Quantified brain asymmetry for age estimation of normal and AD/MCI subjects

L. A. Teverovskiy, J. T. Becker, O. L. Lopez, Y. Liu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

We propose a quantified asymmetry based method for age estimation. Our method uses machine learning to discover automatically the most discriminative asymmetry feature set from different brain regions and image scales. Applying this regression model on a T1 MR brain image set of 246 healthy individuals (121 females; 125 males, 66 ± 7.5 years old), we achieve a mean absolute error of 5.4 years and a mean signed error of -0.2 years for age estimation on unseen MR images using the stringent leave-15%-out cross validation. Our results show significant changes in asymmetry with aging in the following regions: the posterior horns of the lateral ventricles, the amygdala, the ventral putamen with a nearby region of the anterior inferior caudate nucleus, the basal forebrain, hyppocampus and parahyppocampal regions. We confirm the validity of the age estimation model using permutation test on 30 replicas of the original dataset with randomly permuted ages (with p-value < 0.001). Furthermore, we apply this model to a separate set of MR images containing normal, Alzheimer's disease (AD) and mild cognitive impairment (MCI) subjects. Our results reflect the relative severity of brain pathology between the three subject groups: mean signed age estimation error is 0.6 years for normal controls, 2.2 years for MCI patients, and 4.7 years for AD patients.

Original languageEnglish (US)
Title of host publication2008 5th IEEE International Symposium on Biomedical Imaging
Subtitle of host publicationFrom Nano to Macro, Proceedings, ISBI
Pages1509-1512
Number of pages4
DOIs
StatePublished - Sep 10 2008
Event2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI - Paris, France
Duration: May 14 2008May 17 2008

Publication series

Name2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI

Other

Other2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI
CountryFrance
CityParis
Period5/14/085/17/08

Fingerprint

Brain
Pathology
Error analysis
Learning systems
Aging of materials

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering

Cite this

Teverovskiy, L. A., Becker, J. T., Lopez, O. L., & Liu, Y. (2008). Quantified brain asymmetry for age estimation of normal and AD/MCI subjects. In 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI (pp. 1509-1512). [4541295] (2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI). https://doi.org/10.1109/ISBI.2008.4541295
Teverovskiy, L. A. ; Becker, J. T. ; Lopez, O. L. ; Liu, Y. / Quantified brain asymmetry for age estimation of normal and AD/MCI subjects. 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI. 2008. pp. 1509-1512 (2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI).
@inproceedings{a29416b51494450b9f95991919b2e8a2,
title = "Quantified brain asymmetry for age estimation of normal and AD/MCI subjects",
abstract = "We propose a quantified asymmetry based method for age estimation. Our method uses machine learning to discover automatically the most discriminative asymmetry feature set from different brain regions and image scales. Applying this regression model on a T1 MR brain image set of 246 healthy individuals (121 females; 125 males, 66 ± 7.5 years old), we achieve a mean absolute error of 5.4 years and a mean signed error of -0.2 years for age estimation on unseen MR images using the stringent leave-15{\%}-out cross validation. Our results show significant changes in asymmetry with aging in the following regions: the posterior horns of the lateral ventricles, the amygdala, the ventral putamen with a nearby region of the anterior inferior caudate nucleus, the basal forebrain, hyppocampus and parahyppocampal regions. We confirm the validity of the age estimation model using permutation test on 30 replicas of the original dataset with randomly permuted ages (with p-value < 0.001). Furthermore, we apply this model to a separate set of MR images containing normal, Alzheimer's disease (AD) and mild cognitive impairment (MCI) subjects. Our results reflect the relative severity of brain pathology between the three subject groups: mean signed age estimation error is 0.6 years for normal controls, 2.2 years for MCI patients, and 4.7 years for AD patients.",
author = "Teverovskiy, {L. A.} and Becker, {J. T.} and Lopez, {O. L.} and Y. Liu",
year = "2008",
month = "9",
day = "10",
doi = "10.1109/ISBI.2008.4541295",
language = "English (US)",
isbn = "9781424420032",
series = "2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI",
pages = "1509--1512",
booktitle = "2008 5th IEEE International Symposium on Biomedical Imaging",

}

Teverovskiy, LA, Becker, JT, Lopez, OL & Liu, Y 2008, Quantified brain asymmetry for age estimation of normal and AD/MCI subjects. in 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI., 4541295, 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI, pp. 1509-1512, 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI, Paris, France, 5/14/08. https://doi.org/10.1109/ISBI.2008.4541295

Quantified brain asymmetry for age estimation of normal and AD/MCI subjects. / Teverovskiy, L. A.; Becker, J. T.; Lopez, O. L.; Liu, Y.

2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI. 2008. p. 1509-1512 4541295 (2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Quantified brain asymmetry for age estimation of normal and AD/MCI subjects

AU - Teverovskiy, L. A.

AU - Becker, J. T.

AU - Lopez, O. L.

AU - Liu, Y.

PY - 2008/9/10

Y1 - 2008/9/10

N2 - We propose a quantified asymmetry based method for age estimation. Our method uses machine learning to discover automatically the most discriminative asymmetry feature set from different brain regions and image scales. Applying this regression model on a T1 MR brain image set of 246 healthy individuals (121 females; 125 males, 66 ± 7.5 years old), we achieve a mean absolute error of 5.4 years and a mean signed error of -0.2 years for age estimation on unseen MR images using the stringent leave-15%-out cross validation. Our results show significant changes in asymmetry with aging in the following regions: the posterior horns of the lateral ventricles, the amygdala, the ventral putamen with a nearby region of the anterior inferior caudate nucleus, the basal forebrain, hyppocampus and parahyppocampal regions. We confirm the validity of the age estimation model using permutation test on 30 replicas of the original dataset with randomly permuted ages (with p-value < 0.001). Furthermore, we apply this model to a separate set of MR images containing normal, Alzheimer's disease (AD) and mild cognitive impairment (MCI) subjects. Our results reflect the relative severity of brain pathology between the three subject groups: mean signed age estimation error is 0.6 years for normal controls, 2.2 years for MCI patients, and 4.7 years for AD patients.

AB - We propose a quantified asymmetry based method for age estimation. Our method uses machine learning to discover automatically the most discriminative asymmetry feature set from different brain regions and image scales. Applying this regression model on a T1 MR brain image set of 246 healthy individuals (121 females; 125 males, 66 ± 7.5 years old), we achieve a mean absolute error of 5.4 years and a mean signed error of -0.2 years for age estimation on unseen MR images using the stringent leave-15%-out cross validation. Our results show significant changes in asymmetry with aging in the following regions: the posterior horns of the lateral ventricles, the amygdala, the ventral putamen with a nearby region of the anterior inferior caudate nucleus, the basal forebrain, hyppocampus and parahyppocampal regions. We confirm the validity of the age estimation model using permutation test on 30 replicas of the original dataset with randomly permuted ages (with p-value < 0.001). Furthermore, we apply this model to a separate set of MR images containing normal, Alzheimer's disease (AD) and mild cognitive impairment (MCI) subjects. Our results reflect the relative severity of brain pathology between the three subject groups: mean signed age estimation error is 0.6 years for normal controls, 2.2 years for MCI patients, and 4.7 years for AD patients.

UR - http://www.scopus.com/inward/record.url?scp=51049109621&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51049109621&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2008.4541295

DO - 10.1109/ISBI.2008.4541295

M3 - Conference contribution

AN - SCOPUS:51049109621

SN - 9781424420032

T3 - 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI

SP - 1509

EP - 1512

BT - 2008 5th IEEE International Symposium on Biomedical Imaging

ER -

Teverovskiy LA, Becker JT, Lopez OL, Liu Y. Quantified brain asymmetry for age estimation of normal and AD/MCI subjects. In 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI. 2008. p. 1509-1512. 4541295. (2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI). https://doi.org/10.1109/ISBI.2008.4541295