Quantifying brain development in early childhood using segmentation and registration

P. Aljabar; K. K. Bhatia; M. Murgasova; J. V. Hajnal; J. P. Boardman; L. Srinivasan; M. A. Rutherford; L. E. Dyet; A. D. Edwards; D. Rueckert

doi:10.1117/12.706508

Quantifying brain development in early childhood using segmentation and registration

P. Aljabar, K. K. Bhatia, M. Murgasova, J. V. Hajnal, J. P. Boardman, L. Srinivasan, M. A. Rutherford, L. E. Dyet, A. D. Edwards, D. Rueckert

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

Abstract

In this work we obtain estimates of tissue growth using longitudinal data comprising MR brain images of 25 preterm children scanned at one and two years. The growth estimates are obtained using segmentation and registration based methods. The segmentation approach used an expectation maximisation (EM) method to classify tissue types and the registration approach used tensor based morphometry (TBM) applied to a free form deformation (FFD) model. The two methods show very good agreement indicating that the registration and segmentation approaches can be used interchangeably. The advantage of the registration based method, however, is that it can provide more local estimates of tissue growth. This is the first longitudinal study of growth in early childhood, previous longitudinal studies have focussed on later periods during childhood.

Original language	English
Title of host publication	Medical Imaging 2007
Subtitle of host publication	Image Processing
Edition	PART 1
DOIs	https://doi.org/10.1117/12.706508
State	Published - 2007
Externally published	Yes
Event	Medical Imaging 2007: Image Processing - San Diego, CA, United States Duration: 18 Feb 2007 → 20 Feb 2007

Publication series

Name	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Number	PART 1
Volume	6512
ISSN (Print)	1605-7422

Conference

Conference	Medical Imaging 2007: Image Processing
Country/Territory	United States
City	San Diego, CA
Period	18/02/07 → 20/02/07

Keywords

Growth
Registration
Segmentation

Access to Document

10.1117/12.706508

Cite this

Aljabar, P., Bhatia, K. K., Murgasova, M., Hajnal, J. V., Boardman, J. P., Srinivasan, L., Rutherford, M. A., Dyet, L. E., Edwards, A. D., & Rueckert, D. (2007). Quantifying brain development in early childhood using segmentation and registration. In Medical Imaging 2007: Image Processing (PART 1 ed.). Article 65120O (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 6512, No. PART 1). https://doi.org/10.1117/12.706508

@inproceedings{6303c5e96d27426b915c138dad94a2a3,

title = "Quantifying brain development in early childhood using segmentation and registration",

abstract = "In this work we obtain estimates of tissue growth using longitudinal data comprising MR brain images of 25 preterm children scanned at one and two years. The growth estimates are obtained using segmentation and registration based methods. The segmentation approach used an expectation maximisation (EM) method to classify tissue types and the registration approach used tensor based morphometry (TBM) applied to a free form deformation (FFD) model. The two methods show very good agreement indicating that the registration and segmentation approaches can be used interchangeably. The advantage of the registration based method, however, is that it can provide more local estimates of tissue growth. This is the first longitudinal study of growth in early childhood, previous longitudinal studies have focussed on later periods during childhood.",

keywords = "Growth, Registration, Segmentation",

author = "P. Aljabar and Bhatia, {K. K.} and M. Murgasova and Hajnal, {J. V.} and Boardman, {J. P.} and L. Srinivasan and Rutherford, {M. A.} and Dyet, {L. E.} and Edwards, {A. D.} and D. Rueckert",

year = "2007",

doi = "10.1117/12.706508",

language = "English",

isbn = "0819466301",

series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

number = "PART 1",

booktitle = "Medical Imaging 2007",

edition = "PART 1",

note = "Medical Imaging 2007: Image Processing ; Conference date: 18-02-2007 Through 20-02-2007",

}

Aljabar, P, Bhatia, KK, Murgasova, M, Hajnal, JV, Boardman, JP, Srinivasan, L, Rutherford, MA, Dyet, LE, Edwards, AD & Rueckert, D 2007, Quantifying brain development in early childhood using segmentation and registration. in Medical Imaging 2007: Image Processing. PART 1 edn, 65120O, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, no. PART 1, vol. 6512, Medical Imaging 2007: Image Processing, San Diego, CA, United States, 18/02/07. https://doi.org/10.1117/12.706508

Quantifying brain development in early childhood using segmentation and registration. / Aljabar, P.; Bhatia, K. K.; Murgasova, M. et al.
Medical Imaging 2007: Image Processing. PART 1. ed. 2007. 65120O (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 6512, No. PART 1).

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

TY - GEN

T1 - Quantifying brain development in early childhood using segmentation and registration

AU - Aljabar, P.

AU - Bhatia, K. K.

AU - Murgasova, M.

AU - Hajnal, J. V.

AU - Boardman, J. P.

AU - Srinivasan, L.

AU - Rutherford, M. A.

AU - Dyet, L. E.

AU - Edwards, A. D.

AU - Rueckert, D.

PY - 2007

Y1 - 2007

N2 - In this work we obtain estimates of tissue growth using longitudinal data comprising MR brain images of 25 preterm children scanned at one and two years. The growth estimates are obtained using segmentation and registration based methods. The segmentation approach used an expectation maximisation (EM) method to classify tissue types and the registration approach used tensor based morphometry (TBM) applied to a free form deformation (FFD) model. The two methods show very good agreement indicating that the registration and segmentation approaches can be used interchangeably. The advantage of the registration based method, however, is that it can provide more local estimates of tissue growth. This is the first longitudinal study of growth in early childhood, previous longitudinal studies have focussed on later periods during childhood.

AB - In this work we obtain estimates of tissue growth using longitudinal data comprising MR brain images of 25 preterm children scanned at one and two years. The growth estimates are obtained using segmentation and registration based methods. The segmentation approach used an expectation maximisation (EM) method to classify tissue types and the registration approach used tensor based morphometry (TBM) applied to a free form deformation (FFD) model. The two methods show very good agreement indicating that the registration and segmentation approaches can be used interchangeably. The advantage of the registration based method, however, is that it can provide more local estimates of tissue growth. This is the first longitudinal study of growth in early childhood, previous longitudinal studies have focussed on later periods during childhood.

KW - Growth

KW - Registration

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=36248977623&partnerID=8YFLogxK

U2 - 10.1117/12.706508

DO - 10.1117/12.706508

M3 - Conference contribution

AN - SCOPUS:36248977623

SN - 0819466301

SN - 9780819466303

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Medical Imaging 2007

T2 - Medical Imaging 2007: Image Processing

Y2 - 18 February 2007 through 20 February 2007

ER -

Quantifying brain development in early childhood using segmentation and registration

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this