Pulmonary Hypertension and Anastrozole (PHANTOM): A Randomized, Double-Blind, Placebo-Controlled Trial.

RATIONALE: Inhibition of aromatase with anastrozole reduces pulmonary hypertension in experimental models. OBJECTIVES: We aimed to determine whether anastrozole improved six-minute walk distance (6MWD) at six months in pulmonary arterial hypertension (PAH). METHODS: We performed a randomized, double-blind, placebo-controlled Phase II clinical trial of anastrozole in subjects with PAH at seven centers. Eighty-four post-menopausal women and men with PAH were randomized in a 1:1 ratio to receive anastrozole 1 mg or placebo by mouth daily, stratified by sex using permuted blocks of variable sizes. All subjects and study staff were masked. The primary outcome was the change from baseline in 6MWD at six months. Using intent-to-treat analysis, we estimated the treatment effect of anastrozole using linear regression models adjusted for sex and baseline 6MWD. Assuming 10% loss to follow-up, we anticipated having 80% power to detect a difference in the change in 6MWD of 22 meters. MEASUREMENTS AND MAIN RESULTS: Forty-one subjects were randomized to placebo and 43 to anastrozole and all received the allocated treatment. Three subjects in the placebo group and two in the anastrozole group discontinued study drug. There was no significant difference in the change in 6MWD at six months (placebo-corrected treatment effect -7.9 m, 95%CI -32.7 - 16.9, p = 0.53). There was no difference in adverse events between the groups. CONCLUSIONS: Anastrozole did not show a significant effect on 6MWD compared to placebo in post-menopausal women and men with PAH. Anastrozole was safe and did not show adverse effects. Clinical trial registration available at www. CLINICALTRIALS: gov, ID: NCT03229499.

A practical evaluation of measures derived from compressed sensing diffusion spectrum imaging.

Diffusion Spectrum Imaging (DSI) using dense Cartesian sampling of q-space has been shown to provide important advantages for modeling complex white matter architecture. However, its adoption has been limited by the lengthy acquisition time required. Sparser sampling of q-space combined with compressed sensing (CS) reconstruction techniques has been proposed as a way to reduce the scan time of DSI acquisitions. However prior studies have mainly evaluated CS-DSI in post-mortem or non-human data. At present, the capacity for CS-DSI to provide accurate and reliable measures of white matter anatomy and microstructure in the living human brain remains unclear. We evaluated the accuracy and inter-scan reliability of 6 different CS-DSI schemes that provided up to 80% reductions in scan time compared to a full DSI scheme. We capitalized on a dataset of 26 participants who were scanned over eight independent sessions using a full DSI scheme. From this full DSI scheme, we subsampled images to create a range of CS-DSI images. This allowed us to compare the accuracy and inter-scan reliability of derived measures of white matter structure (bundle segmentation, voxel-wise scalar maps) produced by the CS-DSI and the full DSI schemes. We found that CS-DSI estimates of both bundle segmentations and voxel-wise scalars were nearly as accurate and reliable as those generated by the full DSI scheme. Moreover, we found that the accuracy and reliability of CS-DSI was higher in white matter bundles that were more reliably segmented by the full DSI scheme. As a final step, we replicated the accuracy of CS-DSI in a prospectively acquired dataset (n = 20, scanned once). Together, these results illustrate the utility of CS-DSI for reliably delineating in vivo white matter architecture in a fraction of the scan time, underscoring its promise for both clinical and research applications.

Similarity-based multimodal regression.

To better understand complex human phenotypes, large-scale studies have increasingly collected multiple data modalities across domains such as imaging, mobile health, and physical activity. The properties of each data type often differ substantially and require either separate analyses or extensive processing to obtain comparable features for a combined analysis. Multimodal data fusion enables certain analyses on matrix-valued and vector-valued data, but it generally cannot integrate modalities of different dimensions and data structures. For a single data modality, multivariate distance matrix regression provides a distance-based framework for regression accommodating a wide range of data types. However, no distance-based method exists to handle multiple complementary types of data. We propose a novel distance-based regression model, which we refer to as Similarity-based Multimodal Regression (SiMMR), that enables simultaneous regression of multiple modalities through their distance profiles. We demonstrate through simulation, imaging studies, and longitudinal mobile health analyses that our proposed method can detect associations between clinical variables and multimodal data of differing properties and dimensionalities, even with modest sample sizes. We perform experiments to evaluate several different test statistics and provide recommendations for applying our method across a broad range of scenarios.

Psychosis brain subtypes validated in first-episode cohorts and related to illness remission: results from the PHENOM consortium.

Using machine learning, we recently decomposed the neuroanatomical heterogeneity of established schizophrenia to discover two volumetric subgroups-a 'lower brain volume' subgroup (SG1) and an 'higher striatal volume' subgroup (SG2) with otherwise normal brain structure. In this study, we investigated whether the MRI signatures of these subgroups were also already present at the time of the first-episode of psychosis (FEP) and whether they were related to clinical presentation and clinical remission over 1-, 3-, and 5-years. We included 572 FEP and 424 healthy controls (HC) from 4 sites (Sao Paulo, Santander, London, Melbourne) of the PHENOM consortium. Our prior MRI subgrouping models (671 participants; USA, Germany, and China) were applied to both FEP and HC. Participants were assigned into 1 of 4 categories: subgroup 1 (SG1), subgroup 2 (SG2), no subgroup membership ('None'), and mixed SG1 + SG2 subgroups ('Mixed'). Voxel-wise analyses characterized SG1 and SG2 subgroups. Supervised machine learning analyses characterized baseline and remission signatures related to SG1 and SG2 membership. The two dominant patterns of 'lower brain volume' in SG1 and 'higher striatal volume' (with otherwise normal neuromorphology) in SG2 were identified already at the first episode of psychosis. SG1 had a significantly higher proportion of FEP (32%) vs. HC (19%) than SG2 (FEP, 21%; HC, 23%). Clinical multivariate signatures separated the SG1 and SG2 subgroups (balanced accuracy = 64%; p < 0.0001), with SG2 showing higher education but also greater positive psychosis symptoms at first presentation, and an association with symptom remission at 1-year, 5-year, and when timepoints were combined. Neuromorphological subtypes of schizophrenia are already evident at illness onset, separated by distinct clinical presentations, and differentially associated with subsequent remission. These results suggest that the subgroups may be underlying risk phenotypes that could be targeted in future treatment trials and are critical to consider when interpreting neuroimaging literature.

Proteomic cardiovascular risk assessment in chronic kidney disease.

AIMS: Chronic kidney disease (CKD) is widely prevalent and independently increases cardiovascular risk. Cardiovascular risk prediction tools derived in the general population perform poorly in CKD. Through large-scale proteomics discovery, this study aimed to create more accurate cardiovascular risk models. METHODS AND RESULTS: Elastic net regression was used to derive a proteomic risk model for incident cardiovascular risk in 2182 participants from the Chronic Renal Insufficiency Cohort. The model was then validated in 485 participants from the Atherosclerosis Risk in Communities cohort. All participants had CKD and no history of cardiovascular disease at study baseline when ∼5000 proteins were measured. The proteomic risk model, which consisted of 32 proteins, was superior to both the 2013 ACC/AHA Pooled Cohort Equation and a modified Pooled Cohort Equation that included estimated glomerular filtrate rate. The Chronic Renal Insufficiency Cohort internal validation set demonstrated annualized receiver operating characteristic area under the curve values from 1 to 10 years ranging between 0.84 and 0.89 for the protein and 0.70 and 0.73 for the clinical models. Similar findings were observed in the Atherosclerosis Risk in Communities validation cohort. For nearly half of the individual proteins independently associated with cardiovascular risk, Mendelian randomization suggested a causal link to cardiovascular events or risk factors. Pathway analyses revealed enrichment of proteins involved in immunologic function, vascular and neuronal development, and hepatic fibrosis. CONCLUSION: In two sizeable populations with CKD, a proteomic risk model for incident cardiovascular disease surpassed clinical risk models recommended in clinical practice, even after including estimated glomerular filtration rate. New biological insights may prioritize the development of therapeutic strategies for cardiovascular risk reduction in the CKD population.

Image harmonization: A review of statistical and deep learning methods for removing batch effects and evaluation metrics for effective harmonization.

Magnetic resonance imaging and computed tomography from multiple batches (e.g. sites, scanners, datasets, etc.) are increasingly used alongside complex downstream analyses to obtain new insights into the human brain. However, significant confounding due to batch-related technical variation, called batch effects, is present in this data; direct application of downstream analyses to the data may lead to biased results. Image harmonization methods seek to remove these batch effects and enable increased generalizability and reproducibility of downstream results. In this review, we describe and categorize current approaches in statistical and deep learning harmonization methods. We also describe current evaluation metrics used to assess harmonization methods and provide a standardized framework to evaluate newly-proposed methods for effective harmonization and preservation of biological information. Finally, we provide recommendations to end-users to advocate for more effective use of current methods and to methodologists to direct future efforts and accelerate development of the field.

Multiscale functional connectivity patterns of the aging brain learned from harmonized rsfMRI data of the multi-cohort iSTAGING study.

To learn multiscale functional connectivity patterns of the aging brain, we built a brain age prediction model of functional connectivity measures at seven scales on a large fMRI dataset, consisting of resting-state fMRI scans of 4186 individuals with a wide age range (22 to 97 years, with an average of 63) from five cohorts. We computed multiscale functional connectivity measures of individual subjects using a personalized functional network computational method, harmonized the functional connectivity measures of subjects from multiple datasets in order to build a functional brain age model, and finally evaluated how functional brain age gap correlated with cognitive measures of individual subjects. Our study has revealed that functional connectivity measures at multiple scales were more informative than those at any single scale for the brain age prediction, the data harmonization significantly improved the brain age prediction performance, and the data harmonization in the functional connectivity measures' tangent space worked better than in their original space. Moreover, brain age gap scores of individual subjects derived from the brain age prediction model were significantly correlated with clinical and cognitive measures. Overall, these results demonstrated that multiscale functional connectivity patterns learned from a large-scale multi-site rsfMRI dataset were informative for characterizing the aging brain and the derived brain age gap was associated with cognitive and clinical measures.

AI-based dimensional neuroimaging system for characterizing heterogeneity in brain structure and function in major depressive disorder: COORDINATE-MDD consortium design and rationale.

BACKGROUND: Efforts to develop neuroimaging-based biomarkers in major depressive disorder (MDD), at the individual level, have been limited to date. As diagnostic criteria are currently symptom-based, MDD is conceptualized as a disorder rather than a disease with a known etiology; further, neural measures are often confounded by medication status and heterogeneous symptom states. METHODS: We describe a consortium to quantify neuroanatomical and neurofunctional heterogeneity via the dimensions of novel multivariate coordinate system (COORDINATE-MDD). Utilizing imaging harmonization and machine learning methods in a large cohort of medication-free, deeply phenotyped MDD participants, patterns of brain alteration are defined in replicable and neurobiologically-based dimensions and offer the potential to predict treatment response at the individual level. International datasets are being shared from multi-ethnic community populations, first episode and recurrent MDD, which are medication-free, in a current depressive episode with prospective longitudinal treatment outcomes and in remission. Neuroimaging data consist of de-identified, individual, structural MRI and resting-state functional MRI with additional positron emission tomography (PET) data at specific sites. State-of-the-art analytic methods include automated image processing for extraction of anatomical and functional imaging variables, statistical harmonization of imaging variables to account for site and scanner variations, and semi-supervised machine learning methods that identify dominant patterns associated with MDD from neural structure and function in healthy participants. RESULTS: We are applying an iterative process by defining the neural dimensions that characterise deeply phenotyped samples and then testing the dimensions in novel samples to assess specificity and reliability. Crucially, we aim to use machine learning methods to identify novel predictors of treatment response based on prospective longitudinal treatment outcome data, and we can externally validate the dimensions in fully independent sites. CONCLUSION: We describe the consortium, imaging protocols and analytics using preliminary results. Our findings thus far demonstrate how datasets across many sites can be harmonized and constructively pooled to enable execution of this large-scale project.

Privacy-preserving harmonization via distributed ComBat.

Challenges in clinical data sharing and the need to protect data privacy have led to the development and popularization of methods that do not require directly transferring patient data. In neuroimaging, integration of data across multiple institutions also introduces unwanted biases driven by scanner differences. These scanner effects have been shown by several research groups to severely affect downstream analyses. To facilitate the need of removing scanner effects in a distributed data setting, we introduce distributed ComBat, an adaptation of a popular harmonization method for multivariate data that borrows information across features. We present our fast and simple distributed algorithm and show that it yields equivalent results using data from the Alzheimer's Disease Neuroimaging Initiative. Our method enables harmonization while ensuring maximal privacy protection, thus facilitating a broad range of downstream analyses in functional and structural imaging studies.

Harmonizing functional connectivity reduces scanner effects in community detection.

Community detection on graphs constructed from functional magnetic resonance imaging (fMRI) data has led to important insights into brain functional organization. Large studies of brain community structure often include images acquired on multiple scanners across different studies. Differences in scanner can introduce variability into the downstream results, and these differences are often referred to as scanner effects. Such effects have been previously shown to significantly impact common network metrics. In this study, we identify scanner effects in data-driven community detection results and related network metrics. We assess a commonly employed harmonization method and propose new methodology for harmonizing functional connectivity that leverage existing knowledge about network structure as well as patterns of covariance in the data. Finally, we demonstrate that our new methods reduce scanner effects in community structure and network metrics. Our results highlight scanner effects in studies of brain functional organization and provide additional tools to address these unwanted effects. These findings and methods can be incorporated into future functional connectivity studies, potentially preventing spurious findings and improving reliability of results.

Mitigating site effects in covariance for machine learning in neuroimaging data.

To acquire larger samples for answering complex questions in neuroscience, researchers have increasingly turned to multi-site neuroimaging studies. However, these studies are hindered by differences in images acquired across multiple sites. These effects have been shown to bias comparison between sites, mask biologically meaningful associations, and even introduce spurious associations. To address this, the field has focused on harmonizing data by removing site-related effects in the mean and variance of measurements. Contemporaneously with the increase in popularity of multi-center imaging, the use of machine learning (ML) in neuroimaging has also become commonplace. These approaches have been shown to provide improved sensitivity, specificity, and power due to their modeling the joint relationship across measurements in the brain. In this work, we demonstrate that methods for removing site effects in mean and variance may not be sufficient for ML. This stems from the fact that such methods fail to address how correlations between measurements can vary across sites. Data from the Alzheimer's Disease Neuroimaging Initiative is used to show that considerable differences in covariance exist across sites and that popular harmonization techniques do not address this issue. We then propose a novel harmonization method called Correcting Covariance Batch Effects (CovBat) that removes site effects in mean, variance, and covariance. We apply CovBat and show that within-site correlation matrices are successfully harmonized. Furthermore, we find that ML methods are unable to distinguish scanner manufacturer after our proposed harmonization is applied, and that the CovBat-harmonized data retain accurate prediction of disease group.

Magnetic susceptibility and R2* of myocardial reperfusion injury at 3T and 7T.

PURPOSE: Magnetic susceptibility (Δχ) alterations have shown association with myocardial infarction (MI) iron deposition, yet there remains limited understanding of the relationship between relaxation rates and susceptibility or the effect of magnetic field strength. Hence, Δχ and R2∗ in MI were compared at 3T and 7T. METHODS: Subacute MI was induced by coronary artery ligation in male Yorkshire swine. 3D multiecho gradient echo imaging was performed at 1-week postinfarction at 3T and 7T. Quantitative susceptibility mapping images were reconstructed using a morphology-enabled dipole inversion. R2∗ maps and quantitative susceptibility mapping were generated to assess the relationship between R2∗ , Δχ, and field strength. Infarct histopathology was investigated. RESULTS: Magnetic susceptibility was not significantly different across field strengths (7T: 126.8 ± 41.7 ppb; 3T: 110.2 ± 21.0 ppb, P = NS), unlike R2∗ (7T: 247.0 ± 14.8 Hz; 3T: 106.1 ± 6.5 Hz, P < .001). Additionally, infarct Δχ and R2∗ were significantly higher than remote myocardium. Magnetic susceptibility at 7T versus 3T had a significant association (ß = 1.02, R2 = 0.82, P < .001), as did R2∗ (ß = 2.35, R2 = 0.98, P < .001). Infarct pathophysiology and iron deposition were detected through histology and compared with imaging findings. CONCLUSION: R2∗ showed dependence and Δχ showed independence of field strength. Histology validated the presence of iron and supported imaging findings.

Deep Generative Medical Image Harmonization for Improving Cross-Site Generalization in Deep Learning Predictors.

BACKGROUND: In the medical imaging domain, deep learning-based methods have yet to see widespread clinical adoption, in part due to limited generalization performance across different imaging devices and acquisition protocols. The deviation between estimated brain age and biological age is an established biomarker of brain health and such models may benefit from increased cross-site generalizability. PURPOSE: To develop and evaluate a deep learning-based image harmonization method to improve cross-site generalizability of deep learning age prediction. STUDY TYPE: Retrospective. POPULATION: Eight thousand eight hundred and seventy-six subjects from six sites. Harmonization models were trained using all subjects. Age prediction models were trained using 2739 subjects from a single site and tested using the remaining 6137 subjects from various other sites. FIELD STRENGTH/SEQUENCE: Brain imaging with magnetization prepared rapid acquisition with gradient echo or spoiled gradient echo sequences at 1.5 T and 3 T. ASSESSMENT: StarGAN v2, was used to perform a canonical mapping from diverse datasets to a reference domain to reduce site-based variation while preserving semantic information. Generalization performance of deep learning age prediction was evaluated using harmonized, histogram matched, and unharmonized data. STATISTICAL TESTS: Mean absolute error (MAE) and Pearson correlation between estimated age and biological age quantified the performance of the age prediction model. RESULTS: Our results indicated a substantial improvement in age prediction in out-of-sample data, with the overall MAE improving from 15.81 (±0.21) years to 11.86 (±0.11) with histogram matching to 7.21 (±0.22) years with generative adversarial network (GAN)-based harmonization. In the multisite case, across the 5 out-of-sample sites, MAE improved from 9.78 (±6.69) years to 7.74 (±3.03) years with histogram normalization to 5.32 (±4.07) years with GAN-based harmonization. DATA CONCLUSION: While further research is needed, GAN-based medical image harmonization appears to be a promising tool for improving cross-site deep learning generalization. LEVEL OF EVIDENCE: 4 TECHNICAL EFFICACY: Stage 1.

Association of Multiple Plasma Biomarker Concentrations with Progression of Prevalent Diabetic Kidney Disease: Findings from the Chronic Renal Insufficiency Cohort (CRIC) Study.

BACKGROUND: Although diabetic kidney disease is the leading cause of ESKD in the United States, identifying those patients who progress to ESKD is difficult. Efforts are under way to determine if plasma biomarkers can help identify these high-risk individuals. METHODS: In our case-cohort study of 894 Chronic Renal Insufficiency Cohort Study participants with diabetes and an eGFR of <60 ml/min per 1.73 m2 at baseline, participants were randomly selected for the subcohort; cases were those patients who developed progressive diabetic kidney disease (ESKD or 40% eGFR decline). Using a multiplex system, we assayed plasma biomarkers related to tubular injury, inflammation, and fibrosis (KIM-1, TNFR-1, TNFR-2, MCP-1, suPAR, and YKL-40). Weighted Cox regression models related biomarkers to progression of diabetic kidney disease, and mixed-effects models estimated biomarker relationships with rate of eGFR change. RESULTS: Median follow-up was 8.7 years. Higher concentrations of KIM-1, TNFR-1, TNFR-2, MCP-1, suPAR, and YKL-40 were each associated with a greater risk of progression of diabetic kidney disease, even after adjustment for established clinical risk factors. After accounting for competing biomarkers, KIM-1, TNFR-2, and YKL-40 remained associated with progression of diabetic kidney disease; TNFR-2 had the highest risk (adjusted hazard ratio, 1.61; 95% CI, 1.15 to 2.26). KIM-1, TNFR-1, TNFR-2, and YKL-40 were associated with rate of eGFR decline. CONCLUSIONS: Higher plasma levels of KIM-1, TNFR-1, TNFR-2, MCP-1, suPAR, and YKL-40 were associated with increased risk of progression of diabetic kidney disease; TNFR-2 had the highest risk after accounting for the other biomarkers. These findings validate previous literature on TNFR-1, TNFR-2, and KIM-1 in patients with prevalent CKD and provide new insights into the influence of suPAR and YKL-40 as plasma biomarkers that require validation.

Pitfalls in brain age analyses.

Over the past decade, there has been an abundance of research on the difference between age and age predicted using brain features, which is commonly referred to as the "brain age gap." Researchers have identified that the brain age gap, as a linear transformation of an out-of-sample residual, is dependent on age. As such, any group differences on the brain age gap could simply be due to group differences on age. To mitigate the brain age gap's dependence on age, it has been proposed that age be regressed out of the brain age gap. If this modified brain age gap is treated as a corrected deviation from age, model accuracy statistics such as R2 will be artificially inflated to the extent that it is highly improbable that an R2 value below .85 will be obtained no matter the true model accuracy. Given the limitations of proposed brain age analyses, further theoretical work is warranted to determine the best way to quantify deviation from normality.

Adherence to Healthy Dietary Patterns and Risk of CKD Progression and All-Cause Mortality: Findings From the CRIC (Chronic Renal Insufficiency Cohort) Study.

RATIONALE & OBJECTIVE: Current dietary guidelines recommend that patients with chronic kidney disease (CKD) restrict individual nutrients, such as sodium, potassium, phosphorus, and protein. This approach can be difficult for patients to implement and ignores important nutrient interactions. Dietary patterns are an alternative method to intervene on diet. Our objective was to define the associations of 4 healthy dietary patterns with risk for CKD progression and all-cause mortality among people with CKD. STUDY DESIGN: Prospective cohort study. SETTING & PARTICIPANTS: 2,403 participants aged 21 to 74 years with estimated glomerular filtration rates of 20 to 70mL/min/1.73m2 and dietary data in the Chronic Renal Insufficiency Cohort (CRIC) Study. EXPOSURES: Healthy Eating Index-2015, Alternative Healthy Eating Index-2010, alternate Mediterranean diet (aMed), and Dietary Approaches to Stop Hypertension (DASH) diet scores were calculated from food frequency questionnaires. OUTCOMES: (1) CKD progression defined as≥50% estimated glomerular filtration rate decline, kidney transplantation, or dialysis and (2) all-cause mortality. ANALYTICAL APPROACH: Cox proportional hazards regression models adjusted for demographic, lifestyle, and clinical covariates to estimate hazard ratios (HRs) and 95% CIs. RESULTS: There were 855 cases of CKD progression and 773 deaths during a maximum of 14 years. Compared with participants with the lowest adherence, the most highly adherent tertile of Alternative Healthy Eating Index-2010, aMed, and DASH had lower adjusted risk for CKD progression, with the strongest results for aMed (HR, 0.75; 95% CI, 0.62-0.90). Compared with participants with the lowest adherence, the highest adherence tertiles for all scores had lower adjusted risk for all-cause mortality for each index (24%-31% lower risk). LIMITATIONS: Self-reported dietary intake. CONCLUSIONS: Greater adherence to several healthy dietary patterns is associated with lower risk for CKD progression and all-cause mortality among people with CKD. Guidance to adopt healthy dietary patterns can be considered as a strategy for managing CKD.

Alzheimer-like amyloid and tau alterations associated with cognitive deficit in temporal lobe epilepsy.

Temporal lobe epilepsy represents a major cause of drug-resistant epilepsy. Cognitive impairment is a frequent comorbidity, but the mechanisms are not fully elucidated. We hypothesized that the cognitive impairment in drug-resistant temporal lobe epilepsy could be due to perturbations of amyloid and tau signalling pathways related to activation of stress kinases, similar to those observed in Alzheimer's disease. We examined these pathways, as well as amyloid-ß and tau pathologies in the hippocampus and temporal lobe cortex of drug-resistant temporal lobe epilepsy patients who underwent temporal lobe resection (n = 19), in comparison with age- and region-matched samples from neurologically normal autopsy cases (n = 22). Post-mortem temporal cortex samples from Alzheimer's disease patients (n = 9) were used as positive controls to validate many of the neurodegeneration-related antibodies. Western blot and immunohistochemical analysis of tissue from temporal lobe epilepsy cases revealed increased phosphorylation of full-length amyloid precursor protein and its associated neurotoxic cleavage product amyloid-ß*56. Pathological phosphorylation of two distinct tau species was also increased in both regions, but increases in amyloid-ß1-42 peptide, the main component of amyloid plaques, were restricted to the hippocampus. Furthermore, several major stress kinases involved in the development of Alzheimer's disease pathology were significantly activated in temporal lobe epilepsy brain samples, including the c-Jun N-terminal kinase and the protein kinase R-like endoplasmic reticulum kinase. In temporal lobe epilepsy cases, hippocampal levels of phosphorylated amyloid precursor protein, its pro-amyloidogenic processing enzyme beta-site amyloid precursor protein cleaving enzyme 1, and both total and hyperphosphorylated tau expression, correlated with impaired preoperative executive function. Our study suggests that neurodegenerative and stress-related processes common to those observed in Alzheimer's disease may contribute to cognitive impairment in drug-resistant temporal lobe epilepsy. In particular, we identified several stress pathways that may represent potential novel therapeutic targets.

Two distinct neuroanatomical subtypes of schizophrenia revealed using machine learning.

Neurobiological heterogeneity in schizophrenia is poorly understood and confounds current analyses. We investigated neuroanatomical subtypes in a multi-institutional multi-ethnic cohort, using novel semi-supervised machine learning methods designed to discover patterns associated with disease rather than normal anatomical variation. Structural MRI and clinical measures in established schizophrenia (n = 307) and healthy controls (n = 364) were analysed across three sites of PHENOM (Psychosis Heterogeneity Evaluated via Dimensional Neuroimaging) consortium. Regional volumetric measures of grey matter, white matter, and CSF were used to identify distinct and reproducible neuroanatomical subtypes of schizophrenia. Two distinct neuroanatomical subtypes were found. Subtype 1 showed widespread lower grey matter volumes, most prominent in thalamus, nucleus accumbens, medial temporal, medial prefrontal/frontal and insular cortices. Subtype 2 showed increased volume in the basal ganglia and internal capsule, and otherwise normal brain volumes. Grey matter volume correlated negatively with illness duration in Subtype 1 (r = -0.201, P = 0.016) but not in Subtype 2 (r = -0.045, P = 0.652), potentially indicating different underlying neuropathological processes. The subtypes did not differ in age (t = -1.603, df = 305, P = 0.109), sex (chi-square = 0.013, df = 1, P = 0.910), illness duration (t = -0.167, df = 277, P = 0.868), antipsychotic dose (t = -0.439, df = 210, P = 0.521), age of illness onset (t = -1.355, df = 277, P = 0.177), positive symptoms (t = 0.249, df = 289, P = 0.803), negative symptoms (t = 0.151, df = 289, P = 0.879), or antipsychotic type (chi-square = 6.670, df = 3, P = 0.083). Subtype 1 had lower educational attainment than Subtype 2 (chi-square = 6.389, df = 2, P = 0.041). In conclusion, we discovered two distinct and highly reproducible neuroanatomical subtypes. Subtype 1 displayed widespread volume reduction correlating with illness duration, and worse premorbid functioning. Subtype 2 had normal and stable anatomy, except for larger basal ganglia and internal capsule, not explained by antipsychotic dose. These subtypes challenge the notion that brain volume loss is a general feature of schizophrenia and suggest differential aetiologies. They can facilitate strategies for clinical trial enrichment and stratification, and precision diagnostics.

MRI signatures of brain age and disease over the lifespan based on a deep brain network and 14 468 individuals worldwide.

Deep learning has emerged as a powerful approach to constructing imaging signatures of normal brain ageing as well as of various neuropathological processes associated with brain diseases. In particular, MRI-derived brain age has been used as a comprehensive biomarker of brain health that can identify both advanced and resilient ageing individuals via deviations from typical brain ageing. Imaging signatures of various brain diseases, including schizophrenia and Alzheimer's disease, have also been identified using machine learning. Prior efforts to derive these indices have been hampered by the need for sophisticated and not easily reproducible processing steps, by insufficiently powered or diversified samples from which typical brain ageing trajectories were derived, and by limited reproducibility across populations and MRI scanners. Herein, we develop and test a sophisticated deep brain network (DeepBrainNet) using a large (n = 11 729) set of MRI scans from a highly diversified cohort spanning different studies, scanners, ages and geographic locations around the world. Tests using both cross-validation and a separate replication cohort of 2739 individuals indicate that DeepBrainNet obtains robust brain-age estimates from these diverse datasets without the need for specialized image data preparation and processing. Furthermore, we show evidence that moderately fit brain ageing models may provide brain age estimates that are most discriminant of individuals with pathologies. This is not unexpected as tightly-fitting brain age models naturally produce brain-age estimates that offer little information beyond age, and loosely fitting models may contain a lot of noise. Our results offer some experimental evidence against commonly pursued tightly-fitting models. We show that the moderately fitting brain age models obtain significantly higher differentiation compared to tightly-fitting models in two of the four disease groups tested. Critically, we demonstrate that leveraging DeepBrainNet, along with transfer learning, allows us to construct more accurate classifiers of several brain diseases, compared to directly training classifiers on patient versus healthy control datasets or using common imaging databases such as ImageNet. We, therefore, derive a domain-specific deep network likely to reduce the need for application-specific adaptation and tuning of generic deep learning networks. We made the DeepBrainNet model freely available to the community for MRI-based evaluation of brain health in the general population and over the lifespan.

Imaging endpoints of intracranial atherosclerosis using vessel wall MR imaging: a systematic review.

PURPOSE: The vessel wall MR imaging (VWI) literature was systematically reviewed to assess the criteria and measurement methods of VWI-related imaging endpoints for symptomatic intracranial plaque in patients with ischemic events. METHODS: PubMed, Scopus, Web of Science, EMBASE, and Cochrane databases were searched up to October 2019. Two independent reviewers extracted data from 47 studies. A modified Guideline for Reporting Reliability and Agreement Studies was used to assess completeness of reporting. RESULTS: The specific VWI-pulse sequence used to identify plaque was reported in 51% of studies. A VWI-based criterion to define plaque was reported in 38% of studies. A definition for culprit plaque was reported in 40% of studies. Frequently scored qualitative imaging endpoints were plaque quadrant (21%) and enhancement (21%). Frequently measured quantitative imaging endpoints were stenosis (19%), lumen area (15%), and remodeling index (14%). Reproducibility for all endpoints ranged from good to excellent (range: ICCT1 hyperintensity = 0.451 to ICCstenosis = 0.983). However, rater specialty and years of experience varied among studies. CONCLUSIONS: Investigators are using different criteria to identify and measure VWI-imaging endpoints for culprit intracranial plaque. Early awareness of these differences to address methods of acquisition and measurement will help focus research resources and efforts in technique optimization and measurement reproducibility. Consensual definitions to detect plaque will be important to develop automatic lesion detection tools particularly in the era of radiomics.