Two different approaches to small sample size - a common problem in MRI-based studies

JANOUŠOVÁ, Eva, Daniel SCHWARZ and Tomáš KAŠPÁREK. Two different approaches to small sample size - a common problem in MRI-based studies. In Mezinárodní workshop funkční magnetické rezonance. 2010.

Basic information

• Original name: Two different approaches to small sample size - a common problem in MRI-based studies
• Name in Czech: Srovnání dvou přístupů k problému malého počtu vzorků v MRI studiích
• Authors: JANOUŠOVÁ, Eva, Daniel SCHWARZ and Tomáš KAŠPÁREK.
• Edition: Mezinárodní workshop funkční magnetické rezonance, 2010.

Other information

• Original language: English
• Type of outcome: Conference abstract
• Field of Study: 20200 2.2 Electrical engineering, Electronic engineering, Information engineering
• Country of publisher: Czech Republic
• Confidentiality degree: is not subject to a state or trade secret
• Organization unit: Faculty of Medicine
• Keywords in English: principal component analysis;schizophrenia;MRI;computational neuroanatomy;2DPCA;pPCA

Abstract

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.

Links

• NS10347, research and development project: Name: Moderní metody rozpoznávání pro analýzu obrazových dat v neuropsychiatrickém výzkumu

Investor: Ministry of Health of the CR

• NS9893, research and development project: Name: Predikce průběhu iniciálních fází schizofrenie pomocí morfologie mozku

Investor: Ministry of Health of the CR