6533b861fe1ef96bd12c4edd
RESEARCH PRODUCT
Quantification and classification of high-resolution magic angle spinning data for brain tumor diagnosis.
Bernardo CeldaS. Van HuffelM.c Martinez-bisbalJean-baptiste PoulletD. ValverdeDaniel MonleonCarles Arússubject
Magnetic Resonance SpectroscopyProtonComputer scienceFeature extractionBrain tumorHigh resolutionSensitivity and SpecificityLeast squares support vector machineBiomarkers TumorMagic angle spinningmedicineHumansDiagnosis Computer-AssistedSpinningBrain Neoplasmsbusiness.industryMagic (programming)Reproducibility of ResultsPattern recognitionNuclear magnetic resonance spectroscopymedicine.diseaseSupport vector machineComputingMethodologies_PATTERNRECOGNITIONSpin LabelsArtificial intelligenceProtonsbusinessAlgorithmsdescription
The goal of this work is to propose a complete protocol (preprocessing, processing and classification) for classifying brain tumors with proton high-resolution magic-angle spinning ((1)H HR-MAS) data. The different steps of the procedure are detailed and discussed. Feature extraction techniques such as peak integration, including also the automated quantitation method AQSES, were combined with linear (LDA) and non-linear (least-squares support vector machine or LS-SVM) classifiers. Classification accuracy was assessed using a stratified random sampling scheme. The results suggest that LS-SVM performs better than LDA while AQSES performs better than the standard peak integration feature extraction method.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2007-11-16 |