A new MRI technique is helping researchers identify a distinct pattern of brain structure that is characteristic of mild cognitive impairment (MCI). The results may lead to treatments that target early Alzheimer’s disease before irreversible brain damage sets in, according to Christos Davatzikos, PhD, Director of the Biomedical Image Analysis Section within the Department of Radiology at the University of Pennsylvania in Philadelphia, and colleagues. Their findings will be published in an upcoming issue of Neurobiology of Aging.

Using MRI, the researchers were able to create a unique picture of the brain by combining and analyzing images, then measuring the volume and density of different tissues and their spatial distribution within the brain. Their study included 15 participants from the Baltimore Longitudinal Study of Aging, all of whom were without dementia at initial enrollment but developed MCI over the course of nine years. Among the participants, 10 had progressed to Alz­heimer’s disease, reported the authors. The results from the patients’ MRI were compared with those from 15 age- and gender-matched participants who were unimpaired. Then, the researchers used a spatial map to identify distinct characteristics of MCI in the impaired participants. The map revealed atrophy in the lateral and inferior areas of both hippocampi; the bilateral superior, middle, and inferior temporal gyri; parts of the bilateral orbitofrontal cortex; the left fusiform gyrus; the right collateral sulcus; and the cingulate. Clusters of reduced white matter volumes in the inferior temporal gyri and in the middle and superior frontal gyri were also reported.

Based on this pattern, “individuals with MCI were distinguished initially with 100% accuracy from those without cognitive impairment, thereby demonstrating full separation between MCI and cognitively normal individuals, using this nonlinear classifier,” reported the authors. The prediction power was determined to be 90% ­via leave-one-out cross-validation class­­ification: “This is an esti­mate of classification accuracy of a new individual’s scan and therefore of direct diagnostic relevance,” they concluded.            

NR