A multicohort geometric deep learning study of age dependent cortical and subcortical morphologic interactions for fluid intelligence prediction

The relationship of human brain structure to cognitive function is complex, and how this relationship differs between childhood and adulthood is poorly understood. One strong hypothesis suggests the cognitive function of Fluid Intelligence (Gf) is dependent on prefrontal cortex and parietal cortex. In this work, we developed a novel graph convolutional neural networks (gCNNs) for the analysis of localized anatomic shape and prediction of Gf. Morphologic information of the cortical ribbons and subcortical structures was extracted from T1-weighted MRIs within two independent cohorts, the Adolescent Brain Cognitive Development Study (ABCD; age: 9.93 ± 0.62 years) of children and the Human Connectome Project (HCP; age: 28.81 ± 3.70 years). Prediction combining cortical and subcortical surfaces together yielded the highest accuracy of Gf for both ABCD (R = 0.314) and HCP datasets (R = 0.454), outperforming the state-of-the-art prediction of Gf from any other brain measures in the literature. Across both datasets, the morphology of the amygdala, hippocampus, and nucleus accumbens, along with temporal, parietal and cingulate cortex consistently drove the prediction of Gf, suggesting a significant reframing of the relationship between brain morphology and Gf to include systems involved with reward/aversion processing, judgment and decision-making, motivation, and emotion.

Interpretation of Brain Morphology in Association to Alzheimer's Disease Dementia Classification Using Graph Convolutional Networks on Triangulated Meshes

We propose a mesh-based technique to aid in the classification of Alzheimer's disease dementia (ADD) using mesh representations of the cortex and subcortical structures. Deep learning methods for classification tasks that utilize structural neuroimaging often require extensive learning parameters to optimize. Frequently, these approaches for automated medical diagnosis also lack visual interpretability for areas in the brain involved in making a diagnosis. This work: (a) analyzes brain shape using surface information of the cortex and subcortical structures, (b) proposes a residual learning framework for state-of-the-art graph convolutional networks which offer a significant reduction in learnable parameters, and (c) offers visual interpretability of the network via class-specific gradient information that localizes important regions of interest in our inputs. With our proposed method leveraging the use of cortical and subcortical surface information, we outperform other machine learning methods with a 96.35% testing accuracy for the ADD vs. healthy control problem. We confirm the validity of our model by observing its performance in a 25-trial Monte Carlo cross-validation. The generated visualization maps in our study show correspondences with current knowledge regarding the structural localization of pathological changes in the brain associated to dementia of the Alzheimer's type.

Discrete, recurrent, and scalable patterns in non-operant judgement underlie affective picture ratings

Operant keypress tasks in a reinforcement-reward framework where behavior is shaped by its consequence, show lawful relationships in human preference behavior (i.e., approach/avoidance) and have been analogized to "wanting". However, they take 20-40 min as opposed to short non-operant rating tasks, which can be as short as 3 min and unsupervised, thus more readily applied to internet research. It is unknown if non-operant rating tasks where each action does not have a consequence, analogous to "liking", show similar lawful relationships. We studied non-operant, picture-rating data from three independent population cohorts (N = 501, 506, and 4019 participants) using the same 7-point Likert scale for negative to positive preferences, and the same categories of images from the International Affective Picture System. Non-operant picture ratings were used to compute location, dispersion, and pattern (entropy) variables, that in turn produced similar value, limit, and trade-off functions to those reported for operant keypress tasks, all with individual R2 > 0.80. For all three datasets, the individual functions were discrete in mathematical formulation. They were also recurrent or consistent across the cohorts and scaled between individual and group curves. Behavioral features such as risk aversion and other interpretable features of the graphs were also consistent across cohorts. Together, these observations argue for lawfulness in the modeling of the ratings. This picture rating task demonstrates a simple, quick, and low-cost framework for quantitatively assessing human preference without forced choice decisions, games of chance, or operant keypressing. This framework can be easily deployed on any digital device worldwide.