MARŠÁLOVÁ, Kateřina and Daniel SCHWARZ. Wavelet Imaging Features for Classification of First-Episode Schizophrenia. Online. In Pietka, E.; Badura, P.; Kawa, J.; Wieclawek, W. Information Technology in Biomedicine, ITIB 2019, Kamień Śląski, Poland, 18-20 June, 2019. 1011th ed. Kamień Śląski, Poland: Springer, 2019, p. 280-291. ISBN 978-3-030-23761-5. Available from: https://dx.doi.org/10.1007/978-3-030-23762-2_25. |
Other formats:
BibTeX
LaTeX
RIS
@inproceedings{1582476, author = {Maršálová, Kateřina and Schwarz, Daniel}, address = {Kamień Śląski, Poland}, booktitle = {Information Technology in Biomedicine, ITIB 2019, Kamień Śląski, Poland, 18-20 June, 2019}, doi = {http://dx.doi.org/10.1007/978-3-030-23762-2_25}, edition = {1011}, editor = {Pietka, E.; Badura, P.; Kawa, J.; Wieclawek, W.}, keywords = {classification; machine learning; neuroimaging; schizophrenia; support vector machines; wavelet transformation}, howpublished = {elektronická verze "online"}, language = {eng}, location = {Kamień Śląski, Poland}, isbn = {978-3-030-23761-5}, pages = {280-291}, publisher = {Springer}, title = {Wavelet Imaging Features for Classification of First-Episode Schizophrenia}, url = {https://link.springer.com/chapter/10.1007%2F978-3-030-23762-2_25}, year = {2019} }
TY - JOUR ID - 1582476 AU - Maršálová, Kateřina - Schwarz, Daniel PY - 2019 TI - Wavelet Imaging Features for Classification of First-Episode Schizophrenia PB - Springer CY - Kamień Śląski, Poland SN - 9783030237615 KW - classification KW - machine learning KW - neuroimaging KW - schizophrenia KW - support vector machines KW - wavelet transformation UR - https://link.springer.com/chapter/10.1007%2F978-3-030-23762-2_25 N2 - Recently, multiple attempts have been made to support computer diagnostics of neuropsychiatric disorders, using neuroimaging data and machine learning methods. This paper deals with the design and implementation of an algorithm for the analysis and classification of magnetic resonance imaging data for the purpose of computer-aided diagnosis of schizophrenia. Features for classification are first extracted using two morphometric methods: voxel-based morphometry (VBM) and deformation-based morphometry (DBM); and then transformed into a wavelet domain by discrete wavelet transform (DWT) with various numbers of decomposition levels. The number of features is reduced by thresholding and subsequent selection by: Fisher’s Discrimination Ratio, Bhattacharyya Distance, and Variances – a metric proposed in the literature recently. Support Vector Machine with a linear kernel is used here as a classifier. The evaluation strategy is based on leave-one-out cross-validation. The highest classification accuracy – 73.08% – was achieved with 1000 features extracted by VBM and DWT at four decomposition levels and selected by Fisher’s Discrimination Ratio and Bhattacharyya distance. In the case of DBM features, the classifier achieved the highest accuracy of 72.12% with 5000 discriminating features, five decomposition levels and the use of Fisher’s Discrimination Ratio. ER -
MARŠÁLOVÁ, Kateřina and Daniel SCHWARZ. Wavelet Imaging Features for Classification of First-Episode Schizophrenia. Online. In Pietka, E.; Badura, P.; Kawa, J.; Wieclawek, W. \textit{Information Technology in Biomedicine, ITIB 2019, Kamie\'n \'Sląski, Poland, 18-20 June, 2019}. 1011th ed. Kamie\'n \'Sląski, Poland: Springer, 2019, p.~280-291. ISBN~978-3-030-23761-5. Available from: https://dx.doi.org/10.1007/978-3-030-23762-2\_{}25.
|