Classification of whole-brain functional connectivity MRI data with convolutional neural networks (CNNs) has shown promise, but the complexity of these models impedes understanding of which aspects of brain activity contribute to classification. While visualization techniques have been developed to interpret CNNs, bias inherent in the method of encoding abstract input data, as well as the natural variance of deep learning models, detract from the accuracy of these techniques. We introduce a stochastic encoding method in an ensemble of CNNs to classify functional connectomes by gender. We applied our method to resting-state and task data from the UK BioBank, using two visualization techniques to measure the salience of three brain networks involved in task- and resting-states, and their interaction. To regress confounding factors such as head motion, age, and intracranial volume, we introduced a multivariate balancing algorithm to ensure equal distributions of such covariates between classes in our data. We achieved a final AUROC of 0.8459. We found that resting-state data classifies more accurately than task data, with the inner salience network playing the most important role of the three networks overall in classification of resting-state data and connections to the central executive network in task data.

To find out what's behind the phenomenon of super-agers, researchers conducted a study examining the brains and cognitive performances of two groups: 41 young adults between the ages of 18 and 35 and 40 older adults between the ages of 60 and 80. First, the researchers administered a series of cognitive tests, like the California Verbal Learning Test (CVLT) and the Trail Making Test (TMT). Seventeen members of the older group scored at or above the mean scores of the younger group. That is, these 17 could be considered super-agers, performing at the same level as the younger study participants. Aside from these individuals, members of the older group tended to perform less well on the cognitive tests. The default mode network is, as its name might suggest, a series of brain regions that are active by default -- when we're not engaged in a task, they tend to show higher levels of activity.