JGrid/FCC - A tool for efficient knowledge extraction from magnetic resonance images
Magnetic Resonance Imaging allows to display different kinds of soft issue with highest resolution and has attracted increased interest in the analysis of anatomical differences between normal and pathologic populations even in the field of neuroscience. However, to get a deeper insight in complex neurological abnormalities like dementia or somatoform disorder large-scale analysis is indispensable but mostly difficult and time consuming.
JGrid a highly efficient distributed computing system that combines several Data Mining techniques including feature selection, clustering and classification (FCC) in order to provide a concise classification of pathogenous areas in the brain.
The software as well as the user's guide can be downloaded here:
The Launch Pad Dialog contains settings for the JGrid core features including server port, whether or not to broadcast the server location, the number of allowed simultaneous I/O locks, and the path of the SQLite database that stores software specific settings. By loading a payload JAR file, external libraries are automatically loaded and distributed to the client machines. Furthermore, several tabs for specifying the parameters for the FCC-Framework are displayed.
The Status Dialog informs about connected clients that are processing or waiting. Clients 1 and 3 are holding an I/O lock, indicated by 'L', whereas client 2 is waiting for an I/O lock ('W'). The progress display on the right shows running and completed tasks. The multi-tabbed display area at the bottom reports arising error messages, logging information and client events.
Related Papers:
Plant C., Teipel S., Oswald A., Böhm C., Mourao-Miranda J., Bokde A. W., Hampel H., Ewers M. Automated detection of brain atrophy patterns based on MRI for the prediction of Alzheimers disease. In Journal on Neuroimage, 2009.
