Hippocampus segmentation and SPHARM coefficient selection are decisive for MCI detection

A. Uhl; M. Liedlgruber; K. Butz; Yvonne Höller; G. Kuchukhidze; A. Taylor; A. Thomschevski; O. Tomasi; E. Trinka

doi:10.1007/978-3-662-56537-7_65

Hippocampus segmentation and SPHARM coefficient selection are decisive for MCI detection

A. Uhl, M. Liedlgruber, K. Butz, Yvonne Höller, G. Kuchukhidze, A. Taylor, A. Thomschevski, O. Tomasi, E. Trinka

Research output: Contribution to journal › Conference article › peer-review

Abstract

Spherical Harmonics (SPHARM), when computed from hippocampus segmentation, have been shown to be useful features for discriminatingMCI affected patients from healthy controls. In this paper we assess the impact (i) of using different hippocampus segmentation techniques, among them three out-of-the-box automated segmentation tools and three human raters with different qualification, and (ii) of applying different strategies which SPHARM coefficients to submit to SVM-based two-class classification. We find that both choices are crucial for successful classification.

Original language	English
Pages (from-to)	239-244
Number of pages	6
Journal	Informatik aktuell
Issue number	211279
DOIs	https://doi.org/10.1007/978-3-662-56537-7_65
Publication status	Published - 2018
Externally published	Yes
Event	Workshop on Bildverarbeitung fur die Medizin, 2018 - Erlangen, Germany Duration: 11 Mar 2018 → 13 Mar 2018

Bibliographical note

Funding Information: Acknowledgement. This work has been partially supported by the Austrian Science Fund, project no. KLIF 00012. Publisher Copyright: © Springer-Verlag GmbH Deutschland 2018.

Other keywords

Brain
Hippocampus segmentation
Neuroscience

Access to Document

10.1007/978-3-662-56537-7_65

Cite this

@article{8537114ba4fa43278472c3bddd1676a4,

title = "Hippocampus segmentation and SPHARM coefficient selection are decisive for MCI detection",

abstract = "Spherical Harmonics (SPHARM), when computed from hippocampus segmentation, have been shown to be useful features for discriminatingMCI affected patients from healthy controls. In this paper we assess the impact (i) of using different hippocampus segmentation techniques, among them three out-of-the-box automated segmentation tools and three human raters with different qualification, and (ii) of applying different strategies which SPHARM coefficients to submit to SVM-based two-class classification. We find that both choices are crucial for successful classification.",

keywords = "Brain, Hippocampus segmentation, Neuroscience",

author = "A. Uhl and M. Liedlgruber and K. Butz and Yvonne H{\"o}ller and G. Kuchukhidze and A. Taylor and A. Thomschevski and O. Tomasi and E. Trinka",

note = "Funding Information: Acknowledgement. This work has been partially supported by the Austrian Science Fund, project no. KLIF 00012. Publisher Copyright: {\textcopyright} Springer-Verlag GmbH Deutschland 2018.; Workshop on Bildverarbeitung fur die Medizin, 2018 ; Conference date: 11-03-2018 Through 13-03-2018",

year = "2018",

doi = "10.1007/978-3-662-56537-7\_65",

language = "English",

pages = "239--244",

journal = "Informatik aktuell",

issn = "1431-472X",

publisher = "Springer Science and Business Media Deutschland GmbH",

number = "211279",

}

TY - JOUR

T1 - Hippocampus segmentation and SPHARM coefficient selection are decisive for MCI detection

AU - Uhl, A.

AU - Liedlgruber, M.

AU - Butz, K.

AU - Höller, Yvonne

AU - Kuchukhidze, G.

AU - Taylor, A.

AU - Thomschevski, A.

AU - Tomasi, O.

AU - Trinka, E.

N1 - Funding Information: Acknowledgement. This work has been partially supported by the Austrian Science Fund, project no. KLIF 00012. Publisher Copyright: © Springer-Verlag GmbH Deutschland 2018.

PY - 2018

Y1 - 2018

N2 - Spherical Harmonics (SPHARM), when computed from hippocampus segmentation, have been shown to be useful features for discriminatingMCI affected patients from healthy controls. In this paper we assess the impact (i) of using different hippocampus segmentation techniques, among them three out-of-the-box automated segmentation tools and three human raters with different qualification, and (ii) of applying different strategies which SPHARM coefficients to submit to SVM-based two-class classification. We find that both choices are crucial for successful classification.

AB - Spherical Harmonics (SPHARM), when computed from hippocampus segmentation, have been shown to be useful features for discriminatingMCI affected patients from healthy controls. In this paper we assess the impact (i) of using different hippocampus segmentation techniques, among them three out-of-the-box automated segmentation tools and three human raters with different qualification, and (ii) of applying different strategies which SPHARM coefficients to submit to SVM-based two-class classification. We find that both choices are crucial for successful classification.

KW - Brain

KW - Hippocampus segmentation

KW - Neuroscience

UR - https://www.scopus.com/pages/publications/85043348181

U2 - 10.1007/978-3-662-56537-7_65

DO - 10.1007/978-3-662-56537-7_65

M3 - Conference article

SN - 1431-472X

SP - 239

EP - 244

JO - Informatik aktuell

JF - Informatik aktuell

IS - 211279

T2 - Workshop on Bildverarbeitung fur die Medizin, 2018

Y2 - 11 March 2018 through 13 March 2018

ER -

Hippocampus segmentation and SPHARM coefficient selection are decisive for MCI detection

Abstract

Bibliographical note

Other keywords

Access to Document

Fingerprint

Cite this