Detail publikace

Classification of First-Episode Schizophrenia Using Wavelet Imaging Features

MARŠÁLOVÁ, K. SCHWARZ, D. PROVAZNÍK, I.

Originální název

Classification of First-Episode Schizophrenia Using Wavelet Imaging Features

Anglický název

Classification of First-Episode Schizophrenia Using Wavelet Imaging Features

Jazyk

en

Originální abstrakt

This work explores the design and implementation of an algorithm for the classification of magnetic resonance imaging data for computer-aided diagnosis of schizophrenia. Features for classification were first extracted using two morphometric methods: voxel-based morphometry (VBM) and deformation-based morphometry (DBM). These features were then transformed into a wavelet domain using the discrete wavelet transform with various numbers of decomposition levels. The number of features was then reduced by thresholding and subsequent selection by: Fisher's Discrimination Ratio (FDR), Bhattacharyya Distance, and Variances (Var.). A Support Vector Machine with a linear kernel was used for classification. The evaluation strategy was based on leave-one-out cross-validation.

Anglický abstrakt

This work explores the design and implementation of an algorithm for the classification of magnetic resonance imaging data for computer-aided diagnosis of schizophrenia. Features for classification were first extracted using two morphometric methods: voxel-based morphometry (VBM) and deformation-based morphometry (DBM). These features were then transformed into a wavelet domain using the discrete wavelet transform with various numbers of decomposition levels. The number of features was then reduced by thresholding and subsequent selection by: Fisher's Discrimination Ratio (FDR), Bhattacharyya Distance, and Variances (Var.). A Support Vector Machine with a linear kernel was used for classification. The evaluation strategy was based on leave-one-out cross-validation.

Dokumenty

BibTex 


@inproceedings{BUT167774,
  author="Kateřina {Maršálová} and Daniel {Schwarz} and Valentine {Provazník}",
  title="Classification of First-Episode Schizophrenia Using Wavelet Imaging Features",
  annote="This work explores the design and implementation of an algorithm for the classification of magnetic resonance imaging data for computer-aided diagnosis of schizophrenia. Features for classification were first extracted using two morphometric methods: voxel-based morphometry (VBM) and deformation-based morphometry (DBM). These features were then transformed into a wavelet domain using the discrete wavelet transform with various numbers of decomposition levels. The number of features was then reduced by thresholding and subsequent selection by: Fisher's Discrimination Ratio (FDR), Bhattacharyya Distance, and Variances (Var.). A Support Vector Machine with a linear kernel was used for classification. The evaluation strategy was based on leave-one-out cross-validation.",
  address="IOS Press",
  booktitle="Digital Personalized Health and Medicine",
  chapter="167774",
  doi="10.3233/SHTI200372",
  edition="Studies in Health Technology and Informatics",
  howpublished="online",
  institution="IOS Press",
  year="2020",
  month="may",
  pages="1221--1222",
  publisher="IOS Press",
  type="conference paper"
}