Tissue segmentation-assisted analysis of fMRI for human motor response: Anapproach combining artificial neural network and fuzzy C means

The authors have developed an automated algorithm for segmentation of magne tic resonance images (MRI) of the human brain. They investigated the quanti tative analysis of tissue-specific human motor response through an approach combining gradient echo functional MRI and automated segmentation analysis . Fifteen healthy volunteers, placed in a 1.5 T clinical MR imager, perform ed a self-paced finger opposition throughout the activation periods. T-1-we ighted images (WI), T2WI, and proton density WI were acquired for segmentat ion analysis. Single-slice axial T-2* fast low-angle shot (FLASH) images we re obtained during the functional study. Pixelwise cross-correlation analys is was performed to obtain an activation map. A cascaded algorithm, combini ng Kohonen feature maps and fuzzy C means, was applied for segmentation. Af ter processing, masks for gray matter, white matter, small vessels, and lar ge vessels were generated. Tissue-specific analysis showed a signal change rate of 4.53% in gray matter, 2.98% in white matter, 5.79% in small vessels , and 7.24% in large vessels. Different temporal patterns as well as differ ent levels of activation were identified in the functional response from va rious types of tissue. High correlation exists between cortical gray matter and subcortical white matter (r = 0.957), while the vessel behaves somewha t different temporally. The cortical gray matter fits best to the assumed i nput function (r = 0.957) followed by subcortical white matter (r = 0.829) and vessels (r = 0.726). The automated algorithm of tissue-specific analysi s thus can assist functional MRI studies with different modalities of respo nse in different brain regions. Copyright (C) 2001 by W.B. Saunders Company .