Další formáty:
BibTeX
LaTeX
RIS
@proceedings{878091, author = {Janoušová, Eva and Schwarz, Daniel and Kašpárek, Tomáš}, booktitle = {Mezinárodní workshop funkční magnetické rezonance}, keywords = {principal component analysis;schizophrenia;MRI;computational neuroanatomy;2DPCA;pPCA}, language = {eng}, title = {Two different approaches to small sample size - a common problem in MRI-based studies}, year = {2010} }
TY - CONF ID - 878091 AU - Janoušová, Eva - Schwarz, Daniel - Kašpárek, Tomáš PY - 2010 TI - Two different approaches to small sample size - a common problem in MRI-based studies KW - principal component analysis;schizophrenia;MRI;computational neuroanatomy;2DPCA;pPCA N2 - Recently, the small sample size problem and huge image data have often been discussed in MRI-based studies. Two methods for data reduction are compared here and further modified to solve classification of 3-D MRI data sets in the schizophrenia research. The results show that PCA based on covariance matrix of patients (pPCA) is more suitable for large MRI data reduction than 2DPCA. The results also indicate that deformation images are more appropriate for classification than GM density images. ER -
JANOUŠOVÁ, Eva, Daniel SCHWARZ a Tomáš KAŠPÁREK. Two different approaches to small sample size - a common problem in MRI-based studies. In \textit{Mezinárodní workshop funkční magnetické rezonance}. 2010.
|