Research and projectsResearch groups at IBA MU

Research groups at IBA MU Neuroimaging Group

Leader of the research group Leader of the research group: Daniel Schwarz, Ph.D.

The Neuroimaging Group at the Institute of Biostatistics and Analyses is a voluntary group of young scientists – pregraduate and postgraduate students of mathematical biology, biophysics, neuroscience, and biomedical engineering – solving together problems and challenges from the area of brain research.

Leader of the research group:

Daniel Schwarz, Ph.D.

Daniel Schwarz, Ph.D.


The most commonly solved problems include tasks from the area of processing and analysis of MR images of brain for the purpose of neuropsychiatric research. The group deals with the design and technical implementation of methods such as registration, segmentation, or morphometry, and also interconnects the scientific disciplines of neuroimaging and machine learning.

List of projects

Advanced methods for recognition of MR brain images for computer aided diagnosis of neuropsychiatric disorders

The project funded by the Internal Grant Agency of the Czech Ministry of Health (IGA) (2012-2015) proposes to develop software usable in clinical practice for computer aided diagnosis of neuropsychiatric disorders from MR images of brain. It is based on experience with advanced analysis of MR images, including assessment of brain morphology in the first episode of schizophrenia. Authorized software - the main subject of the proposed project - will combine methods for image processing and analysis with advanced machine learning algorithms for prediction, classification and recognition. This will provide a new tool for analyzing image data, which will bring medical imaging closer to the clinical psychiatry by making diagnosis objective, which is in the current practice based on subjective evaluation of clinically evident changes in mental function and behavior. The methodology includes the development of algorithms aimed at the description of the images with the use of automated morphometry as well as the development of classifiers using features extracted from various data sources.

Modern pattern recognition methods for image data analysis in neuropsychiatric research

The project funded by the Internal Grant Agency of the Czech Ministry of Health (IGA) (2009-2011) led to the creation of authorized software utilizable in the clinical practice for computer-aided diagnostics of neuropsychiatric disorders from MRI brain images. The project proposal came from the experience with existing software packages which are nowadays utilized in the neuroimaging community and also from our original methodology for brain morphology assessment in first episode schizophrenia. The software, which is the main subject of the proposed project, connected complex methods for 3-D MRI brain image processing and analysis with an advanced assessing apparatus based on pattern recognition and machine learning methods. A new tool for automated analysis of image data was developed for the application field of computational neuroanatomy. Besides common comparisons among groups of patients and normal subjects, it made it possible to set a new type of classification assessment, even in the case of an individual analyzed subject, in contrast to VBM and DBM.

Selected publications

  • Schwarz D, Kasparek T. Brain morphometry of MR images for automated classification of first-episode schizophrenia. Information Fusion 2014, 19: 97–102. doi: 10.1016/j.inffus.2013.02.002.
  • Janousova E, Schwarz D, Kašpárek T. Combining various types of classifiers and features extracted from magnetic resonance imaging data in schizophrenia recognition. Psychiatry Research: Neuroimaging 2014 [submitted, in revision]
  • Dluhos P, Schwarz D, Kasparek T. Wavelet features for recognition of first episode of schizophrenia from MRI brain images. Radioengineering 2014, 23: 274–281.
  • Schwarz D, Kasparek T. Comparison of two methods for automatic brain morphometry analysis. Radioengineering 2011, 20: 996–1001.
  • Schwarz D, Kasparek T, Provaznik I, Jarkovsky J. A deformable registration method for automated morphometry of MRI brain images in neuropsychiatric research. IEEE Transactions on Medical Imaging 2007, 26: 452 –461. doi: 10.1109/TMI.2007.892512.