Machine-based rejection of low-quality spectra and estimation of brain tumor probabilities from magnetic resonance spectroscopic images

Bjoern H. Menze, B. Michael Kelm, Daniel Heck, Matthias P. Lichy, Fred A. Hamprecht

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

3 Scopus citations

Abstract

Magnetic resonance spectroscopic images (MRSI) carry spatially resolved information about the in vivo metabolism, however, their evaluation is difficult. Problems arise especially from artifacts and noise, yielding non-evaluable signals in many voxels. We propose a two-step approach to the processing of MRSI. In the first step a non-linear classifier is employed in every voxel to determine whether the spectral signal is evaluable, and if so, the tumor probability is computed in the second step. Thus, the quality control is strictly separated from the diagnostic evaluation of the spectrum. For an assessment of the proposed approach we consider MRSI-based brain tumor detection and localization and a tumor probability mapping by pattern recognition. In a quantitative comparison against the standard operator-controlled processing our interaction-free approach shows similar to superior performance.

Original languageEnglish
Title of host publicationBildverarbeitung fur die Medizin 2006
Subtitle of host publicationAlgorithmen - Systeme - Anwendungen, BVM 2006 - Proceedings des Workshops
PublisherKluwer Academic Publishers
Pages31-35
Number of pages5
ISBN (Print)9783540321361
DOIs
StatePublished - 2006
Externally publishedYes
EventWorkshops Bildverarbeitung fur die Medizin: Algorithmen Systeme Anwendungen, BVM 2006 - Workshop on Image Processing for Medicine: Algorithms - Systems - Applications, BVM 2006 - Hamburg, Germany
Duration: 19 Mar 200621 Mar 2006

Publication series

NameInformatik aktuell
ISSN (Print)1431-472X

Conference

ConferenceWorkshops Bildverarbeitung fur die Medizin: Algorithmen Systeme Anwendungen, BVM 2006 - Workshop on Image Processing for Medicine: Algorithms - Systems - Applications, BVM 2006
Country/TerritoryGermany
CityHamburg
Period19/03/0621/03/06

Fingerprint

Dive into the research topics of 'Machine-based rejection of low-quality spectra and estimation of brain tumor probabilities from magnetic resonance spectroscopic images'. Together they form a unique fingerprint.

Cite this