Neural-network-based classification of cognitively normal, demented, Alzheimer disease and vascular dementia from single photon emission with computed tomography image data from brain.

Single photon emission with computed tomography (SPECT) hexamethylphenylethyleneamineoxime 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 elderly normal, Alzheimer disease (AD), and vascular dementia (VD) subjects. After initial image preprocessing and registration, image features were obtained that were representative of the mean regional tissue uptake. These features were extracted from a given image by averaging the intensities over various regions defined by suitable masks. After training, the network classified independent trials of patients whose clinical diagnoses conformed to published criteria for probable AD or probable/possible VD. For the SPECT data used in the current tests, the OINN agreement was 80 and 86% for probable AD and probable/possible VD, respectively. These results suggest that artificial neural network methods offer potential in diagnoses from brain images and possibly in other areas of scientific research where complex patterns of data may have scientifically meaningful groupings that are not easily identifiable by the researcher.

Apolipoprotein E and Alzheimer disease.

Inheritance of specific apolipoprotein E (apoE) alleles determines, in large part, the risk and mean age of onset of late-onset familial and sporadic Alzheimer disease. The mechanism by which the apoE isoforms differentially contribute to disease expression is, however, unknown. Isoform-specific differences have been identified in the binding of apoE to the microtubule-associated protein tau, which forms the paired helical filament and neurofibrillary tangles, and to amyloid beta peptide, a major component of the neuritic plaque. These and other isoform-specific interactions of apoE give rise to testable hypotheses for the mechanism(s) of pathogenesis of Alzheimer disease. An unresolved issue of increasing importance is the relationship between the structural pathological lesions and the cellular pathogenesis responsible for the clinical disease phenotype, progressive dementia. The identification of apoE in the cytoplasm of human neurons and the characterization of isoform-specific binding of apoE to the microtubule-associated proteins tau and MAP-2 present the possibility that apoE may affect microtubule function in the Alzheimer brain.

Serum amyloid P component prevents proteolysis of the amyloid fibrils of Alzheimer disease and systemic amyloidosis.

Extracellular deposition of amyloid fibrils is responsible for the pathology in the systemic amyloidoses and probably also in Alzheimer disease [Haass, C. & Selkoe, D. J. (1993) Cell 75, 1039-1042] and type II diabetes mellitus [Lorenzo, A., Razzaboni, B., Weir, G. C. & Yankner, B. A. (1994) Nature (London) 368, 756-760]. The fibrils themselves are relatively resistant to proteolysis in vitro but amyloid deposits do regress in vivo, usually with clinical benefit, if new amyloid fibril formation can be halted. Serum amyloid P component (SAP) binds to all types of amyloid fibrils and is a universal constituent of amyloid deposits, including the plaques, amorphous amyloid beta protein deposits and neurofibrillary tangles of Alzheimer disease [Coria, F., Castano, E., Prelli, F., Larrondo-Lillo, M., van Duinen, S., Shelanski, M. L. & Frangione, B. (1988) Lab. Invest. 58, 454-458; Duong, T., Pommier, E. C. & Scheibel, A. B. (1989) Acta Neuropathol. 78, 429-437]. Here we show that SAP prevents proteolysis of the amyloid fibrils of Alzheimer disease, of systemic amyloid A amyloidosis and of systemic monoclonal light chain amyloidosis and may thereby contribute to their persistence in vivo. SAP is not an enzyme inhibitor and is protective only when bound to the fibrils. Interference with binding of SAP to amyloid fibrils in vivo is thus an attractive therapeutic objective, achievement of which should promote regression of the deposits.

Early Alzheimer disease-like histopathology increases in frequency with age in mice transgenic for beta-APP751.

beta-Amyloid deposition and neurofibrillary tangle formation are two histopathological features of Alzheimer disease. We have previously reported that beta-amyloid immunoreactive deposits form in the brains of transgenic mice programmed for neuronal expression of the 751-amino acid isoform of human beta-amyloid precursor protein (beta-APP751) and now describe that these animals also display Alz50 intraneuronal immunoreactivity similar to that seen in early Alzheimer disease. This suggests that abnormal beta-APP expression and/or beta-amyloid deposition promotes pathogenic alterations in tau protein. The frequency of both beta-amyloid deposition and Alz50-positive neurons was twice as prevalent in brains from old (22 months) as compared to young (2-3 months) beta-APP751 transgenic mice. This increase in histopathology with age in beta-APP751 transgenic mice parallels the time-dependent progression seen in the human disease.

Quantitative analysis of senile plaques in Alzheimer disease: observation of log-normal size distribution and molecular epidemiology of differences associated with apolipoprotein E genotype and trisomy 21 (Down syndrome).

The discovery that the epsilon 4 allele of the apolipoprotein E (apoE) gene is a putative risk factor for Alzheimer disease (AD) in the general population has highlighted the role of genetic influences in this extremely common and disabling illness. It has long been recognized that another genetic abnormality, trisomy 21 (Down syndrome), is associated with early and severe development of AD neuropathological lesions. It remains a challenge, however, to understand how these facts relate to the pathological changes in the brains of AD patients. We used computerized image analysis to examine the size distribution of one of the characteristic neuropathological lesions in AD, deposits of A beta peptide in senile plaques (SPs). Surprisingly, we find that a log-normal distribution fits the SP size distribution quite well, motivating a porous model of SP morphogenesis. We then analyzed SP size distribution curves in genotypically defined subgroups of AD patients. The data demonstrate that both apoE epsilon 4/AD and trisomy 21/AD lead to increased amyloid deposition, but by apparently different mechanisms. The size distribution curve is shifted toward larger plaques in trisomy 21/AD, probably reflecting increased A beta production. In apoE epsilon 4/AD, the size distribution is unchanged but the number of SP is increased compared to apoE epsilon 3, suggesting increased probability of SP initiation. These results demonstrate that subgroups of AD patients defined on the basis of molecular characteristics have quantitatively different neuropathological phenotypes.