Heterogeneity of comprehensive clinical phenotype and longitudinal adaptive function and correlation with computational predictions of severity of missense genotypes in KIF1A-associated neurological disorder.

PURPOSE: Pathogenic variants in kinesin family member 1A (KIF1A) are associated with KIF1A-associated neurological disorder. We report the clinical phenotypes and correlate genotypes of individuals with KIF1A-associated neurological disorder. METHODS: Medical history and adaptive function were assessed longitudinally. In-person evaluations included neurological, motor, ophthalmologic, and cognitive assessments. RESULTS: We collected online data on 177 individuals. Fifty-seven individuals were also assessed in-person. Most individuals had de novo heterozygous missense likely pathogenic/pathogenic KIF1A variants. The most common characteristics were hypotonia, spasticity, ataxia, seizures, optic nerve atrophy, cerebellar atrophy, and cognitive impairment. Mean Vineland adaptive behavior composite score (VABS-ABC) was low (M = 62.9, SD = 19.1). The mean change in VABS-ABC over time was -3.1 (SD = 7.3). The decline in VABS-ABC was associated with the age at first assessment and abnormal electroencephalogram/seizure. There was a positive correlation between evolutionary scale model (ESM) score for the variants and final VABS-ABC (P = .003). Abnormal electroencephalogram/seizure, neuroimaging result, and ESM explain 34% of the variance in final VABS-ABC (P < .001). CONCLUSION: In-person assessment confirmed caregiver report and identified additional visual deficits. Adaptive function declined over time consistent with both the neurodevelopmental and neurodegenerative nature of the condition. Using ESM score assists in predicting phenotype across a wide range of unique variants.

Interaction of interictal epileptiform activity with sleep spindles is associated with cognitive deficits and adverse surgical outcome in pediatric focal epilepsy.

OBJECTIVE: Temporal coordination between oscillations enables intercortical communication and is implicated in cognition. Focal epileptic activity can affect distributed neural networks and interfere with these interactions. Refractory pediatric epilepsies are often accompanied by substantial cognitive comorbidity, but mechanisms and predictors remain mostly unknown. Here, we investigate oscillatory coupling across large-scale networks in the developing brain. METHODS: We analyzed large-scale intracranial electroencephalographic recordings in children with medically refractory epilepsy undergoing presurgical workup (n = 25, aged 3-21 years). Interictal epileptiform discharges (IEDs), pathologic high-frequency oscillations (HFOs), and sleep spindles were detected. Spatiotemporal metrics of oscillatory coupling were determined and correlated with age, cognitive function, and postsurgical outcome. RESULTS: Children with epilepsy demonstrated significant temporal coupling of both IEDs and HFOs to sleep spindles in discrete brain regions. HFOs were associated with stronger coupling patterns than IEDs. These interactions involved tissue beyond the clinically identified epileptogenic zone and were ubiquitous across cortical regions. Increased spatial extent of coupling was most prominent in older children. Poor neurocognitive function was significantly correlated with high IED-spindle coupling strength and spatial extent; children with strong pathologic interactions additionally had decreased likelihood of postoperative seizure freedom. SIGNIFICANCE: Our findings identify pathologic large-scale oscillatory coupling patterns in the immature brain. These results suggest that such intercortical interactions could predict risk for adverse neurocognitive and surgical outcomes, with the potential to serve as novel therapeutic targets to restore physiologic development.

Access for ALL in ALS: A large-scale, inclusive, collaborative consortium to unlock the molecular and genetic mechanisms of amyotrophic lateral sclerosis.

Recent progress in therapeutics for amyotrophic lateral sclerosis (ALS) has spurred development and imbued the field of ALS with hope for more breakthroughs, yet substantial scientific gaps persist. This unmet need remains a stark reminder that innovative paradigms are needed to invigorate ALS research. To move toward more informative, targeted, and personalized drug development, the National Institutes of Health (NIH) established a national ALS clinical research consortium called Access for ALL in ALS (ALL ALS). This new consortium is a multi-institutional effort that aims to organize the ALS clinical research landscape in the United States. ALL ALS is operating in partnership with several stakeholders to operationalize the recommendations of the Accelerating Access to Critical Therapies for ALS Act (ACT for ALS) Public Private Partnership. ALL ALS will provide a large-scale, centralized, and readily accessible infrastructure for the collection and storage of a wide range of data from people living with ALS (symptomatic cohort) or who may be at risk of developing ALS (asymptomatic ALS gene carriers). Importantly, ALL ALS is designed to encourage community engagement, equity, and inclusion. The consortium is prioritizing the enrollment of geographically, ethnoculturally, and socioeconomically diverse participants. Collected data include longitudinal clinical data and biofluids, genomic, and digital biomarkers that will be harmonized and linked to the central Accelerating Medicines Partnership for ALS (AMP ALS) portal for sharing with the research community. The aim of ALL ALS is to deliver a comprehensive, inclusive, open-science dataset to help researchers answer important scientific questions of clinical relevance in ALS.

Convolutional neural network-aided tuber segmentation in tuberous sclerosis complex patients correlates with electroencephalogram.

OBJECTIVE: One of the clinical hallmarks of tuberous sclerosis complex (TSC) is radiologically identified cortical tubers, which are present in most patients. Intractable epilepsy may require surgery, often involving invasive diagnostic procedures such as intracranial electroencephalography (EEG). Identifying the location of the dominant tuber responsible for generating epileptic activities is a critical issue. However, the link between cortical tubers and epileptogenesis is poorly understood. Given this, we hypothesized that tuber voxel intensity may be an indicator of the dominant epileptogenic tuber. Also, via tuber segmentation based on deep learning, we explored whether an automatic quantification of the tuber burden is feasible. METHODS: We annotated tubers from structural magnetic resonance images across 29 TSC subjects, summarized tuber statistics in eight brain lobes, and determined suspected epileptogenic lobes from the same group using EEG monitoring data. Then, logistic regression analyses were performed to demonstrate the linkage between the statistics of cortical tuber and the epileptogenic zones. Furthermore, we tested the ability of a neural network to identify and quantify tuber burden. RESULTS: Logistic regression analyses showed that the volume and count of tubers per lobe, not the mean or variance of tuber voxel intensity, were positively correlated with electrophysiological data. In 47.6% of subjects, the lobe with the largest tuber volume concurred with the epileptic brain activity. A neural network model on the test dataset showed a sensitivity of .83 for localizing individual tubers. The predicted masks from the model correlated highly with the neurologist labels, and thus may be a useful tool for determining tuber burden and searching for the epileptogenic zone. SIGNIFICANCE: We have proven the feasibility of an automatic segmentation of tubers and a derivation of tuber burden across brain lobes. Our method may provide crucial insights regarding the treatment and outcome of TSC patients.

Depression Is Associated With Preserved Cortical Thickness Relative to Apathy in Frontotemporal Dementia.

OBJECTIVES: To understand the differential neuroanatomical substrates underlying apathy and depression in Frontotemporal dementia (FTD). METHODS: T1-MRIs and clinical data of patients with behavioral and aphasic variants of FTD were obtained from an open database. Cortical thickness was derived, its association with apathy severity and difference between the depressed and not depressed were examined with appropriate covariates. RESULTS: Apathy severity was significantly associated with cortical thinning of the lateral parts of the right sided frontal, temporal and parietal lobes. The right sided orbitofrontal, parsorbitalis and rostral anterior cingulate cortex were thicker in depressed compared to patients not depressed. CONCLUSIONS: Greater thickness of right sided ventromedial and inferior frontal cortex in depression compared to patients without depression suggests a possible requisite of gray matter in this particular area for the manifestation of depression in FTD. This study demonstrates a method for deriving neuroanatomical patterns across non-harmonized neuroimaging data in a neurodegenerative disease.

Rasmussen Encephalitis: An Update.

Rasmussen encephalitis (RE) is a rare, devastating, progressive pediatric epilepsy. First described 60 years ago, RE continues to present challenges in diagnosis and management. RE causes a unilateral focal epilepsy in children that typically becomes medically refractory, results in significant hemiparesis, and causes progressive cognitive decline. The etiology is a cell-mediated immune attack on one cerebral hemisphere, though the inciting antigen remains unknown. While the underlying histopathology is unilateral and RE is described as "unihemispheric," studies have demonstrated (1) atrophy of the unaffected hemisphere, (2) electroencephalographic abnormalities (slowing and spikes) in the unaffected hemisphere, and (3) cognitive decline referable to the unaffected hemisphere. These secondary contralateral effects likely reflect the impact of uncontrolled epileptic activity (i.e., epileptic encephalopathy). Hemispheric disconnection (HD) renders 70 to 80% of patients seizure free. While it has the potential to limit the influence of seizures and abnormal electrical activity emanating from the pathological hemisphere, HD entails hemiparesis and hemianopia, as well as aphasia for patients with dominant HD. With the recent expansion of available immunomodulatory therapies, there has been interest in identifying an alternative to HD, though evidence for disease modification is limited to date. We review what is known and what remains unknown about RE.

Education modulates the impact of white matter lesions on the risk of mild cognitive impairment and dementia.

OBJECTIVES: Conflicting results have been reported regarding the association between white matter lesions (WML) and cognitive impairment. We hypothesized that education, a marker of cognitive reserve (CR), could modulate the effects of WML on the risk of mild cognitive impairment (MCI) or dementia. METHODS: We followed 500 healthy subjects from a cohort of community-dwelling persons aged 65 years and over (ESPRIT Project). At baseline, WML volume was measured using a semi-automatic method on T2-weighted MRI. Standardized cognitive and neurological evaluations were repeated after 2, 4, and 7 years. The sample was dichotomized according to education level into low (≤8 years) and high (>8 years) education groups. Cox proportional hazard models were constructed to study the association between WML and risk of MCI/dementia. RESULTS: The interaction between education level and WML volume reached significance (p = 0.017). After adjustment for potential confounders, the association between severe WML and increased MCI/dementia risk was significant in the low education group (≤8 years) (p = 0.02, hazard ratio [HR]: 3.77 [1.29-10.99]), but not in the high education group (>8 years) (p = 0.82, HR: 1.07 [0.61-1.87]). CONCLUSIONS: Severe WML significantly increases the risk of developing MCI/dementia over a 7-year period in low educated participants. Subjects with higher education levels were seen to be more likely to be resilient to the deleterious effects of severe WML. The CR hypothesis suggests several avenues for dementia prevention.

APOE ε4 and risk for Alzheimer's disease: do regionally distributed white matter hyperintensities play a role?

BACKGROUND: We previously demonstrated that parietal lobe white matter hyperintensities (WMH) increase the risk for Alzheimer's disease (AD). Here, we examined whether individuals with apolipoprotein E gene (APOE ε4) have increased parietal WMH volume. METHODS: Participants were from the Washington Heights-Inwood Columbia Aging Project (WHICAP; n = 694, 47 with dementia) in northern Manhattan and the Etude Santé Psychologique Prévalence Risques et Traitement study (ESPRIT; n = 539, 8 with dementia) in Montpellier. The association between regional WMH and APOE ε4 was examined separately in each group and then in a combined analysis. RESULTS: In WHICAP, ε4 carriers had higher WMH volume particularly in parietal and occipital lobes. In ESPRIT, ε4 carriers had elevated WMH particularly in parietal and temporal lobes. In the combined analysis, ε4 carriers had higher WMH in parietal and occipital lobes. Increased WMH volume was associated with increased frequency of dementia irrespective of APOE ε4 status; those with the ε4 were more likely to have dementia if they also had increased parietal WMH. CONCLUSIONS: APOE ε4 is associated with increased parietal lobe WMH.

Increased parietal and occipital lobe gyrification predicts conversion to syndromal psychosis in a clinical high-risk cohort.

BACKGROUND: Local gyrification index (lGI), indicative of the degree of cortical folding is a proxy marker for early cortical neurodevelopmental abnormalities. We studied the difference in lGI between those who do and do not convert to psychosis (non-converters) in a clinical high-risk (CHR) cohort, and whether lGI predicts conversion to psychosis. METHODS: Seventy-two CHR participants with attenuated positive symptom syndrome were followed up for two years. The difference in baseline whole-brain lGI was examined on the T1-weighted MRIs between, i)CHR (N = 72) and healthy controls (N = 19), ii)Converters to psychosis (N = 24) and non-converters (N = 48), adjusting for age and sex, on Freesurfer-6.0. The significant cluster obtained in the converters versus non-converters comparison was registered as a region of interest to individual images of all 72 participants and lGI values were extracted from this region. A cox proportional hazards model was applied with these values to study whether lGI predicts conversion to psychosis. RESULTS: lGI was not different between CHR and healthy controls. lGI was increased in converters in the right-sided inferior parietal and lateral occipital areas (corrected cluster-wise-p-value = 0.009, cohen's f = 0.42) compared to non-converters, which significantly increased the risk of onset of psychosis (p = 0.029, hazard ratio = 1.471). CONCLUSIONS: Increased gyrification in the right-sided inferior parietal and lateral occipital area differentiates converters to psychosis in CHR, significantly increasing the risk of conversion to psychosis. This measure may reflect underlying traits in parts of the brain that develop earliest in-utero (parietal and occipital), conferring a heightened vulnerability to convert to syndromal psychosis subsequently.

White matter predictors of cognitive functioning in older adults.

Few studies have applied multiple imaging modalities to examine cognitive correlates of white matter. We examined the utility of T2-weighted magnetic resonance imaging (MRI) -derived white matter hyperintensities (WMH) and diffusion tensor imaging-derived fractional anisotropy (FA) to predict cognitive functioning among older adults. Quantitative MRI and neuropsychological evaluations were performed in 112 older participants from an ongoing study of the genetics of Alzheimer's disease (AD) in African Americans. Regional WMH volumes and FA were measured in multiple regions of interest. We examined the association of regional WMH and an FA summary score with cognitive test performance. Differences in WMH and FA were compared across diagnostic groups (i.e., normal controls, mild cognitive impairment, and probable AD). Increased WMH volume in frontal lobes was associated with poorer delayed memory performance. FA did not emerge as a significant predictor of cognition. White matter hyperintensity volume in the frontal and parietal lobes was increased in MCI participants and more so in AD patients relative to controls. These results highlight the importance of regionally distributed small vessel cerebrovascular disease in memory performance and AD among African American older adults. White matter microstructural changes, quantified with diffusion tensor imaging, appear to play a lesser role in our sample.

Metabolic syndrome and localization of white matter hyperintensities in the elderly population.

BACKGROUND: Metabolic syndrome (MetS) is defined as a clustering of metabolic disorders: abdominal obesity, dyslipidemia, hypertension, and hyperglycemia. Although specific components of MetS have been associated with white matter hyperintensities (WMH), less is known about the association between MetS as a whole and WMH, especially in normal aging. We aimed to: (1) investigate this association in a cohort of healthy elderly individuals, and (2) examine the relationship between MetS and the regional distribution of WMH, to further understanding of the relationship between MetS and structural brain changes. METHODS: Analyses were carried out on 308 participants (48.1% men, age: 71.0 ± 3.9 years) from the French longitudinal ESPRIT (Enquête de Santé Psychologique--Risques, Incidence et Traitement) study, who were free of cerebrovascular disease cognitive and functional impairment. Logistic regression models were used to examine the cross-sectional association between MetS (defined using the National Cholesterol Education Program-Adult Treatment Panel III criteria) and (1) WMH volumes, and (2) WMH volumes according to their localization in insulofrontal and temporoparietal regions. RESULTS: After adjusting for potential confounders, participants with MetS had a twofold increased chance of presenting with high levels of WMH volume compared with those without (odds ratio [OR] = 2.74, 95% confidence interval [CI]: 1.25-6.03). MetS was specifically associated with an increase of temporoparietal WMH volumes, but no association was found between MetS and WMH localized in the insulofrontal region. CONCLUSION: Our findings suggest that effective management of MetS may reduce WMH accumulation in brain areas already vulnerable to the aging process.

A deep learning MRI approach outperforms other biomarkers of prodromal Alzheimer's disease.

BACKGROUND: The three core pathologies of Alzheimer's disease (AD) are amyloid pathology, tau pathology, and neurodegeneration. Biomarkers exist for each. Neurodegeneration is often detected by neuroimaging, and we hypothesized that a voxel-based deep learning approach using structural MRI might outperform other neuroimaging methods. METHODS: First, we implement an MRI-based deep learning model, trained with a data augmentation strategy, which classifies Alzheimer's dementia and generates class activation maps. Next, we tested the model in prodromal AD and compared its performance to other biomarkers of amyloid pathology, tau pathology, and neuroimaging biomarkers of neurodegeneration. RESULTS: The model distinguished between controls and AD with high accuracy (AUROC = 0.973) with class activation maps that localized to the hippocampal formation. As hypothesized, the model also outperformed other neuroimaging biomarkers of neurodegeneration in prodromal AD (AUROC = 0.788) but also outperformed biomarkers of amyloid (CSF Aß = 0.702) or tau pathology (CSF tau = 0.682), and the findings are interpreted in the context of AD's known anatomical biology. CONCLUSIONS: The advantages of using deep learning to extract biomarker information from conventional MRIs extend practically, potentially reducing patient burden, risk, and cost.

Brain volumetric correlates of remotely versus in-person administered symbol digit modalities test in multiple sclerosis.

BACKGROUND: Prior studies in multiple sclerosis (MS) support reliability of telehealth-delivered cognitive batteries, although, to date, none have reported relationships of cognitive test performance to neural correlates across administration modalities. In this study we aimed to compare brain-behavior relationships, using the Symbol Digit Modalities Test (SDMT), the most reliable and sensitive cognitive measure in MS, measured from patients seen via telehealth versus in-person. METHODS: SDMT was administered to individuals with MS either in-person (N=60, mean age=39.7) or remotely via video conference (N=51, mean age=47.4). Magnetic resonance imaging (MRI) data was collected in 3-Tesla scanners. Using 3-dimensional T1 images cerebral, cortical, deep gray, cerebral white matter and thalamic nuclei volumes were calculated. Using a meta-analysis approach with an interaction term for participant group, individual regression models were run for each MRI measure having SDMT scores as the outcome variable in each model. In addition, the correlation and average difference between In-person and Remote group associations across the MRI measures were calculated. Finally, for each MRI variable I2 score was quantified to test the heterogeneity between the groups. RESULTS: Administration modality did not affect the association of SDMT performance with MRI measures. Brain tissue volumes showing high associations with the SDMT scores in one group also showed high associations in the other (r = 0.83; 95% CI = [0.07, 0.86]). The average difference between the In-person and the Remote group associations was not significant (ßRemote - ßIn-person = 0.14, 95% CI = [-0.04, 0.34]). Across MRI measures, the average I2 value was 14%, reflecting very little heterogeneity in the relationship of SDMT performance to brain volume. CONCLUSION: We found consistent relationships to neural correlates across in-person and remote SDMT administration modalities. Hence, our study extended the findings of the previous studies demonstrating the feasibility of remote administration of the SDMT.

Deep learning of MRI contrast enhancement for mapping cerebral blood volume from single-modal non-contrast scans of aging and Alzheimer's disease brains.

While MRI contrast agents such as those based on Gadolinium are needed for high-resolution mapping of brain metabolism, these contrast agents require intravenous administration, and there are rising concerns over their safety and invasiveness. Furthermore, non-contrast MRI scans are more commonly performed than those with contrast agents and are readily available for analysis in public databases such as the Alzheimer's Disease Neuroimaging Initiative (ADNI). In this article, we hypothesize that a deep learning model, trained using quantitative steady-state contrast-enhanced structural MRI datasets, in mice and humans, can generate contrast-equivalent information from a single non-contrast MRI scan. The model was first trained, optimized, and validated in mice, and was then transferred and adapted to humans. We observe that the model can substitute for Gadolinium-based contrast agents in approximating cerebral blood volume, a quantitative representation of brain activity, at sub-millimeter granularity. Furthermore, we validate the use of our deep-learned prediction maps to identify functional abnormalities in the aging brain using locally obtained MRI scans, and in the brain of patients with Alzheimer's disease using publicly available MRI scans from ADNI. Since it is derived from a commonly-acquired MRI protocol, this framework has the potential for broad clinical utility and can also be applied retrospectively to research scans across a host of neurological/functional diseases.

Quantitative approaches for assessment of white matter hyperintensities in elderly populations.

White matter hyperintensities (WMH) are areas of increased signal on T2-weighted magnetic resonance imaging (MRI), including fluid attenuated inverse recovery sequences. Total and regional WMH burden (i.e., volume or severity) has been associated with myriad cognitive, neurological, and psychiatric conditions among older adults. In the current report, we illustrate two approaches to quantify periventricular, deep, and total WMH and examine their reliability and criterion validity among 28 elderly patients enrolled in a depression treatment trial. The first approach, an operator-driven quantitative approach, involves visual inspection of individual MRI scans and manual labeling using a three-step series of procedures. The second approach, a fully automated quantitative approach, uses a processing stream that involves image segmentation, voxel intensity thresholding, and seed growing to label WMH and calculate their volume automatically. There was good agreement in WMH quantification between the two approaches (Cronbach's alpha values from 0.835 to 0.968). Further, severity of WMH was significantly associated with worse depression and increased age, and these associations did not differ significantly between the two quantification approaches. We provide evidence for good reliability and criterion validity for two approaches for WMH volume determination. The operator-driven approach may be better suited for smaller studies with highly trained raters, whereas the fully automated quantitative approach may be more appropriate for larger, high-throughput studies.

An exploratory magnetic resonance imaging study of suicidal ideation in individuals at clinical high-risk for psychosis.

Suicide is a major cause of death in psychosis and associated with significant morbidity. Suicidal ideation (SI) is very common in those at clinical high-risk for psychosis (CHR) and predicts later suicide. Despite substantial work on the pathobiology of suicide in schizophrenia, little is known of its neurobiological underpinnings in the CHR or putatively prodromal state. Therefore, in this pilot study, we examined the neurobiology of SI in CHR individuals using structural MRI. Subjects were aged 14-30 and met criteria for the Attenuated Positive Symptom Psychosis-Risk Syndrome (APSS) delineated in the Structured Interview for Psychosis-Risk Syndromes (SIPS). Suicidality was assessed using the Columbia Suicide Severity Rating Scale (C-SSRS). Volumetric MRI scans were obtained on a 3T Phillips scanner. MRI data were available for 69 individuals (19 CHR without SI, 31 CHR with SI and 19 healthy control subjects). CHR individuals with SI had thicker middle temporal and right insular cortices than CHR individuals without SI and healthy control subjects. The location of these findings is consistent with neurobiological findings regarding suicide in syndromal psychosis. These findings underscore the potential for the use of brain imaging biomarkers of suicide risk in CHR individuals.

Right parahippocampal volume deficit in an older population with posttraumatic stress disorder.

BACKGROUND: Posttraumatic Stress Disorder (PTSD) is an increasingly prevalent condition among older adults and may escalate further as the general population including veterans from recent conflicts grow older. Despite growing evidence of higher medical comorbidity, cognitive impairment and dementia, and disability in older individuals with PTSD, there are very few studies examining brain cortical structure in this population. Hence, we examined cortical volumes in a cross-sectional study of veterans and civilians aged ≥50 years, of both sexes and exposed to trauma (interpersonal, combat, non-interpersonal). METHODS: Cortical volumes were obtained from T1-weighted structural MRI and compared between individuals with PTSD and Trauma Exposed Healthy Controls (TEHC) adjusting for age, sex, estimated intracranial volume, depression severity, and time elapsed since trauma exposure. RESULTS: The PTSD group (N = 55) had smaller right parahippocampal gyrus compared to TEHC (N = 36), corrected p(pFWER) = 0.034, with an effect size of 0.75 (Cohen's d), with no significant group differences in other cortical areas. CONCLUSIONS: These findings are different from the structural brain findings reported in studies in younger age groups (larger parahippocampal volume in PTSD patients), suggesting a possible significant change in brain structure as PTSD patients age. These results need replication in longitudinal studies across the age-span to test whether they are neuroanatomical markers representing disease vulnerability, trauma resilience or pathological neurodegeneration associated with cognitive impairment and dementia.

Deep learning improves utility of tau PET in the study of Alzheimer's disease.

INTRODUCTION: Positron emission tomography (PET) imaging targeting neurofibrillary tau tangles is increasingly used in the study of Alzheimer's disease (AD), but its utility may be limited by conventional quantitative or qualitative evaluation techniques in earlier disease states. Convolutional neural networks (CNNs) are effective in learning spatial patterns for image classification. METHODS: 18F-MK6240 (n = 320) and AV-1451 (n = 446) PET images were pooled from multiple studies. We performed iterations with differing permutations of radioligands, heuristics, and architectures. Performance was compared to a standard region of interest (ROI)-based approach on prediction of memory impairment. We visualized attention of the network to illustrate decision making. RESULTS: Overall, models had high accuracy (> 80%) with good average sensitivity and specificity (75% and 82%, respectively), and had comparable or higher accuracy to the ROI standard. Visualizations of model attention highlight known characteristics of tau radioligand binding. DISCUSSION: CNNs could improve tau PET's role in early disease and extend the utility of tau PET across generations of radioligands.

The role of stereo-electroencephalography to localize the epileptogenic zone in children with nonlesional brain magnetic resonance imaging.

OBJECTIVE: This study aimed to assess the clinical outcome and outcome predictive factors in pediatric epilepsy patients evaluated with stereo-electroencephalography (SEEG). METHODS: Thirty-eight patients who underwent SEEG implantation at the Pediatric Epilepsy Center in New York Presbyterian Hospital between June 2014 and December 2019 were enrolled for retrospective chart review. Postoperative seizure outcomes were evaluated in patients with at least 12-months follow up. Meta-analysis was conducted via electronic literature search of data reported from 2000 to 2020 to evaluate significant surgical outcome predictors for SEEG evaluation in the pediatric population. RESULTS: In the current case series of 25 postsurgical patients with long-term follow up, 16 patients (64.0%) were seizure free. An additional 7 patients (28.0%) showed significant seizure improvement and 2 patients (8.0%) showed no change in seizure activity. Patients with nonlesional magnetic resonance imaging (MRI) achieved seizure freedom in 50% (5/10) of cases. By comparison, 73% (11/15) of patients with lesional MRI achieved seizure freedom. Out of 12 studies, 158 pediatric patients were identified for inclusion in a meta-analysis of the effectiveness of SEEG. Seizure freedom was reported 54.4% (n = 86/158) of patients at last follow up. Among patients with nonlesional MRI, 45% (n = 24) achieved seizure freedom compared with patients with lesional MRI findings (61.2%, n:= 60) (p = 0.02). The risk for seizure recurrence was 2.15 times higher [95% confidence interval [CI] 1.06-4.37, p = 0.033] in patients diagnosed with nonlesional focal epilepsy compared to those with lesional epilepsy [ 1.49 (95% CI 1.06-2.114, p = 0.021]. CONCLUSION: Evaluation by SEEG implantation in pediatric epilepsy is effective in localizing the epileptogenic zone with favorable outcome. Presence of a non-lesional brain MRI was associated with lower chances of seizure freedom. Further research is warranted to improve the efficacy of SEEG in localizing the epileptogenic zone in pediatric patients with non-lesional brain MRI.

Estimating brain age based on a uniform healthy population with deep learning and structural magnetic resonance imaging.

Numerous studies have established that estimated brain age constitutes a valuable biomarker that is predictive of cognitive decline and various neurological diseases. In this work, we curate a large-scale brain MRI data set of healthy individuals, on which we train a uniform deep learning model for brain age estimation. We demonstrate an age estimation accuracy on a hold-out test set (mean absolute error = 4.06 years, r = 0.970) and an independent life span evaluation data set (mean absolute error = 4.21 years, r = 0.960). We further demonstrate the utility of the estimated age in a life span aging analysis of cognitive functions. In summary, we achieve age estimation performance comparable to previous studies, but with a more heterogenous data set confirming the efficacy of this deep learning framework. We also evaluated training with varying age distributions. The analysis of regional contributions to our brain age predictions through multiple analyses, and confirmation of the association of divergence between the estimated and chronological brain age with neuropsychological measures, may be useful in the development and evaluation of similar imaging biomarkers.