Exploring the link between tooth loss, cognitive function, and brain wellness in the context of healthy aging.

AIMS: The aim of this study was to evaluate the utility of using MRI-derived tooth count, an indirect and nonspecific indicator of oral/periodontal health, and brain age gap (BAG), an MRI-based measure of premature brain aging, in predicting cognition in a population of otherwise healthy adults. METHODS: This retrospective study utilized data from 329 participants from the University of South Carolina's Aging Brain Cohort Repository. Participants underwent neuropsychological testing including the Montreal Cognitive Assessment (MoCA), completed an oral/periodontal health questionnaire, and submitted to high-resolution structural MRI imaging. The study compared variability on cognitive scores (MoCA) accounted for by MRI-derived BAG, MRI-derived total tooth count, and self-reported oral/periodontal health. RESULTS: We report a significant positive correlation between the total number of teeth and MoCA total scores after controlling for age, sex, and race, indicating a robust relationship between tooth count and cognition, r(208) = .233, p < .001. In a subsample of participants identified as being at risk for MCI (MoCA <= 25, N = 36) inclusion of MRI-based tooth count resulted in an R2 change of .192 (H0 = 0.138 → H1 = 0.330), F(1,31) = 8.86, p = .006. Notably, inclusion of BAG, a valid and reliable measure of overall brain health, did not significantly improve prediction of MoCA scores in similar linear regression models. CONCLUSIONS: Our data support the idea that inclusion of MRI-based total tooth count may enhance the ability to predict clinically meaningful differences in cognitive abilities in healthy adults. This study contributes to the growing body of evidence linking oral/periodontal health with cognitive function.

Diabetes, brain health, and treatment gains in post-stroke aphasia.

In post-stroke aphasia, language improvements following speech therapy are variable and can only be partially explained by the lesion. Brain tissue integrity beyond the lesion (brain health) may influence language recovery and can be impacted by cardiovascular risk factors, notably diabetes. We examined the impact of diabetes on structural network integrity and language recovery. Seventy-eight participants with chronic post-stroke aphasia underwent six weeks of semantic and phonological language therapy. To quantify structural network integrity, we evaluated the ratio of long-to-short-range white matter fibers within each participant's whole brain connectome, as long-range fibers are more susceptible to vascular injury and have been linked to high level cognitive processing. We found that diabetes moderated the relationship between structural network integrity and naming improvement at 1 month post treatment. For participants without diabetes (n = 59), there was a positive relationship between structural network integrity and naming improvement (t = 2.19, p = 0.032). Among individuals with diabetes (n = 19), there were fewer treatment gains and virtually no association between structural network integrity and naming improvement. Our results indicate that structural network integrity is associated with treatment gains in aphasia for those without diabetes. These results highlight the importance of post-stroke structural white matter architectural integrity in aphasia recovery.

Neural Activity During Imagery Supports Three Imagery Abilities as Measured by the Movement Imagery Questionnaire-3.

Self-report and neural data were examined in 14 right-handed college-age males screened from a pool of 200 to verify neural activity during imagery and that the neural activity (area of brain) varies as a function of the imagery type. Functional magnetic resonance imaging data collected during real-time imagery of the three Movement Imagery Questionnaire-3 abilities indicated frontal areas, motor areas, and cerebellum active during kinesthetic imagery, motor areas, and superior parietal lobule during internal visual imagery, and parietal lobule and occipital cortex during external visual imagery. Central and imagery-specific neural patterns were found providing further biological validation of kinesthetic, internal visual, and external visual complementing results on females. Next, research should (a) compare neural activity between male participants screened by self-reported imagery abilities to determine if good imagers have more efficient neural networks than poor imagers and (b) determine if there is a statistical link between participants' neural activity during imagery and self-report Movement Imagery Questionnaire-3 scores.

Machine learning-based multimodal prediction of language outcomes in chronic aphasia.

Recent studies have combined multiple neuroimaging modalities to gain further understanding of the neurobiological substrates of aphasia. Following this line of work, the current study uses machine learning approaches to predict aphasia severity and specific language measures based on a multimodal neuroimaging dataset. A total of 116 individuals with chronic left-hemisphere stroke were included in the study. Neuroimaging data included task-based functional magnetic resonance imaging (fMRI), diffusion-based fractional anisotropy (FA)-values, cerebral blood flow (CBF), and lesion-load data. The Western Aphasia Battery was used to measure aphasia severity and specific language functions. As a primary analysis, we constructed support vector regression (SVR) models predicting language measures based on (i) each neuroimaging modality separately, (ii) lesion volume alone, and (iii) a combination of all modalities. Prediction accuracy across models was subsequently statistically compared. Prediction accuracy across modalities and language measures varied substantially (predicted vs. empirical correlation range: r = .00-.67). The multimodal prediction model yielded the most accurate prediction in all cases (r = .53-.67). Statistical superiority in favor of the multimodal model was achieved in 28/30 model comparisons (p-value range: <.001-.046). Our results indicate that different neuroimaging modalities carry complementary information that can be integrated to more accurately depict how brain damage and remaining functionality of intact brain tissue translate into language function in aphasia.

Impaired frontostriatal functional connectivity among chronic opioid using pain patients is associated with dysregulated affect.

Preclinical studies have shown effects of chronic exposure to addictive drugs on glutamatergic-mediated neuroplasticity in frontostriatal circuitry. These initial findings have been paralleled by human functional magnetic resonance imaging (fMRI) research demonstrating weaker frontostriatal resting-state functional connectivity (rsFC) among individuals with psychostimulant use disorders. However, there is a dearth of human imaging literature describing associations between long-term prescription opioid use, frontostriatal rsFC, and brain morphology among chronic pain patients. We hypothesized that prescription opioid users with chronic pain, as compared with healthy control subjects, would evidence weaker frontostriatal rsFC coupled with less frontostriatal gray matter volume (GMV). Further, those opioid use-related deficits in frontostriatal circuitry would be associated with negative affect and drug misuse. Prescription opioid users with chronic pain (n = 31) and drug-free healthy controls (n = 30) underwent a high-resolution anatomical and an eyes-closed resting-state functional scan. The opioid group, relative to controls, exhibited weaker frontostriatal rsFC, and less frontostriatal GMV in both L.NAc and L.vmPFC. Frontostriatal rsFC partially mediated group differences in negative affect. Within opioid users, L.NAc GMV predicted opioid misuse severity. The current study revealed that prescription opioid use in the context of chronic pain is associated with functional and structural abnormalities in frontostriatal circuitry. These results suggest that opioid use-related abnormalities in frontostriatal circuitry may undergird disturbances in affect that may contribute to the ongoing maintenance of opioid use and misuse. These findings warrant further examination of interventions to treat opioid pathophysiology in frontostriatal circuitry over the course of treatment.

Visual Simultaneity Judgments Activate a Bilateral Frontoparietal Timing System.

In everyday life, we often make judgments regarding the sequence of events, for example, deciding whether a baseball runner's foot hit the plate before or after the ball hit the glove. Numerous studies have examined the functional correlates of temporal processing using variations of the temporal order judgment and simultaneity judgment (SJ) tasks. To perform temporal order judgment tasks, observers must bind temporal information with identity and/or spatial information relevant to the task itself. SJs, on the other hand, require observers to detect stimulus asynchrony but not the order of stimulus presentation and represent a purer measure of temporal processing. Some previous studies suggest that these temporal decisions rely primarily on right-hemisphere parietal structures, whereas others provide evidence that temporal perception depends on bilateral TPJ or inferior frontal regions (inferior frontal gyrus). Here, we report brain activity elicited by a visual SJ task. Our methods are unique given our use of two orthogonal control conditions, discrimination of spatial orientation and color, which were used to control for brain activation associated with the classic dorsal ("where/how") and ventral ("what") visual pathways. Our neuroimaging experiment shows that performing the SJ task selectively activated a bilateral network in the parietal (TPJ) and frontal (inferior frontal gyrus) cortices. We argue that SJ tasks are a purer measure of temporal perception because they do not require observers to process either identity or spatial information, both of which may activate separate cognitive networks.

Biological evidence of imagery abilities: intraindividual differences.

This study extended motor imagery theories by establishing specificity and verification of expected brain activation patterns during imagery. Eighteen female participants screened with the Movement Imagery Questionnaire-3 (MIQ-3) as having good imagery abilities were scanned to determine the neural networks active during an arm rotation task. Four experimental conditions (i.e., KINESTHETIC, INTERNAL Perspective, EXTERNAL Perspective, and REST) were randomly presented (counterbalanced for condition) during three brain scans. Behaviorally, moderate interscale correlations were found between the MIQ-3 and Vividness of Movement Imagery Questionnaire-2, indicating relatedness between the questionnaires. Partially confirming our hypotheses, common and distinct brain activity provides initial biological validation for imagery abilities delineated in the MIQ-3: kinesthetic imagery activated motor-related areas, internal visual imagery activated inferior parietal lobule, and external visual imagery activated temporal, but no occipital areas. Lastly, inconsistent neuroanatomical intraindividual differences per condition were found. These findings relative to recent biological evidence of imagery abilities are highlighted.

Distinct brain morphometry patterns revealed by deep learning improve prediction of post-stroke aphasia severity.

BACKGROUND: Emerging evidence suggests that post-stroke aphasia severity depends on the integrity of the brain beyond the lesion. While measures of lesion anatomy and brain integrity combine synergistically to explain aphasic symptoms, substantial interindividual variability remains unaccounted. One explanatory factor may be the spatial distribution of morphometry beyond the lesion (e.g., atrophy), including not just specific brain areas, but distinct three-dimensional patterns. METHODS: Here, we test whether deep learning with Convolutional Neural Networks (CNNs) on whole brain morphometry (i.e., segmented tissue volumes) and lesion anatomy better predicts chronic stroke individuals with severe aphasia (N = 231) than classical machine learning (Support Vector Machines; SVMs), evaluating whether encoding spatial dependencies identifies uniquely predictive patterns. RESULTS: CNNs achieve higher balanced accuracy and F1 scores, even when SVMs are nonlinear or integrate linear or nonlinear dimensionality reduction. Parity only occurs when SVMs access features learned by CNNs. Saliency maps demonstrate that CNNs leverage distributed morphometry patterns, whereas SVMs focus on the area around the lesion. Ensemble clustering of CNN saliencies reveals distinct morphometry patterns unrelated to lesion size, consistent across individuals, and which implicate unique networks associated with different cognitive processes as measured by the wider neuroimaging literature. Individualized predictions depend on both ipsilateral and contralateral features outside the lesion. CONCLUSIONS: Three-dimensional network distributions of morphometry are directly associated with aphasia severity, underscoring the potential for CNNs to improve outcome prognostication from neuroimaging data, and highlighting the prospective benefits of interrogating spatial dependence at different scales in multivariate feature space.

Some stroke survivors experience difficulties understanding and producing language. We performed brain imaging to capture information about brain structure in stroke survivors and used it to predict which survivors have more severe language problems. We found that a type of artificial intelligence (AI) specifically designed to find patterns in spatial data was more accurate at this task than more traditional methods. AI found more complex patterns of brain structure that distinguish stroke survivors with severe language problems by analyzing the brain's spatial properties. Our findings demonstrate that AI tools can provide new information about brain structure and function following stroke. With further developments, these models may be able to help clinicians understand the extent to which language problems can be improved after a stroke.

Improving 3D edge detection for visual inspection of MRI coregistration and alignment.

BACKGROUND: Visualizing edges is critical for neuroimaging. For example, edge maps enable quality assurance for the automatic alignment of an image from one modality (or individual) to another. NEW METHOD: We suggest that using the second derivative (difference of Gaussian, or DoG) provides robust edge detection. This method is tuned by size (which is typically known in neuroimaging) rather than intensity (which is relative). RESULTS: We demonstrate that this method performs well across a broad range of imaging modalities. The edge contours produced consistently form closed surfaces, whereas alternative methods may generate disconnected lines, introducing potential ambiguity in contiguity. COMPARISON WITH EXISTING METHODS: Current methods for computing edges are based on either the first derivative of the image (FSL), or a variation of the Canny Edge detection method (AFNI). These methods suffer from two primary limitations. First, the crucial tuning parameter for each of these methods relates to the image intensity. Unfortunately, image intensity is relative for most neuroimaging modalities making the performance of these methods unreliable. Second, these existing approaches do not necessarily generate a closed edge/surface, which can reduce the ability to determine the correspondence between a represented edge and another image. CONCLUSION: The second derivative is well suited for neuroimaging edge detection. We include this method as part of both the AFNI and FSL software packages, standalone code and online.

Under pressure: the interplay of hypertension and white matter hyperintensities with cognition in chronic stroke aphasia.

While converging research suggests that increased white matter hyperintensity load is associated with poorer cognition, and the presence of hypertension is associated with increased white matter hyperintensity load, the relationship among hypertension, cognition and white matter hyperintensities is not well understood. We sought to determine the effect of white matter hyperintensity burden on the relationship between hypertension and cognition in individuals with post-stroke aphasia, with the hypothesis that white matter hyperintensity load moderates the relationship between history of hypertension and cognitive function. Health history, Fazekas scores for white matter hyperintensities and Wechsler Adult Intelligence Scale Matrix Reasoning subtest scores for 79 people with aphasia collected as part of the Predicting Outcomes of Language Rehabilitation study at the Center for the Study of Aphasia Recovery at the University of South Carolina and the Medical University of South Carolina were analysed retrospectively. We found that participants with a history of hypertension had increased deep white matter hyperintensity severity (P < 0.001), but not periventricular white matter hyperintensity severity (P = 0.116). Moderation analysis revealed that deep white matter hyperintensity load moderates the relationship between high blood pressure and Wechsler Adult Intelligence Scale scores when controlling for age, education, aphasia severity and lesion volume. The interaction is significant, showing that a history of high blood pressure and severe deep white matter hyperintensities together are associated with poorer Matrix Reasoning scores. The overall model explains 41.85% of the overall variation in Matrix Reasoning score in this group of participants. These findings underscore the importance of considering cardiovascular risk factors in aphasia treatment, specifically hypertension and its relationship to brain health in post-stroke cognitive function.

Progressive lesion necrosis is related to increasing aphasia severity in chronic stroke.

BACKGROUND: Volumetric investigations of cortical damage resulting from stroke indicate that lesion size and shape continue to change even in the chronic stage of recovery. However, the potential clinical relevance of continued lesion growth has yet to be examined. In the present study, we investigated the prevalence of lesion expansion and the relationship between expansion and changes in aphasia severity in a large sample of individuals in the chronic stage of aphasia recovery. METHODS: Retrospective structural MRI scans from 104 S survivors with at least 2 observations (k = 301 observations; mean time between scans = 31 months) were included. Lesion demarcation was performed using an automated lesion segmentation software and lesion volumes at each timepoint were subsequently calculated. A linear mixed effects model was conducted to investigate the effect of days between scan on lesion expansion. Finally, we investigated the association between lesion expansion and changes on the Western Aphasia Battery (WAB) in a group of participants assessed and scanned at 2 timepoints (N = 54) using a GLM. RESULTS: Most participants (81 %) showed evidence of lesion expansion. The mixed effects model revealed lesion volumes significantly increase, on average, by 0.02 cc each day (7.3 cc per year) following a scan (p < 0.0001). Change on language performance was significantly associated with change in lesion volume (p = 0.025) and age at stroke (p = 0.031). The results suggest that with every 10 cc increase in lesion size, language performance decreases by 0.9 points, and for every 10-year increase in age at stroke, language performance decreases by 1.9 points. CONCLUSIONS: The present study confirms and extends prior reports that lesion expansion occurs well into the chronic stage of stroke. For the first time, we present evidence that expansion is predictive of longitudinal changes in language performance in individuals with aphasia. Future research should focus on the potential mechanisms that may lead to necrosis in areas surrounding the chronic stroke lesion.

Story Recall in Peer Conflict Resolution Discourse Task to Identify Older Adults Testing Within Range of Cognitive Impairment.

PURPOSE: The current study used behavioral measures of discourse complexity and story recall accuracy in an expository discourse task to distinguish older adults testing within range of cognitive impairment according to a standardized cognitive screening tool in a sample of self-reported healthy older adults. METHOD: Seventy-three older adults who self-identified as healthy completed an expository discourse task and neuropsychological screener. Discourse data were used to classify participants testing within range of cognitive impairment using multiple machine learning algorithms and stability analysis for identifying reliably predictive features in an effort to maximize prediction accuracy. We hypothesized that a higher rate of pronoun use and lower scores on story recall would best classify older adults testing within range of cognitive impairment. RESULTS: The highest classification accuracy exploited a single variable in a remarkably intuitive way: using 66% story recall as a cutoff for cognitive impairment. Forcing this decision tree model to use more features or increasing its complexity did not improve accuracy. Permutation testing confirmed that the 77% accuracy and 0.18 Brier skill score achieved by the model were statistically significant (p < .00001). CONCLUSIONS: These results suggest that expository discourse tasks that place demands on executive functions, such as working memory, can be used to identify aging adults who test within range of cognitive impairment. Accurate representation of story elements in working memory is critical for coherent discourse. Our simple yet highly accurate predictive model of expository discourse provides a promising assessment for easy identification of cognitive impairment in older adults. SUPPLEMENTAL MATERIAL: https://doi.org/10.23641/asha.26543824.

Cerebellar Atrophy and Language Processing in Chronic Left-Hemisphere Stroke.

Chronic stroke results in significant downstream changes at connected cortical sites. However, less is known about the impact of cortical stroke on cerebellar structure. Here, we examined the relationship between chronic stroke, cerebellar volume, cerebellar symmetry, language impairment, and treatment trajectories in a large cohort (N = 249) of chronic left hemisphere (LH) stroke patients with aphasia, using a healthy aging cohort (N = 244) as control data. Cerebellar gray matter volume was significantly reduced in chronic LH stroke relative to healthy control brains. Within the chronic LH stroke group, we observed a robust relationship between cerebellar volume, lesion size, and days post-stroke. Notably, the extent of cerebellar atrophy in chronic LH patients, particularly in the contralesional (right) cerebellar gray matter, explained significant variability in post-stroke aphasia severity, as measured by the Western Aphasia Battery-Revised, above and beyond traditional considerations such as cortical lesion size, days post-stroke, and demographic measures (age, race, sex). In a subset of participants that took part in language treatment studies, greater cerebellar gray matter volume was associated with greater treatment gains. These data support the importance of considering both cerebellar volume and symmetry in models of post-stroke aphasia severity and recovery.

Age-Related Hearing Loss, Cognitive Decline, and Social Interaction: Testing a Framework.

PURPOSE: Aging increases risk for hearing loss, cognitive decline, and social isolation; however, the nature of their interconnection remains unclear. This study examined the interplay between age-related hearing loss, cognitive decline, and social isolation in adults by testing the ability to understand speech in background noise, a challenge frequently reported by many older adults. METHOD: We analyzed data collected from 128 adults (20-79 years of age, Mage = 51 years) recruited as part of the Aging Brain Cohort at the University of South Carolina repository. The participants underwent testing for hearing, cognition, and social interaction, which included pure-tone audiometry, a words-in-noise (WIN) test, a hearing questionnaire (Speech, Spatial and Qualities of Hearing Scale [SSQ12]), a social questionnaire (Patient-Reported Outcomes Measurement Information System-57 Social), and the Montreal Cognitive Assessment. We used a single pure-tone average (PTA) threshold value and a single WIN threshold value for each participant because there were no differences on average between the left and right ears. RESULTS: Poorer hearing was significantly associated with cognitive decline, through both PTA and WIN thresholds, with a stronger association observed for WIN threshold. Adults with poorer hearing also exhibited greater social isolation, as evidenced by their WIN threshold and SSQ12 score, although not through PTA. This connection was more pronounced with the WIN threshold than with the SSQ12 score. Cognition was not related to social isolation, suggesting that social isolation is affected more by the ability to understand words in noise than by cognition in a nondemented population. CONCLUSIONS: Understanding speech in challenging auditory environments rather than mere threshold detection is strongly linked to social isolation and cognitive decline. Thus, inclusion of a word-recognition-in-noise test and a social isolation survey in clinical settings is warranted. SUPPLEMENTAL MATERIAL: https://doi.org/10.23641/asha.26237060.

Long-range white matter fibres and post-stroke verbal and non-verbal cognition.

Among stroke survivors, linguistic and non-linguistic impairments exhibit substantial inter-individual variability. Stroke lesion volume and location do not sufficiently explain outcomes, and the neural mechanisms underlying the severity of aphasia or non-verbal cognitive deficits remain inadequately understood. Converging evidence supports the idea that white matter is particularly susceptible to ischaemic injury, and long-range fibres are commonly associated with verbal and non-verbal function. Here, we investigated the relationship among post-stroke aphasia severity, cognition, and white matter integrity. Eighty-seven individuals in the chronic stage of stroke underwent diffusion MRI and behavioural testing, including language and cognitive measures. We used whole-brain structural connectomes from each participant to calculate the ratio of long-range fibres to short-range fibres. We found that a higher proportion of long-range fibres was associated with lower aphasia severity, more accurate picture naming, and increased performance on non-verbal semantic memory/processing and non-verbal reasoning while controlling for lesion volume, key damage areas, age, and years post stroke. Our findings corroborate the hypothesis that, after accounting for age and lesion anatomy, inter-individual differences in post-stroke aphasia severity, verbal, and non-verbal cognitive outcomes are related to the preservation of long-range white matter fibres beyond the lesion.

Regional brain aging: premature aging of the domain general system predicts aphasia severity.

Premature brain aging is associated with poorer cognitive reserve and lower resilience to injury. When there are focal brain lesions, brain regions may age at different rates within the same individual. Therefore, we hypothesize that reduced gray matter volume within specific brain systems commonly associated with language recovery may be important for long-term aphasia severity. Here we show that individuals with stroke aphasia have a premature brain aging in intact regions of the lesioned hemisphere. In left domain-general regions, premature brain aging, gray matter volume, lesion volume and age were all significant predictors of aphasia severity. Increased brain age following a stroke is driven by the lesioned hemisphere. The relationship between brain age in left domain-general regions and aphasia severity suggests that degradation is possible to specific brain regions and isolated aging matters for behavior.

The stroke outcome optimization project: Acute ischemic strokes from a comprehensive stroke center.

Stroke is a leading cause of disability, and Magnetic Resonance Imaging (MRI) is routinely acquired for acute stroke management. Publicly sharing these datasets can aid in the development of machine learning algorithms, particularly for lesion identification, brain health quantification, and prognosis. These algorithms thrive on large amounts of information, but require diverse datasets to avoid overfitting to specific populations or acquisitions. While there are many large public MRI datasets, few of these include acute stroke. We describe clinical MRI using diffusion-weighted, fluid-attenuated and T1-weighted modalities for 1715 individuals admitted in the upstate of South Carolina, of whom 1461 have acute ischemic stroke. Demographic and impairment data are provided for 1106 of the stroke survivors from this cohort. Our validation demonstrates that machine learning can leverage the imaging data to predict stroke severity as measured by the NIH Stroke Scale/Score (NIHSS). We share not only the raw data, but also the scripts for replicating our findings. These tools can aid in education, and provide a benchmark for validating improved methods.

Identifying a group of factors predicting cognitive impairment among older adults.

BACKGROUND: Cognitive impairment has multiple risk factors spanning several domains, but few studies have evaluated risk factor clusters. We aimed to identify naturally occurring clusters of risk factors of poor cognition among middle-aged and older adults and evaluate associations between measures of cognition and these risk factor clusters. METHODS: We used data from the National Health and Nutrition Examination Survey (NHANES) III (training dataset, n = 4074) and the NHANES 2011-2014 (validation dataset, n = 2510). Risk factors were selected based on the literature. We used both traditional logistic models and support vector machine methods to construct a composite score of risk factor clusters. We evaluated associations between the risk score and cognitive performance using the logistic model by estimating odds ratios (OR) and 95% confidence intervals (CI). RESULTS: Using the training dataset, we developed a composite risk score that predicted undiagnosed cognitive decline based on ten selected predictive risk factors including age, waist circumference, healthy eating index, race, education, income, physical activity, diabetes, hypercholesterolemia, and annual visit to dentist. The risk score was significantly associated with poor cognitive performance both in the training dataset (OR Tertile 3 verse tertile 1 = 8.15, 95% CI: 5.36-12.4) and validation dataset (OR Tertile 3 verse tertile 1 = 4.31, 95% CI: 2.62-7.08). The area under the receiver operating characteristics curve for the predictive model was 0.74 and 0.77 for crude model and model adjusted for age, sex, and race. CONCLUSION: The model based on selected risk factors may be used to identify high risk individuals with cognitive impairment.

Functional correlates of increasing gestural articulatory fluency using a miniature second-language approach.

OBJECTIVES: Gesture-based second languages have become an important tool in the rehabilitation of language-impaired subpopulations. Acquiring the ability to use manual gestures as a means to construct meaningful utterances places unique demands on the brain. This study identified changes in the blood oxygen level-dependent (BOLD) signal associated with the development of gestural fluency using a miniature second-language-based approach. PARTICIPANTS AND METHODS: Twelve healthy right-handed adults (19-31 years) were trained to produce sequences of meaningful gestures over a period of 2 weeks. Functional magnetic resonance imaging was used to identify brain regions involved in actual and imagined production of meaningful sentences both before (nonfluent production) and after (fluent production) practice. RESULTS: Brain areas showing learning-dependent increases in activity associated with the development of fluency included sites associated with language articulation, while learning-related decreases in the BOLD signal were observed in cortical networks associated with motor imagery, and native language processing. CONCLUSION: These findings provide novel insights regarding the neural basis of fluency that could inform the design of interventions for treating speech disorders characterized by the loss of fluency.

Distinct brain morphometry patterns revealed by deep learning improve prediction of aphasia severity.

Emerging evidence suggests that post-stroke aphasia severity depends on the integrity of the brain beyond the stroke lesion. While measures of lesion anatomy and brain integrity combine synergistically to explain aphasic symptoms, significant interindividual variability remains unaccounted for. A possible explanatory factor may be the spatial distribution of brain atrophy beyond the lesion. This includes not just the specific brain areas showing atrophy, but also distinct three-dimensional patterns of atrophy. Here, we tested whether deep learning with Convolutional Neural Networks (CNN) on whole brain morphometry (i.e., segmented tissue volumes) and lesion anatomy can better predict which individuals with chronic stroke (N=231) have severe aphasia, and whether encoding spatial dependencies in the data might be capable of improving predictions by identifying unique individualized spatial patterns. We observed that CNN achieves significantly higher accuracy and F1 scores than Support Vector Machine (SVM), even when the SVM is nonlinear or integrates linear and nonlinear dimensionality reduction techniques. Performance parity was only achieved when the SVM was directly trained on the latent features learned by the CNN. Saliency maps demonstrated that the CNN leveraged widely distributed patterns of brain atrophy predictive of aphasia severity, whereas the SVM focused almost exclusively on the area around the lesion. Ensemble clustering of CNN saliency maps revealed distinct morphometry patterns that were unrelated to lesion size, highly consistent across individuals, and implicated unique brain networks associated with different cognitive processes as measured by the wider neuroimaging literature. Individualized predictions of severity depended on both ipsilateral and contralateral features outside of the location of stroke. Our findings illustrate that three-dimensional network distributions of atrophy in individuals with aphasia are directly associated with aphasia severity, underscoring the potential for deep learning to improve prognostication of behavioral outcomes from neuroimaging data, and highlighting the prospective benefits of interrogating spatial dependence at different scales in multivariate feature space.