2) as the method 1 but atlas selection is performed in addition, and 3) the atlases are constructed directly in the space of the unseen data. The methods were evaluated in the segmentation of hippocampus from 340 ADNI cases. When comparing with manual segmentations, the Dice similarity indices were 0.84, 0.85 and 0.87 and the correlation coefficients for the volumes were 0.84, 0.92 and 0.96 for the three methods tested. Our results show clearly the importance of probabilistic atlases in segmentation.

KW - segmentation

KW - atlas

KW - brain

U2 - 10.1109/ISBI.2011.5872765

DO - 10.1109/ISBI.2011.5872765

M3 - Conference article in proceedings

SN - 978-1-4244-4127-3

SP - 1839

EP - 1842

BT - 2011 IEEE International Symposium on Biomedical Imaging

PB - IEEE Institute of Electrical and Electronic Engineers

CY - Piscataway

T2 - 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2011

Y2 - 30 March 2011 through 2 April 2011

ER -

Lötjönen J, Wolz R, Koikkalainen J, Thurfjell L, Lundqvist R, Waldemar G et al. Improved generation of probabilistic atlases for the expectation maximization classification. In 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro. Piscataway: IEEE Institute of Electrical and Electronic Engineers. 2011. p. 1839-1842 doi: 10.1109/ISBI.2011.5872765

Improved generation of probabilistic atlases for the expectation maximization classification

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this