Search

An automatic, neural network-based approach was applied to segment normal brain compartments and lesions on MR images. Two supervised networks, backpropagation (BPN) and counterpropagation, and two unsupervised networks, Kohonen learning vector quantizer and analog adaptive resonance theory, were trained on registered T2-weighted and proton density images. The classes of interest were background, gray matter, white matter, cerebrospinal fluid, macrocystic encephalomalacia, gliosis, and "unknown." A comprehensive feature vector was chosen to discriminate these classes. The BPN combined with feature conditioning, multiple discriminant analysis followed by Hotelling transform, produced the most accurate and consistent classification results. Classification of normal brain compartments were generally in agreement with expert interpretation of the images. Macrocystic encephalomalacia and gliosis were recognized and, except around the periphery, classified in agreement with the clinician's report used to train the neural network.

Cranial magnetic resonance imaging (MRI) was performed prospectively in 45 children (ages 3-27 months) with clinically documented motor delay to evaluate the ability of MRI to determine etiologic factors, to determine whether myelination correlated with motor delay, and whether the clinical category corresponded with the imaging findings. Of the 22 children diagnosed clinically as having major motor delay (i.e., cerebral palsy), 77% had magnetic resonance imaging abnormalities. In 23%, etiologic associations were established from MRI alone and in 32% a clinically suspected etiology was supported. No children had myelination delay as the sole abnormality. In 23 children with minor motor delay, only 17% had abnormal scans. Clearly, MRI provided useful information in the majority of children with cerebral palsy; therefore, a classification system is proposed in which MRI can be used in conjunction with clinical assessment to specify more precisely the etiologic factors in cerebral palsy.