Robustness and sensitivity of hotelling's T2-based permutation tests for selection of 3D morphological markers

L. Ferrarini; G. B. Frisoni; M. Pievani; R. Ganzola; J. H C Reiber; J. Milles

doi:10.1109/ISBI.2010.5490414

Robustness and sensitivity of hotelling's T2-based permutation tests for selection of 3D morphological markers

L. Ferrarini, G. B. Frisoni, M. Pievani, R. Ganzola, J. H C Reiber, J. Milles

Centro San Giovanni di Dio - Fatebenefratelli

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

Abstract

Multivariate statistics are a powerful tool to analyze morphological changes in three-dimensional brain structures. The Hotelling's T² (HT²) statistic has previously been used to this purpose. HT ² is a parametric test which assumes normal distribution of the data: when this does not hold, as often happens for shape analysis, the test can still be used as basis for nonparametric permutation tests (PT). In their approximate version, PT are nondeterministic, being affected by the randomly pooled subset of permutations. In this study, we investigate the sensitivity and robustness of HT²-based PT, with respect to nondeterministic effects, both on simulated data and a medical application: the detection of hippocampal morphological changes to accurately predict conversion to Alzheimer's disease. The sensitivity of PT increases significantly with larger sample size, while is less dependent on the number of permutations. Moreover, PT provides statistically consistent classification performances: 80% accuracy in predicting conversion to Alzheimer's disease.

Original language	English
Title of host publication	2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings
Pages	57-60
Number of pages	4
DOIs	https://doi.org/10.1109/ISBI.2010.5490414
Publication status	Published - 2010
Event	7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Rotterdam, Netherlands Duration: Apr 14 2010 → Apr 17 2010

Other

Other	7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010
Country	Netherlands
City	Rotterdam
Period	4/14/10 → 4/17/10

ASJC Scopus subject areas

Biomedical Engineering
Radiology Nuclear Medicine and imaging

Access to Document

10.1109/ISBI.2010.5490414

Fingerprint Dive into the research topics of 'Robustness and sensitivity of hotelling's T2-based permutation tests for selection of 3D morphological markers'. Together they form a unique fingerprint.

Cite this

Ferrarini, L., Frisoni, G. B., Pievani, M., Ganzola, R., Reiber, J. H. C., & Milles, J. (2010). Robustness and sensitivity of hotelling's T2-based permutation tests for selection of 3D morphological markers. In 2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings (pp. 57-60). [5490414] https://doi.org/10.1109/ISBI.2010.5490414

Robustness and sensitivity of hotelling's T2-based permutation tests for selection of 3D morphological markers. / Ferrarini, L.; Frisoni, G. B.; Pievani, M.; Ganzola, R.; Reiber, J. H C; Milles, J.

2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings. 2010. p. 57-60 5490414.

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

Ferrarini, L, Frisoni, GB , Pievani, M, Ganzola, R, Reiber, JHC & Milles, J 2010, Robustness and sensitivity of hotelling's T2-based permutation tests for selection of 3D morphological markers. in 2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings., 5490414, pp. 57-60, 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010, Rotterdam, Netherlands, 4/14/10. https://doi.org/10.1109/ISBI.2010.5490414

@inproceedings{466be4710fcb48779c909256e48c7609,

title = "Robustness and sensitivity of hotelling's T2-based permutation tests for selection of 3D morphological markers",

abstract = "Multivariate statistics are a powerful tool to analyze morphological changes in three-dimensional brain structures. The Hotelling's T2 (HT2) statistic has previously been used to this purpose. HT 2 is a parametric test which assumes normal distribution of the data: when this does not hold, as often happens for shape analysis, the test can still be used as basis for nonparametric permutation tests (PT). In their approximate version, PT are nondeterministic, being affected by the randomly pooled subset of permutations. In this study, we investigate the sensitivity and robustness of HT2-based PT, with respect to nondeterministic effects, both on simulated data and a medical application: the detection of hippocampal morphological changes to accurately predict conversion to Alzheimer's disease. The sensitivity of PT increases significantly with larger sample size, while is less dependent on the number of permutations. Moreover, PT provides statistically consistent classification performances: 80% accuracy in predicting conversion to Alzheimer's disease.",

author = "L. Ferrarini and Frisoni, {G. B.} and M. Pievani and R. Ganzola and Reiber, {J. H C} and J. Milles",

year = "2010",

doi = "10.1109/ISBI.2010.5490414",

language = "English",

isbn = "9781424441266",

pages = "57--60",

booktitle = "2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings",

note = "7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 ; Conference date: 14-04-2010 Through 17-04-2010",

}

TY - GEN

T1 - Robustness and sensitivity of hotelling's T2-based permutation tests for selection of 3D morphological markers

AU - Ferrarini, L.

AU - Frisoni, G. B.

AU - Pievani, M.

AU - Ganzola, R.

AU - Reiber, J. H C

AU - Milles, J.

PY - 2010

Y1 - 2010

N2 - Multivariate statistics are a powerful tool to analyze morphological changes in three-dimensional brain structures. The Hotelling's T2 (HT2) statistic has previously been used to this purpose. HT 2 is a parametric test which assumes normal distribution of the data: when this does not hold, as often happens for shape analysis, the test can still be used as basis for nonparametric permutation tests (PT). In their approximate version, PT are nondeterministic, being affected by the randomly pooled subset of permutations. In this study, we investigate the sensitivity and robustness of HT2-based PT, with respect to nondeterministic effects, both on simulated data and a medical application: the detection of hippocampal morphological changes to accurately predict conversion to Alzheimer's disease. The sensitivity of PT increases significantly with larger sample size, while is less dependent on the number of permutations. Moreover, PT provides statistically consistent classification performances: 80% accuracy in predicting conversion to Alzheimer's disease.

AB - Multivariate statistics are a powerful tool to analyze morphological changes in three-dimensional brain structures. The Hotelling's T2 (HT2) statistic has previously been used to this purpose. HT 2 is a parametric test which assumes normal distribution of the data: when this does not hold, as often happens for shape analysis, the test can still be used as basis for nonparametric permutation tests (PT). In their approximate version, PT are nondeterministic, being affected by the randomly pooled subset of permutations. In this study, we investigate the sensitivity and robustness of HT2-based PT, with respect to nondeterministic effects, both on simulated data and a medical application: the detection of hippocampal morphological changes to accurately predict conversion to Alzheimer's disease. The sensitivity of PT increases significantly with larger sample size, while is less dependent on the number of permutations. Moreover, PT provides statistically consistent classification performances: 80% accuracy in predicting conversion to Alzheimer's disease.

UR - http://www.scopus.com/inward/record.url?scp=77955183419&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955183419&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2010.5490414

DO - 10.1109/ISBI.2010.5490414

M3 - Conference contribution

AN - SCOPUS:77955183419

SN - 9781424441266

SP - 57

EP - 60

BT - 2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings

T2 - 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010

Y2 - 14 April 2010 through 17 April 2010

ER -