Extended boundary shift integral

Jyrki Lötjönen, Christian Ledig, Juha Koikkalainen, Robin Wolz, Lennart Thurfjell, Hilkka Soininen, Sébastien Ourselin, Daniel Rueckert

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

1 Citation (Scopus)

Abstract

The boundary shift integral (BSI) is a widely used method for measuring atrophy rate, dynamic changes of the gray-matter and cerebrospinal fluid boundaries in magnetic resonance images. BSI is based on intensity differences on this boundary region. This work extends the method in two respects: 1) Instead of using only intensity information on the boundary region, a probabilistic approach is proposed in which also other characteristics of the boundary region can be used. 2) The use of the probabilistic model enables to measure changes between any structures or combination of structures in the image. The performance of the extended BSI is verified against standard BSI in the ADNI and AIBL cohorts. The area-under-the-curve is clearly above 90 % in both cohorts when comparing the classification between cognitively normal and Alzheimer's disease groups. The accuracies of the extended BSI were higher than the standard BSI between these groups.
Original languageEnglish
Title of host publicationIEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
PublisherIEEE Institute of Electrical and Electronic Engineers
Pages854-857
ISBN (Electronic)978-1-4673-1961-4
ISBN (Print)978-1-4673-1959-1
DOIs
Publication statusPublished - 2014
MoE publication typeA4 Article in a conference publication
Event11th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2014 - Peking, China
Duration: 29 Apr 20142 May 2014

Conference

Conference11th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2014
Abbreviated titleISBI 2014
CountryChina
CityPeking
Period29/04/142/05/14

Fingerprint

Cerebrospinal fluid
Magnetic resonance
Statistical Models

Keywords

  • boundary shift integral
  • atrophy rate

Cite this

Lötjönen, J., Ledig, C., Koikkalainen, J., Wolz, R., Thurfjell, L., Soininen, H., ... Rueckert, D. (2014). Extended boundary shift integral. In IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014 (pp. 854-857). IEEE Institute of Electrical and Electronic Engineers . https://doi.org/10.1109/ISBI.2014.6868005
Lötjönen, Jyrki ; Ledig, Christian ; Koikkalainen, Juha ; Wolz, Robin ; Thurfjell, Lennart ; Soininen, Hilkka ; Ourselin, Sébastien ; Rueckert, Daniel. / Extended boundary shift integral. IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. IEEE Institute of Electrical and Electronic Engineers , 2014. pp. 854-857
@inproceedings{a31345624e4e4decb58553db2ab8d0c1,
title = "Extended boundary shift integral",
abstract = "The boundary shift integral (BSI) is a widely used method for measuring atrophy rate, dynamic changes of the gray-matter and cerebrospinal fluid boundaries in magnetic resonance images. BSI is based on intensity differences on this boundary region. This work extends the method in two respects: 1) Instead of using only intensity information on the boundary region, a probabilistic approach is proposed in which also other characteristics of the boundary region can be used. 2) The use of the probabilistic model enables to measure changes between any structures or combination of structures in the image. The performance of the extended BSI is verified against standard BSI in the ADNI and AIBL cohorts. The area-under-the-curve is clearly above 90 {\%} in both cohorts when comparing the classification between cognitively normal and Alzheimer's disease groups. The accuracies of the extended BSI were higher than the standard BSI between these groups.",
keywords = "boundary shift integral, atrophy rate",
author = "Jyrki L{\"o}tj{\"o}nen and Christian Ledig and Juha Koikkalainen and Robin Wolz and Lennart Thurfjell and Hilkka Soininen and S{\'e}bastien Ourselin and Daniel Rueckert",
note = "Project code: 71992",
year = "2014",
doi = "10.1109/ISBI.2014.6868005",
language = "English",
isbn = "978-1-4673-1959-1",
pages = "854--857",
booktitle = "IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014",
publisher = "IEEE Institute of Electrical and Electronic Engineers",
address = "United States",

}

Lötjönen, J, Ledig, C, Koikkalainen, J, Wolz, R, Thurfjell, L, Soininen, H, Ourselin, S & Rueckert, D 2014, Extended boundary shift integral. in IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. IEEE Institute of Electrical and Electronic Engineers , pp. 854-857, 11th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2014, Peking, China, 29/04/14. https://doi.org/10.1109/ISBI.2014.6868005

Extended boundary shift integral. / Lötjönen, Jyrki; Ledig, Christian; Koikkalainen, Juha; Wolz, Robin; Thurfjell, Lennart; Soininen, Hilkka; Ourselin, Sébastien; Rueckert, Daniel.

IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. IEEE Institute of Electrical and Electronic Engineers , 2014. p. 854-857.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Extended boundary shift integral

AU - Lötjönen, Jyrki

AU - Ledig, Christian

AU - Koikkalainen, Juha

AU - Wolz, Robin

AU - Thurfjell, Lennart

AU - Soininen, Hilkka

AU - Ourselin, Sébastien

AU - Rueckert, Daniel

N1 - Project code: 71992

PY - 2014

Y1 - 2014

N2 - The boundary shift integral (BSI) is a widely used method for measuring atrophy rate, dynamic changes of the gray-matter and cerebrospinal fluid boundaries in magnetic resonance images. BSI is based on intensity differences on this boundary region. This work extends the method in two respects: 1) Instead of using only intensity information on the boundary region, a probabilistic approach is proposed in which also other characteristics of the boundary region can be used. 2) The use of the probabilistic model enables to measure changes between any structures or combination of structures in the image. The performance of the extended BSI is verified against standard BSI in the ADNI and AIBL cohorts. The area-under-the-curve is clearly above 90 % in both cohorts when comparing the classification between cognitively normal and Alzheimer's disease groups. The accuracies of the extended BSI were higher than the standard BSI between these groups.

AB - The boundary shift integral (BSI) is a widely used method for measuring atrophy rate, dynamic changes of the gray-matter and cerebrospinal fluid boundaries in magnetic resonance images. BSI is based on intensity differences on this boundary region. This work extends the method in two respects: 1) Instead of using only intensity information on the boundary region, a probabilistic approach is proposed in which also other characteristics of the boundary region can be used. 2) The use of the probabilistic model enables to measure changes between any structures or combination of structures in the image. The performance of the extended BSI is verified against standard BSI in the ADNI and AIBL cohorts. The area-under-the-curve is clearly above 90 % in both cohorts when comparing the classification between cognitively normal and Alzheimer's disease groups. The accuracies of the extended BSI were higher than the standard BSI between these groups.

KW - boundary shift integral

KW - atrophy rate

U2 - 10.1109/ISBI.2014.6868005

DO - 10.1109/ISBI.2014.6868005

M3 - Conference article in proceedings

SN - 978-1-4673-1959-1

SP - 854

EP - 857

BT - IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014

PB - IEEE Institute of Electrical and Electronic Engineers

ER -

Lötjönen J, Ledig C, Koikkalainen J, Wolz R, Thurfjell L, Soininen H et al. Extended boundary shift integral. In IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. IEEE Institute of Electrical and Electronic Engineers . 2014. p. 854-857 https://doi.org/10.1109/ISBI.2014.6868005