Graph lesion-deficit mapping of fluid intelligence

Abstract

Fluid intelligence is arguably the defining feature of human cognition. Yet the nature of its relationship with the brain remains a contentious topic. Influential proposals drawing primarily on functional imaging data have implicated 'multiple demand' frontoparietal and more widely distributed cortical networks, but extant lesion-deficit studies with greater causal power are almost all small, methodologically constrained, and inconclusive. The task demands large samples of patients, comprehensive investigation of performance, fine-grained anatomical mapping, and robust lesion-deficit inference, yet to be brought to bear on it. We assessed 165 healthy controls and 227 frontal or non-frontal patients with unilateral brain lesions on the best-established test of fluid intelligence, Raven's Advanced Progressive Matrices, employing an array of lesion-deficit inferential models responsive to the potentially distributed nature of fluid intelligence. Non-parametric Bayesian stochastic block models were used to reveal the community structure of lesion deficit networks, disentangling functional from confounding pathological distributed effects. Impaired performance was confined to patients with frontal lesions [F(2,387) = 18.491; P < 0.001; frontal worse than non-frontal and healthy participants P < 0.01, P <0.001], more marked on the right than left [F(4,385) = 12.237; P < 0.001; right worse than left and healthy participants P < 0.01, P < 0.001]. Patients with non-frontal lesions were indistinguishable from controls and showed no modulation by laterality. Neither the presence nor the extent of multiple demand network involvement affected performance. Both conventional network-based statistics and non-parametric Bayesian stochastic block modelling heavily implicated the right frontal lobe. Crucially, this localization was confirmed on explicitly disentangling functional from pathology-driven effects within a layered stochastic block model, prominently highlighting a right frontal network involving middle and inferior frontal gyrus, pre- and post-central gyri, with a weak contribution from right superior parietal lobule. Similar results were obtained with standard lesion-deficit analyses. Our study represents the first large-scale investigation of the distributed neural substrates of fluid intelligence in the focally injured brain. Combining novel graph-based lesion-deficit mapping with detailed investigation of cognitive performance in a large sample of patients provides crucial information about the neural basis of intelligence. Our findings indicate that a set of predominantly right frontal regions, rather than a more widely distributed network, is critical to the high-level functions involved in fluid intelligence. Further they suggest that Raven's Advanced Progressive Matrices is a useful clinical index of fluid intelligence and a sensitive marker of right frontal lobe dysfunction.

Keywords: executive functions; fluency; focal lesion; frontal lobes; lesion-symptom mapping.

Figure 1

Lesion distribution map. Voxel-wise sum of the 221 modelled lesions overlaid on the SPM152 T₁ template distributed with MRIcroGL(https://www.nitrc.org/projects/mricrogl). The images are displayed in neurological convention (left is left).

Figure 2

Network modelling of fluid intelligence. (A) Network-based statistics identify a significant network associated reduced adjusted APM scores (FWER-P < 0.0001). (B) Radial graph of the community structure of the network inferred from a stochastic block model of its statistics shows that the network clusters into three discrete components encompassing the superolateral cortical surface, the medial (and inferior) wall and a superior frontal gyrus dominant cluster. Nodes are colour-coded in accordance with their stochastic block model cluster. Node size is proportional to node degree count. Edge width and colour is proportional to the t-statistic from the model, with a thicker and more yellow line denoting a stronger link between a given network connection and a reduced adjusted APM score. ACG = anterior cingulate gyrus; L = left; IFG = inferior frontal gyrus; IFG-pt = inferior frontal gyrus pars triangularis; MFG = middle frontal gyrus; OFC = orbitofrontal cortex; PreCg = pre-central gyrus; PoCg = post-central gyrus; R = right; SFG = superior frontal gyrus; SPL = superior parietal lobule.

Figure 3

Predicting fluid intelligence from network properties. (A) Violin plots of the adjusted APM scores of patients whose lesions do or do not overlap with the inferred network illustrate significantly lower APM scores in the former [R² 0.105, coefficient mean ± SD −0.265 ± 0.068 (95% CI −0.396 to −0.129]. (B) Scatter and line plot shows that the degree count of the overlap of a lesion with the inferred network significantly correlates with adjusted APM scores within a univariate Bayesian regression model [R² 0.190, coefficient mean ± SD −0.002 ± 0.0005 (95% CI −0.00250 to −0.00041]. (C) Histogram of the edge t-statistics from the network model illustrates the population of edges significantly associated with the APM after multiple comparisons correction. (D) Scatter and line plot shows the predictability of adjusted APM from the network adjacency matrix within a multivariate Bayesian model (R² 0.640).

Figure 4

Generative stochastic block models of fluid intelligence. (A) Radial graphs of stochastic block models with adjusted APM and lesion co-occurrence layered (top), versus randomly distributed across layers (bottom). Edge colour and width is proportional to the associated edge weight. Model entropy favoured the layered over the null model. (B) Radial graph illustrating the layered stochastic block model fit with edge colour and width proportional to the lesion co-occurrence weight, and node colour and size proportional to the lesion-weight degree. This demonstrates a community of highly interconnected voxels involving the bilateral frontal pole and orbitofrontal cortex, right superior and inferior frontal gyrus and anterior cingulate gyrus. (C) Radial graph illustrating the layered stochastic block model fit with edge colour and width proportional to the adjusted APM weight, node colour and size proportional to the APM-weight degree. This illustrates a characteristically different segregation of brain communities, with high edge incidence linking the right middle and inferior frontal gyrus, (including pars triangularis), right pre-central gyrus and right superior parietal lobule. Brain images are overlayed corresponding to the posterior mean edge weight at these communities. ACG = anterior cingulate gyrus; L = left; IFG = inferior frontal gyrus; IFG-pt = inferior frontal gyrus pars triangularis; MFG = middle frontal gyrus; OFC = orbitofrontal cortex; PreCg = pre-central gyrus; PoCg = post-central gyrus; R = right; SFG = superior frontal gyrus; SPL = superior parietal lobule.

Figure 5

Network communities sensitive to fluid intelligence. A. Axial slices of the mean posterior edge weight for each block at the l₁ aggregation, with more red-orange areas corresponding to a greater value and greater relation to adjusted APM. B. Scatterplot illustrating the relationship between posterior mean edge weights at each community block, for both the lesion weight (y-axis) and adjusted APM (x-axis), with brain reconstructions overlaying these findings. Of note, bilateral frontal-based blocks depicted higher lesion-weight edges, with right fronto blocks more implicating APM. ACG = anterior cingulate gyrus; L = left; IFG= inferior frontal gyrus; IFG-pt = inferior frontal gyrus pars triangularis; MFG = middle frontal gyrus; OFC = orbitofrontal cortex; PreCg = pre-central gyrus; PoCg = post-central gyrus; R = right; SFG = superior frontal gyrus; SPL = superior parietal lobule.