ABSTRACT
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.
Subject(s)
Brain Damage, Chronic/classification , Brain Injuries/classification , Brain/pathology , Image Processing, Computer-Assisted/instrumentation , Magnetic Resonance Imaging/instrumentation , Neural Networks, Computer , Artificial Intelligence , Brain Damage, Chronic/diagnosis , Brain Damage, Chronic/pathology , Brain Injuries/diagnosis , Brain Injuries/pathology , Cerebral Cortex/injuries , Cerebral Cortex/pathology , Cerebrospinal Fluid/physiology , Child , Cysts/classification , Cysts/diagnosis , Cysts/pathology , Encephalomalacia/classification , Encephalomalacia/diagnosis , Encephalomalacia/pathology , Expert Systems , Female , Gliosis/classification , Gliosis/diagnosis , Gliosis/pathology , Head Injuries, Closed/classification , Head Injuries, Closed/diagnosis , Head Injuries, Closed/pathology , Humans , Male , Reference ValuesABSTRACT
A clinico-pathological report is given of two cases of progressive dementia of fronto-temporal type associated with variable cortical neuronal loss and extensive subcortical and deep white matter gliosis. There was minimal demyelination of white matter, significant gliosis of thalamus and inferior olivary nuclei. The authors review the condition of progressive subcortical gliosis, compare such changes with white matter changes in other dementias, examine the relationship to Kraepelin's disease, contrast the disorder with atypical Pick's dementia, progressive dementia with motor neuron disease and Creutzfeldt-Jakob dementia.
Subject(s)
Gliosis/pathology , Dementia/pathology , Diagnosis, Differential , Female , Gliosis/classification , Humans , Middle Aged , Nerve DegenerationABSTRACT
Review of 50 histopathologic cases and a number of clinical cases of congenital retinal anomalies has permitted classification under the following headings: 1) Coloboma-orbital cyst--"anophthalmos" group due to aberrant closure of the embryonic fissure; 2) Retinal fold-central stalk-detachment group comprising a series that varies from simple retinal folds to total retinal detachment and anomalous stalk formation. Cases of the 13-15 trisomy syndrome constitute a special subgroup in this rubric; 3) Retrolental fibroplasia, due to hyperoxia of premature infants, is manifest by "dragged" disks and gliovascular proliferation with occasional detachment; 4) Persistent hyaloid system is occasionally associated with mild anomalies of the retina; 5) Massive gliosis of the retina is usually a hamartomatous manifestation; 6) Congenital absence of ganglion cells occurs with cerebral maldevelopment and 7) Congenital absence of the photoreceptors is the congenital form of retinitis pigmentosa.