Quantitation of grey matter, white matter, and cerebrospinal fluid from spin-echo magnetic resonance images using an artificial neural network technique.

An operator independent technique has been developed to quantitate the volume of white matter (WM), grey matter (GM), and cerebrospinal fluid (CSF) using spin-echo magnetic resonance images. Using skull stripped spin-echo images, CSF was removed using an automated thresholding technique. The bimodal histogram of the remaining images was used to train a perceptron and a single hidden layer neural network to output the percentage of GM and WM in the image. The output values were compared with those of a semiautomated technique employing a least square fitting technique [graduated nonconvexity algorithm (GNC)] applied to the bimodal histogram. This semiautomated technique allowed for intervention by the radiologist. Fourteen normal volunteers with eight contiguous slices each were analyzed. The individual percentages of WM, GM, and CSF of 40 slices from five subjects not used in the training set as well as the total percentages of GM, WM, and CSF in each individual were predicted using the two artificial network architectures. GM, WM, and CSF percentages were predicted within 7% for individual slices while total percentages of WM, GM, and CSF were computed accurately with an absolute error of less than 5% when compared to the semiautomated technique involving a trained neuroradiologist.