Hippocampal atrophy rate using an expectation maximization classifier with a disease-specific prior

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

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

1 Citation (Scopus)

Abstract

Hippocampal atrophy is a well-known characteristic associated with Alzheimer's disease. In this work, we propose a 4D Expectation Maximization framework for measuring the atrophy rate of the hippocampus from serial magnetic resonance images. One novelty of the framework is a disease-specific prior that regularizes the segmentation near the borders of the hippocampus. Regions where the hippocampus tends to get larger in the follow-up images than in the baseline are penalized. Using the ADNI cohort, we obtained classification accuracies of 83 % for healthy control and Alzheimer's disease patient groups and 60 % for stable and progressive MCI groups using the baseline and 12-month follow-up images.
Original languageEnglish
Title of host publicationProceedings
Subtitle of host publicationIEEE International Symposium on Biomedical Imaging, ISBI 2012
PublisherIEEE Institute of Electrical and Electronic Engineers
Pages1164-1167
ISBN (Electronic)978-1-4577-1858-8
ISBN (Print)978-1-4577-1857-1
DOIs
Publication statusPublished - 2012
MoE publication typeNot Eligible
Event9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012 - Barcelona, Spain
Duration: 2 May 20125 May 2012
Conference number: 9

Conference

Conference9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012
Abbreviated titleISBI 2012
CountrySpain
CityBarcelona
Period2/05/125/05/12

Fingerprint

Classifiers
Magnetic resonance

Keywords

  • Alzheimer's disease
  • atrophy rate
  • expectation maximization classifier
  • segmentation

Cite this

Lötjönen, J., Wolz, R., Koikkalainen, J., Manna, V., Ledig, C., Thurfjell, L., ... Rueckert, D. (2012). Hippocampal atrophy rate using an expectation maximization classifier with a disease-specific prior. In Proceedings: IEEE International Symposium on Biomedical Imaging, ISBI 2012 (pp. 1164-1167). IEEE Institute of Electrical and Electronic Engineers . https://doi.org/10.1109/ISBI.2012.6235767
Lötjönen, Jyrki ; Wolz, Robin ; Koikkalainen, Juha ; Manna, Valeria ; Ledig, Christian ; Thurfjell, Lennart ; Lundqvist, Roger ; Waldemar, Gunhild ; Soininen, Hilkka ; Rueckert, Daniel. / Hippocampal atrophy rate using an expectation maximization classifier with a disease-specific prior. Proceedings: IEEE International Symposium on Biomedical Imaging, ISBI 2012. IEEE Institute of Electrical and Electronic Engineers , 2012. pp. 1164-1167
@inproceedings{7d29a5e8ba564532b7d74913700426ec,
title = "Hippocampal atrophy rate using an expectation maximization classifier with a disease-specific prior",
abstract = "Hippocampal atrophy is a well-known characteristic associated with Alzheimer's disease. In this work, we propose a 4D Expectation Maximization framework for measuring the atrophy rate of the hippocampus from serial magnetic resonance images. One novelty of the framework is a disease-specific prior that regularizes the segmentation near the borders of the hippocampus. Regions where the hippocampus tends to get larger in the follow-up images than in the baseline are penalized. Using the ADNI cohort, we obtained classification accuracies of 83 {\%} for healthy control and Alzheimer's disease patient groups and 60 {\%} for stable and progressive MCI groups using the baseline and 12-month follow-up images.",
keywords = "Alzheimer's disease, atrophy rate, expectation maximization classifier, segmentation",
author = "Jyrki L{\"o}tj{\"o}nen and Robin Wolz and Juha Koikkalainen and Valeria Manna and Christian Ledig and Lennart Thurfjell and Roger Lundqvist and Gunhild Waldemar and Hilkka Soininen and Daniel Rueckert",
note = "Project code: 18493 Project code: 71992",
year = "2012",
doi = "10.1109/ISBI.2012.6235767",
language = "English",
isbn = "978-1-4577-1857-1",
pages = "1164--1167",
booktitle = "Proceedings",
publisher = "IEEE Institute of Electrical and Electronic Engineers",
address = "United States",

}

Lötjönen, J, Wolz, R, Koikkalainen, J, Manna, V, Ledig, C, Thurfjell, L, Lundqvist, R, Waldemar, G, Soininen, H & Rueckert, D 2012, Hippocampal atrophy rate using an expectation maximization classifier with a disease-specific prior. in Proceedings: IEEE International Symposium on Biomedical Imaging, ISBI 2012. IEEE Institute of Electrical and Electronic Engineers , pp. 1164-1167, 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012, Barcelona, Spain, 2/05/12. https://doi.org/10.1109/ISBI.2012.6235767

Hippocampal atrophy rate using an expectation maximization classifier with a disease-specific prior. / Lötjönen, Jyrki; Wolz, Robin; Koikkalainen, Juha; Manna, Valeria; Ledig, Christian; Thurfjell, Lennart; Lundqvist, Roger; Waldemar, Gunhild; Soininen, Hilkka; Rueckert, Daniel.

Proceedings: IEEE International Symposium on Biomedical Imaging, ISBI 2012. IEEE Institute of Electrical and Electronic Engineers , 2012. p. 1164-1167.

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

TY - GEN

T1 - Hippocampal atrophy rate using an expectation maximization classifier with a disease-specific prior

AU - Lötjönen, Jyrki

AU - Wolz, Robin

AU - Koikkalainen, Juha

AU - Manna, Valeria

AU - Ledig, Christian

AU - Thurfjell, Lennart

AU - Lundqvist, Roger

AU - Waldemar, Gunhild

AU - Soininen, Hilkka

AU - Rueckert, Daniel

N1 - Project code: 18493 Project code: 71992

PY - 2012

Y1 - 2012

N2 - Hippocampal atrophy is a well-known characteristic associated with Alzheimer's disease. In this work, we propose a 4D Expectation Maximization framework for measuring the atrophy rate of the hippocampus from serial magnetic resonance images. One novelty of the framework is a disease-specific prior that regularizes the segmentation near the borders of the hippocampus. Regions where the hippocampus tends to get larger in the follow-up images than in the baseline are penalized. Using the ADNI cohort, we obtained classification accuracies of 83 % for healthy control and Alzheimer's disease patient groups and 60 % for stable and progressive MCI groups using the baseline and 12-month follow-up images.

AB - Hippocampal atrophy is a well-known characteristic associated with Alzheimer's disease. In this work, we propose a 4D Expectation Maximization framework for measuring the atrophy rate of the hippocampus from serial magnetic resonance images. One novelty of the framework is a disease-specific prior that regularizes the segmentation near the borders of the hippocampus. Regions where the hippocampus tends to get larger in the follow-up images than in the baseline are penalized. Using the ADNI cohort, we obtained classification accuracies of 83 % for healthy control and Alzheimer's disease patient groups and 60 % for stable and progressive MCI groups using the baseline and 12-month follow-up images.

KW - Alzheimer's disease

KW - atrophy rate

KW - expectation maximization classifier

KW - segmentation

U2 - 10.1109/ISBI.2012.6235767

DO - 10.1109/ISBI.2012.6235767

M3 - Conference article in proceedings

SN - 978-1-4577-1857-1

SP - 1164

EP - 1167

BT - Proceedings

PB - IEEE Institute of Electrical and Electronic Engineers

ER -

Lötjönen J, Wolz R, Koikkalainen J, Manna V, Ledig C, Thurfjell L et al. Hippocampal atrophy rate using an expectation maximization classifier with a disease-specific prior. In Proceedings: IEEE International Symposium on Biomedical Imaging, ISBI 2012. IEEE Institute of Electrical and Electronic Engineers . 2012. p. 1164-1167 https://doi.org/10.1109/ISBI.2012.6235767