NEURAL-NETWORK-BASED CLASSIFICATION OF COGNITIVELY NORMAL, DEMENTED, ALZHEIMER-DISEASE AND VASCULAR DEMENTIA FROM SINGLE-PHOTON EMISSION WITH COMPUTED-TOMOGRAPHY IMAGE DATA FROM BRAIN
Rjp. Defigueiredo et al., NEURAL-NETWORK-BASED CLASSIFICATION OF COGNITIVELY NORMAL, DEMENTED, ALZHEIMER-DISEASE AND VASCULAR DEMENTIA FROM SINGLE-PHOTON EMISSION WITH COMPUTED-TOMOGRAPHY IMAGE DATA FROM BRAIN, Proceedings of the National Academy of Sciences of the United Statesof America, 92(12), 1995, pp. 5530-5534
Single photon emission with computed tomography (SPECT) hexamethylphen
ylethyleneamineoxime technetium-99 images were analyzed by an optimal
interpolative neural network (OINN) algorithm to determine whether the
network could discriminate among clinically diagnosed groups of elder
ly normal, Alzheimer disease (AD), and vascular dementia (VD) subjects
, After initial image preprocessing and registration, image features w
ere obtained that were representative of the mean regional tissue upta
ke, These features were extracted from a given image by averaging the
intensities over various regions defined by suitable masks, After trai
ning, the network classified independent trials of patients whose clin
ical diagnoses conformed to published criteria for probable AD or prob
able/possible VD, For the SPECT data used in the current tests, the OI
NN agreement was 80 and 86% for probable AD and probable/possible VD,
respectively, These results suggest that artificial neural network met
hods offer potential in diagnoses from brain images and possibly in ot
her areas of scientific research where complex patterns of data may ha
ve scientifically meaningful groupings that are not easily identifiabl
e by the researcher.