Accurate, uniform volumetric measurements of brain structures are of great importance to morphological studies of the brain in mental health, disease, and developmental research. Automated measurement methods will improve the consistency, accuracy, and availability of such estimates, and will allow more efficient screening of magnetic resonance (MR) images. In Phase I, ORINCON will develop a hierarchical system of fuzzy min-max neural networks (FMMNNs), capable of classifying regions of MR brain images into four categories (gray matter, white matter, cerebro-spinal fluid (CSF), and hyperintensities). Using proton-density weighted (PDW) and T2 weighted (T2W) images from UCSD School of Medicine, sets of """"""""stacked"""""""" MR images will first be preprocessed for improved spatial homogeneity and brain boundary determination. After initial preprocessing, linear combinations of images will he formed, yielding images for CSF/Brain and Gray/White matter separation. The hierarchical neural nets will he trained and tested with these sets of images. Three-dimensional analysis methods will categorize pixels in specified image regions, which will then be compared to pre-existing estimates in a confusion matrix format. A final report will describe experimental procedures, analyze test results, and recommend Phase II research directions for automated identification and volume quantification of specific brain structures.
