Machine Learning Detects Symptomatic Plaques in Patients With Carotid Atherosclerosis on CT Angiography.

BACKGROUND: This study aimed to develop and validate a computed tomography angiography based machine learning model that uses plaque composition data and degree of carotid stenosis to detect symptomatic carotid plaques in patients with carotid atherosclerosis. METHODS: The machine learning based model was trained using degree of stenosis and the volumes of 13 computed tomography angiography derived intracarotid plaque subcomponents (eg, lipid, intraplaque hemorrhage, calcium) to identify plaques associated with cerebrovascular events. The model was internally validated through repeated 10-fold cross-validation and tested on a dedicated testing cohort according to discrimination and calibration. RESULTS: This retrospective, single-center study evaluated computed tomography angiography scans of 268 patients with both symptomatic and asymptomatic carotid atherosclerosis (163 for the derivation set and 106 for the testing set) performed between March 2013 and October 2019. The area-under-receiver-operating characteristics curve by machine learning on the testing cohort (0.89) was significantly higher than the areas under the curve of traditional logit analysis based on the degree of stenosis (0.51, P<0.001), presence of intraplaque hemorrhage (0.69, P<0.001), and plaque composition (0.78, P<0.001), respectively. Comparable performance was obtained on internal validation. The identified plaque components and associated cutoff values that were significantly associated with a higher likelihood of symptomatic status after adjustment were the ratio of intraplaque hemorrhage to lipid volume (≥50%, 38.5 [10.1-205.1]; odds ratio, 95% CI) and percentage of intraplaque hemorrhage volume (≥10%, 18.5 [5.7-69.4]; odds ratio, 95% CI). CONCLUSIONS: This study presented an interpretable machine learning model that accurately identifies symptomatic carotid plaques using computed tomography angiography derived plaque composition features, aiding clinical decision-making.

Structural connectivity at term equivalent age and language in preterm children at 2 years corrected.

We previously reported interhemispheric structural hyperconnectivity bypassing the corpus callosum in children born extremely preterm (<28 weeks) versus term children. This increased connectivity was positively associated with language performance at 4-6 years of age in our prior work. In the present study, we aim to investigate whether this extracallosal connectivity develops in extremely preterm infants at term equivalent age by leveraging a prospective cohort study of 350 very and extremely preterm infants followed longitudinally in the Cincinnati Infant Neurodevelopment Early Prediction Study. For this secondary analysis, we included only children born extremely preterm and without significant brain injury (n = 95). We use higher-order diffusion modelling to assess the degree to which extracallosal pathways are present in extremely preterm infants and predictive of later language scores at 22-26 months corrected age. We compare results obtained from two higher-order diffusion models: generalized q-sampling imaging and constrained spherical deconvolution. Advanced MRI was obtained at term equivalent age (39-44 weeks post-menstrual age). For structural connectometry analysis, we assessed the level of correlation between white matter connectivity at the whole-brain level at term equivalent age and language scores at 2 years corrected age, controlling for post-menstrual age, sex, brain abnormality score and social risk. For our constrained spherical deconvolution analyses, we performed connectivity-based fixel enhancement, using probabilistic tractography to inform statistical testing of the hypothesis that fibre metrics at term equivalent age relate to language scores at 2 years corrected age after adjusting for covariates. Ninety-five infants were extremely preterm with no significant brain injury. Of these, 53 had complete neurodevelopmental and imaging data sets that passed quality control. In the connectometry analyses adjusted for covariates and multiple comparisons (P < 0.05), the following tracks were inversely correlated with language: bilateral cerebellar white matter and middle cerebellar peduncles, bilateral corticospinal tracks, posterior commissure and the posterior inferior fronto-occipital fasciculus. No tracks from the constrained spherical deconvolution/connectivity-based fixel enhancement analyses remained significant after correction for multiple comparisons. Our findings provide critical information about the ontogeny of structural brain networks supporting language in extremely preterm children. Greater connectivity in more posterior tracks that include the cerebellum and connections to the regions of the temporal lobes at term equivalent age appears to be disadvantageous for language development.

Virtual lesions in MEG reveal increasing vulnerability of the language network from early childhood through adolescence.

In childhood, language outcomes following brain injury are inversely related to age. Neuroimaging findings suggest that extensive representation and/or topological redundancy may confer the pediatric advantage. Here, we assess whole brain and language network resilience using in silico attacks, for 85 children participating in a magnetoencephalography (MEG) study. Nodes are targeted based on eigenvector centrality, betweenness centrality, or at random. The size of each connected component is assessed after iterated node removal; the percolation point, or moment of dis-integration, is defined as the first instance where the second largest component peaks in size. To overcome known effects of fixed thresholding on subsequent graph and resilience analyses, we study percolation across all possible network densities, within a Functional Data Analysis (FDA) framework. We observe age-related increases in vulnerability for random and betweenness centrality-based attacks for whole-brain and stories networks (adjusted-p < 0.05). Here we show that changes in topology underlie increasing language network vulnerability in development.

Altered white matter connectivity in children with congenital heart disease with single ventricle physiology.

Children born with congenital heart disease (CHD) have seen a dramatic decrease in mortality thanks to surgical innovations. However, there are numerous risk factors associated with CHD that can disrupt neurodevelopment. Recent studies have found that psychological deficits and structural brain abnormalities persist into adulthood. The goal of the current study was to investigate white matter connectivity in early school-age children (6-11 years), born with complex cyanotic CHD (single ventricle physiology), who have undergone Fontan palliation, compared to a group of heart-healthy, typically developing controls (TPC). Additionally, we investigated associations between white matter tract connectivity and measures on a comprehensive neuropsychological battery within each group. Our results suggest CHD patients exhibit widespread decreases in white matter connectivity, and the extent of these decreases is related to performance in several cognitive domains. Analysis of network topology showed that hub distribution was more extensive and bilateral in the TPC group. Our results are consistent with previous studies suggesting perinatal ischemia leads to white matter lesions and delayed maturation.

Extracallosal Structural Connectivity Is Positively Associated With Language Performance in Well-Performing Children Born Extremely Preterm.

Children born extremely preterm (<28 weeks gestation) are at risk for language delay or disorders. Decreased structural connectivity in preterm children has been associated with poor language outcome. Previously, we used multimodal imaging techniques to demonstrate that increased functional connectivity during a stories listening task was positively associated with language scores for preterm children. This functional connectivity was supported by extracallosal structural hyperconnectivity when compared to term-born children. Here, we attempt to validate this finding in a distinct cohort of well-performing extremely preterm children (EPT, n = 16) vs. term comparisons (TC, n = 28) and also compare this to structural connectivity in a group of extremely preterm children with a history of language delay or disorder (EPT-HLD, n = 8). All participants are 4-6 years of age. We perform q-space diffeomorphic reconstruction and functionally-constrained structural connectometry (based on fMRI activation), including a novel extension enabling between-groups comparisons with non-parametric ANOVA. There were no significant differences between groups in age, sex, race, ethnicity, parental education, family income, or language scores. For EPT, tracks positively associated with language scores included the bilateral posterior inferior fronto-occipital fasciculi and bilateral cerebellar peduncles and additional cerebellar white matter. Quantitative anisotropy in these pathways accounted for 55% of the variance in standardized language scores for the EPT group specifically. Future work will expand this cohort and follow longitudinally to investigate the impact of environmental factors on developing language networks and resiliency in the preterm brain.

Automated grading of enlarged perivascular spaces in clinical imaging data of an acute stroke cohort using an interpretable, 3D deep learning framework.

Enlarged perivascular spaces (EPVS), specifically in stroke patients, has been shown to strongly correlate with other measures of small vessel disease and cognitive impairment at 1 year follow-up. Typical grading of EPVS is often challenging and time consuming and is usually based on a subjective visual rating scale. The purpose of the current study was to develop an interpretable, 3D neural network for grading enlarged perivascular spaces (EPVS) severity at the level of the basal ganglia using clinical-grade imaging in a heterogenous acute stroke cohort, in the context of total cerebral small vessel disease (CSVD) burden. T2-weighted images from a retrospective cohort of 262 acute stroke patients, collected in 2015 from 5 regional medical centers, were used for analyses. Patients were given a label of 0 for none-to-mild EPVS (< 10) and 1 for moderate-to-severe EPVS (≥ 10). A three-dimensional residual network of 152 layers (3D-ResNet-152) was created to predict EPVS severity and 3D gradient class activation mapping (3DGradCAM) was used for visual interpretation of results. Our model achieved an accuracy 0.897 and area-under-the-curve of 0.879 on a hold-out test set of 15% of the total cohort (n = 39). 3DGradCAM showed areas of focus that were in physiologically valid locations, including other prevalent areas for EPVS. These maps also suggested that distribution of class activation values is indicative of the confidence in the model's decision. Potential clinical implications of our results include: (1) support for feasibility of automated of EPVS scoring using clinical-grade neuroimaging data, potentially alleviating rater subjectivity and improving confidence of visual rating scales, and (2) demonstration that explainable models are critical for clinical translation.

Cross-Frequency Coupling in Childhood Absence Epilepsy.

Objective: Absence seizures are the prototypic primarily generalized seizures, but there is incomplete understanding regarding their generation and maintenance. A core network for absence seizures has been defined, including focal cortical and thalamic regions that have frequency-dependent interactions. The purpose of this study was to investigate within-frequency coupling and cross-frequency coupling (CFC) during human absence seizures, to identify key regions (hubs) within the absence network that contribute to propagation and maintenance. Methods: Thirteen children with new-onset and untreated childhood absence epilepsy had over 60 typical absence seizures during both electroencephalography-functional magnetic resonance imaging (fMRI) and magnetoencephalography (MEG) recordings. The spatial map of the ictal network was defined using fMRI and used as prior information for MEG connectivity. A multilayer network approach was used to investigate within-frequency coupling and CFC for canonical frequency bands. A rigorous null-modeling approach was used to determine connections outside the noise floor. Results: Strong coupling between beta and gamma frequencies, within the left frontal cortex, and between the left frontal and right parietal regions was observed. There was also strong connectivity between left frontal and right parietal nodes within the gamma band. Multilayer versatility analysis identified a cluster of network hubs in the left frontal region. Interpretation: Cortical regions commonly identified as being critical for absence seizure generation (frontal cortex, precuneus) have strong CFC and within-frequency coupling between beta and gamma bands. As nonpharmacologic treatments, such as neuromodulation, become available for generalized epilepsies, detailed mechanistic understanding of how "diffuse" seizures are generated and maintained will be necessary to provide optimal outcomes.

Beta synchrony for expressive language lateralizes to right hemisphere in development.

A left perisylvian network is known to support language in healthy adults. Low-beta (13-23 Hz) event-related desynchrony (ERD) has been observed during verb generation, at approximately 700-1200 ms post-stimulus presentation in past studies; the signal is known to reflect increased neuronal firing and metabolic demand during language production. In contrast, concurrent beta event-related synchrony (ERS) is thought to reflect neuronal inhibition but has not been well studied in the context of language. Further, while low-beta ERD for expressive language has been found to gradually shift from bilateral in childhood to left hemispheric by early adulthood, developmental lateralization of ERS has not been established. We used magnetoencephalography to study low beta ERS lateralization in a group of children and adolescents (n = 78), aged 4 to less than 19 years, who performed covert verb generation. We found that the youngest children had bilateral ERD and ERS. By adolescence, low-beta ERD was predominantly left lateralized in perisylvian cortex (i.e., Broca's and Wernicke's regions), while beta ERS was predominantly right lateralized. Increasing lateralization was significantly correlated to age for both ERD (Spearman's r = 0.45, p < 0.01) and ERS (Spearman's r = - 0.44, p < 0.01). Interestingly, while ERD lateralized in a linear manner, ERS lateralization followed a nonlinear trajectory, suggesting distinct developmental trajectories. Implications to early-age neuroplasticity and neuronal inhibition are discussed.

Multilayer Connector Hub Mapping Reveals Key Brain Regions Supporting Expressive Language.

Introduction: How components of the distributed brain networks that support cognition participate in typical functioning remains a largely unanswered question. An important subgroup of regions in the larger network are connector hubs, which are areas that are highly connected to several other functionally specialized sets of regions, and are likely important for sensorimotor integration. The present study attempts to characterize connector hubs involved in typical expressive language functioning using a data-driven, multimodal, full multilayer magnetoencephalography (MEG) connectivity-based pipeline. Methods: Twelve adolescents, 16-18 years of age (five males), participated in this study. Participants underwent MEG scanning during a verb generation task. MEG and structural connectivity were calculated at the whole-brain level. Amplitude/amplitude coupling (AAC) was used to compute functional connections both within and between discrete frequency bins. AAC values were then multiplied by a binary structural connectivity matrix, and then entered into full multilayer network analysis. Initially, hubs were defined based on multilayer versatility and subsequently reranked by a novel measure called delta centrality on interconnectedness (DCI). DCI is defined as the percent change in interfrequency interconnectedness after removal of a hub. Results: We resolved regions that are important for between-frequency communication among other areas during expressive language, with several potential theoretical and clinical applications that can be generalized to other cognitive domains. Conclusion: Our multilayer, data-driven framework captures nonlinear connections that span across scales that are often missed in conventional analyses. The present study suggests that crucial hubs may be conduits for interfrequency communication between action and perception systems that are crucial for typical functioning.

Extremely preterm children exhibit altered cortical thickness in language areas.

Children born extremely preterm (< 28 weeks gestation, EPT) are at increased risk for language and other neurocognitive deficits compared to term controls (TC). Prior studies have reported both increases and decreases in cortical thickness in EPT across the cerebrum. These studies have not formally normalized for intracranial volume (ICV), which is especially important as EPT children often have smaller stature, head size, and ICV. We previously reported increased interhemispheric functional and structural connectivity in a well-controlled group of school-aged EPT children with no known brain injury or neurological deficits. Functional and structural hyperconnectivity between left and right temporoparietal regions was positively related with language scores in EPT, which may be reflected in measures of cortical thickness. To characterize possible language network cortical thickness effects, 15 EPT children and 15 TC underwent standardized assessments of language and structural magnetic resonance imaging at 4 to 6 years of age. Images were subjected to volumetric and cortical thickness analyses using FreeSurfer. Whole-brain analyses of cortical thickness were conducted both with and without normalization by ICV. Non-normalized results showed thinner temporal cortex for EPT, while ICV-normalized results showed thicker cortical regions in the right temporal lobe (FDRq = 0.05). Only ICV-normalized results were significantly related to language scores, with right temporal cortical thickness being positively correlated with performance.

Rewiring the extremely preterm brain: Altered structural connectivity relates to language function.

Children born preterm are at increased risk for cognitive impairment, with higher-order functions such as language being especially vulnerable. Previously, we and others have reported increased interhemispheric functional connectivity in children born extremely preterm; the finding appears at odds with literature showing decreased integrity of the corpus callosum, the primary commissural bundle, in preterm children. We address the apparent discrepancy by obtaining advanced measures of structural connectivity in twelve school-aged children born extremely preterm (<28 weeks) and ten term controls. We hypothesize increased extracallosal structural connectivity might support the functional hyperconnectivity we had previously observed. Participants were aged four to six years at time of study and groups did not differ in age, sex, race, ethnicity, or socioeconomic status. Whole-brain and language-network-specific (functionally-constrained) connectometry analyses were performed. At the whole-brain level, preterm children had decreased connectivity in the corpus callosum and increased connectivity in the cerebellum versus controls. Functionally-constrained analyses revealed significantly increased extracallosal connectivity between bilateral temporal regions in preterm children (FDRq <0.05). Connectivity within these extracallosal pathways was positively correlated with performance on standardized language assessments in children born preterm (FDRq <0.001), but unrelated to performance in controls. This is the first study to identify anatomical substrates for increased interhemispheric functional connectivity in children born preterm; increased reliance on an extracallosal pathway may represent a biomarker for resiliency following extremely preterm birth.

Detrended connectometry analysis to assess white matter correlates of performance in childhood.

The white matter of the brain develops in a robust, regionally-variant, nonlinear manner during childhood. To relate white matter connectivity to performance, these regional nonlinear effects of age must be accounted for. Here, we identify white matter correlates of gross intellectual functioning using cutting-edge diffusion analyses inside a data-driven two-step regression framework. A total of 98 participants, ages 3-18 years, were included in the analyses. First, white matter connectivity was modeled as a function of age for each fiber direction at each voxel, extracted from the spin distribution function, using a 6th-order B-spline. The smoothing parameter for each direction was chosen by minimizing generalized cross-validation (GCV), which prevents overfitting while remaining sensitive to potentially nonlinear effects of age. In the second step, the resulting Gaussian residuals were modeled as a function of either full-scale IQ (FSIQ), or of verbal IQ (VIQ) and performance IQ (PIQ), using a linear regression framework (connectometry). Graph theoretical analyses were also performed to assess how each predictor relates to global topological changes, including average clustering coefficient, characteristic path length, global efficiency, average local efficiency, and small worldness. Analyses revealed widespread positive associations between white matter connectivity and FSIQ, including regions of the corpus callosum, fornix, and corticothalamic tracts (FDRq < .05). A separate regression model revealed a selective positive relationship between VIQ and white matter connectivity in predominately frontal tracts (e.g., anterior corticothalamic radiations, fornix, anterior corpus callosum, frontopontine tracts); in contrast, PIQ predicted white matter connectivity in the posterior brain (e.g. parietopontine tracts, posterior corticothalamic radiations, posterior corticostriatal projections), (FDRq < .05). No negative correlations were observed. Graph analyses revealed FSIQ, VIQ while controlling for PIQ, and PIQ while controlling for VIQ increase clustering coefficient, global efficiency, local efficiency, and small worldness, and decrease characteristic path length of the network. Results indicate regional white matter changes related to cognitive skills in childhood, independent of age.

Mapping Critical Language Sites in Children Performing Verb Generation: Whole-Brain Connectivity and Graph Theoretical Analysis in MEG.

A classic left frontal-temporal brain network is known to support language processes. However, the level of participation of constituent regions, and the contribution of extra-canonical areas, is not fully understood; this is particularly true in children, and in individuals who have experienced early neurological insult. In the present work, we propose whole-brain connectivity and graph-theoretical analysis of magnetoencephalography (MEG) source estimates to provide robust maps of the pediatric expressive language network. We examined neuromagnetic data from a group of typically-developing young children (n = 15, ages 4-6 years) and adolescents (n = 14, 16-18 years) completing an auditory verb generation task in MEG. All source analyses were carried out using a linearly-constrained minimum-variance (LCMV) beamformer. Conventional differential analyses revealed significant (p < 0.05, corrected) low-beta (13-23 Hz) event related desynchrony (ERD) focused in the left inferior frontal region (Broca's area) in both groups, consistent with previous studies. Connectivity analyses were carried out in broadband (3-30 Hz) on time-course estimates obtained at the voxel level. Patterns of connectivity were characterized by phase locking value (PLV), and network hubs identified through eigenvector centrality (EVC). Hub analysis revealed the importance of left perisylvian sites, i.e., Broca's and Wernicke's areas, across groups. The hemispheric distribution of frontal and temporal lobe EVC values was asymmetrical in most subjects; left dominant EVC was observed in 20% of young children, and 71% of adolescents. Interestingly, the adolescent group demonstrated increased critical sites in the right cerebellum, left inferior frontal gyrus (IFG) and left putamen. Here, we show that whole brain connectivity and network analysis can be used to map critical language sites in typical development; these methods may be useful for defining the margins of eloquent tissue in neurosurgical candidates.

Stroop interference associated with efficient reading fluency and prelexical orthographic processing.

The Stroop Color-Word Test involves a dynamic interplay between reading and executive functioning that elicits intuitions of word reading automaticity. One such intuition is that strong reading skills (i.e., more automatized word reading) play a disruptive role within the test, contributing to Stroop interference. However, evidence has accumulated that challenges this intuition. The present study examined associations among Stroop interference, reading skills (i.e., isolated word identification, grapheme-to-phoneme mapping, phonemic awareness, reading fluency) measured on standardized tests, and orthographic skills measured on experimental computerized tasks. Among university students (N = 152), correlational analyses showed greater Stroop interference to be associated with (a) relatively low scores on all standardized reading tests, and (b) longer response latencies on orthographic tasks. Hierarchical regression demonstrated that reading fluency and prelexical orthographic processing predicted unique and significant variance in Stroop interference beyond baseline rapid naming. Results suggest that strong reading skills, including orthographic processing, play a supportive role in resolving Stroop interference.