Classification of in vivo magnetic resonance spectra

Björn H. Menze; Michael Wormit; Peter Bachert; Matthias Lichy; Heinz Peter Schlemmer; Fred A. Hamprecht

doi:10.1007/3-540-28084-7_41

Classification of in vivo magnetic resonance spectra

Björn H. Menze
, Michael Wormit
, Peter Bachert
, Matthias Lichy
, Heinz Peter Schlemmer
, Fred A. Hamprecht

Heidelberg University
German Cancer Research Center
Universitätsklinikum Tübingen

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

3 Scopus citations

Abstract

We present the results of a systematic and quantitative comparison of methods from pattern recognition for the analysis of clinical magnetic resonance spectra. The medical question being addressed is the detection of brain tumor. In this application we find regularized linear methods to be superior to more flexible methods such as support vector machines, neural networks or random forests. The best preprocessing method for our spectral data is a smoothing and subsampling approach.

Original language	English
Title of host publication	Classification - The Ubiquitous Challenge
Subtitle of host publication	Proceedings of the 28th Annual Conference of the Gesellschaft fur Klassifikation e.V., GfKl 2004
Publisher	Kluwer Academic Publishers
Pages	362-369
Number of pages	8
ISBN (Print)	3540256776, 9783540256779
DOIs	https://doi.org/10.1007/3-540-28084-7_41
State	Published - 2005
Externally published	Yes
Event	28th Annual Conference of the German Classification Society (Gesellschaft fur Klassifikation) on Classification: The Ubiquitous Challenge, GfKl 2004 - Dortmund, Germany Duration: 9 Mar 2004 → 11 Mar 2004

Publication series

Name	Studies in Classification, Data Analysis, and Knowledge Organization
ISSN (Print)	1431-8814

Conference

Conference	28th Annual Conference of the German Classification Society (Gesellschaft fur Klassifikation) on Classification: The Ubiquitous Challenge, GfKl 2004
Country/Territory	Germany
City	Dortmund
Period	9/03/04 → 11/03/04

Access to Document

10.1007/3-540-28084-7_41

Cite this

Menze, B. H., Wormit, M., Bachert, P., Lichy, M., Schlemmer, H. P., & Hamprecht, F. A. (2005). Classification of in vivo magnetic resonance spectra. In Classification - The Ubiquitous Challenge: Proceedings of the 28th Annual Conference of the Gesellschaft fur Klassifikation e.V., GfKl 2004 (pp. 362-369). (Studies in Classification, Data Analysis, and Knowledge Organization). Kluwer Academic Publishers. https://doi.org/10.1007/3-540-28084-7_41

Menze, Björn H. ; Wormit, Michael ; Bachert, Peter et al. / Classification of in vivo magnetic resonance spectra. Classification - The Ubiquitous Challenge: Proceedings of the 28th Annual Conference of the Gesellschaft fur Klassifikation e.V., GfKl 2004. Kluwer Academic Publishers, 2005. pp. 362-369 (Studies in Classification, Data Analysis, and Knowledge Organization).

@inproceedings{4359a9579efa46e7b5e9177280d24310,

title = "Classification of in vivo magnetic resonance spectra",

abstract = "We present the results of a systematic and quantitative comparison of methods from pattern recognition for the analysis of clinical magnetic resonance spectra. The medical question being addressed is the detection of brain tumor. In this application we find regularized linear methods to be superior to more flexible methods such as support vector machines, neural networks or random forests. The best preprocessing method for our spectral data is a smoothing and subsampling approach.",

author = "Menze, \{Bj{\"o}rn H.\} and Michael Wormit and Peter Bachert and Matthias Lichy and Schlemmer, \{Heinz Peter\} and Hamprecht, \{Fred A.\}",

year = "2005",

doi = "10.1007/3-540-28084-7\_41",

language = "English",

isbn = "3540256776",

series = "Studies in Classification, Data Analysis, and Knowledge Organization",

publisher = "Kluwer Academic Publishers",

pages = "362--369",

booktitle = "Classification - The Ubiquitous Challenge",

note = "28th Annual Conference of the German Classification Society (Gesellschaft fur Klassifikation) on Classification: The Ubiquitous Challenge, GfKl 2004 ; Conference date: 09-03-2004 Through 11-03-2004",

}

Menze, BH, Wormit, M, Bachert, P, Lichy, M, Schlemmer, HP & Hamprecht, FA 2005, Classification of in vivo magnetic resonance spectra. in Classification - The Ubiquitous Challenge: Proceedings of the 28th Annual Conference of the Gesellschaft fur Klassifikation e.V., GfKl 2004. Studies in Classification, Data Analysis, and Knowledge Organization, Kluwer Academic Publishers, pp. 362-369, 28th Annual Conference of the German Classification Society (Gesellschaft fur Klassifikation) on Classification: The Ubiquitous Challenge, GfKl 2004, Dortmund, Germany, 9/03/04. https://doi.org/10.1007/3-540-28084-7_41

Classification of in vivo magnetic resonance spectra. / Menze, Björn H.; Wormit, Michael; Bachert, Peter et al.
Classification - The Ubiquitous Challenge: Proceedings of the 28th Annual Conference of the Gesellschaft fur Klassifikation e.V., GfKl 2004. Kluwer Academic Publishers, 2005. p. 362-369 (Studies in Classification, Data Analysis, and Knowledge Organization).

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

TY - GEN

T1 - Classification of in vivo magnetic resonance spectra

AU - Menze, Björn H.

AU - Wormit, Michael

AU - Bachert, Peter

AU - Lichy, Matthias

AU - Schlemmer, Heinz Peter

AU - Hamprecht, Fred A.

PY - 2005

Y1 - 2005

N2 - We present the results of a systematic and quantitative comparison of methods from pattern recognition for the analysis of clinical magnetic resonance spectra. The medical question being addressed is the detection of brain tumor. In this application we find regularized linear methods to be superior to more flexible methods such as support vector machines, neural networks or random forests. The best preprocessing method for our spectral data is a smoothing and subsampling approach.

AB - We present the results of a systematic and quantitative comparison of methods from pattern recognition for the analysis of clinical magnetic resonance spectra. The medical question being addressed is the detection of brain tumor. In this application we find regularized linear methods to be superior to more flexible methods such as support vector machines, neural networks or random forests. The best preprocessing method for our spectral data is a smoothing and subsampling approach.

UR - https://www.scopus.com/pages/publications/33747332212

U2 - 10.1007/3-540-28084-7_41

DO - 10.1007/3-540-28084-7_41

M3 - Conference contribution

AN - SCOPUS:33747332212

SN - 3540256776

SN - 9783540256779

T3 - Studies in Classification, Data Analysis, and Knowledge Organization

SP - 362

EP - 369

BT - Classification - The Ubiquitous Challenge

PB - Kluwer Academic Publishers

T2 - 28th Annual Conference of the German Classification Society (Gesellschaft fur Klassifikation) on Classification: The Ubiquitous Challenge, GfKl 2004

Y2 - 9 March 2004 through 11 March 2004

ER -

Menze BH, Wormit M, Bachert P, Lichy M, Schlemmer HP, Hamprecht FA. Classification of in vivo magnetic resonance spectra. In Classification - The Ubiquitous Challenge: Proceedings of the 28th Annual Conference of the Gesellschaft fur Klassifikation e.V., GfKl 2004. Kluwer Academic Publishers. 2005. p. 362-369. (Studies in Classification, Data Analysis, and Knowledge Organization). doi: 10.1007/3-540-28084-7_41

Classification of in vivo magnetic resonance spectra

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this