Heritability of individualized cortical network topography.

Human cortex is patterned by a complex and interdigitated web of large-scale functional networks. Recent methodological breakthroughs reveal variation in the size, shape, and spatial topography of cortical networks across individuals. While spatial network organization emerges across development, is stable over time, and is predictive of behavior, it is not yet clear to what extent genetic factors underlie interindividual differences in network topography. Here, leveraging a nonlinear multidimensional estimation of heritability, we provide evidence that individual variability in the size and topographic organization of cortical networks are under genetic control. Using twin and family data from the Human Connectome Project (n = 1,023), we find increased variability and reduced heritability in the size of heteromodal association networks (h2 : M = 0.34, SD = 0.070), relative to unimodal sensory/motor cortex (h2 : M = 0.40, SD = 0.097). We then demonstrate that the spatial layout of cortical networks is influenced by genetics, using our multidimensional estimation of heritability (h2-multi; M = 0.14, SD = 0.015). However, topographic heritability did not differ between heteromodal and unimodal networks. Genetic factors had a regionally variable influence on brain organization, such that the heritability of network topography was greatest in prefrontal, precuneus, and posterior parietal cortex. Taken together, these data are consistent with relaxed genetic control of association cortices relative to primary sensory/motor regions and have implications for understanding population-level variability in brain functioning, guiding both individualized prediction and the interpretation of analyses that integrate genetics and neuroimaging.

LARO: Learned acquisition and reconstruction optimization to accelerate quantitative susceptibility mapping.

Quantitative susceptibility mapping (QSM) involves acquisition and reconstruction of a series of images at multi-echo time points to estimate tissue field, which prolongs scan time and requires specific reconstruction technique. In this paper, we present our new framework, called Learned Acquisition and Reconstruction Optimization (LARO), which aims to accelerate the multi-echo gradient echo (mGRE) pulse sequence for QSM. Our approach involves optimizing a Cartesian multi-echo k-space sampling pattern with a deep reconstruction network. Next, this optimized sampling pattern was implemented in an mGRE sequence using Cartesian fan-beam k-space segmenting and ordering for prospective scans. Furthermore, we propose to insert a recurrent temporal feature fusion module into the reconstruction network to capture signal redundancies along echo time. Our ablation studies show that both the optimized sampling pattern and proposed reconstruction strategy help improve the quality of the multi-echo image reconstructions. Generalization experiments show that LARO is robust on the test data with new pathologies and different sequence parameters. Our code is available at https://github.com/Jinwei1209/LARO-QSM.git.

Predicting individual task contrasts from resting-state functional connectivity using a surface-based convolutional network.

Task-based and resting-state represent the two most common experimental paradigms of functional neuroimaging. While resting-state offers a flexible and scalable approach for characterizing brain function, task-based techniques provide superior localization. In this paper, we build on recent deep learning methods to create a model that predicts task-based contrast maps from resting-state fMRI scans. Specifically, we propose BrainSurfCNN, a surface-based fully-convolutional neural network model that works with a representation of the brain's cortical sheet. BrainSurfCNN achieves exceptional predictive accuracy on independent test data from the Human Connectome Project, which is on par with the repeat reliability of the measured subject-level contrast maps. Conversely, our analyses reveal that a previously published benchmark is no better than group-average contrast maps. Finally, we demonstrate that BrainSurfCNN can generalize remarkably well to novel domains with limited training data.

NeuroGen: Activation optimized image synthesis for discovery neuroscience.

Functional MRI (fMRI) is a powerful technique that has allowed us to characterize visual cortex responses to stimuli, yet such experiments are by nature constructed based on a priori hypotheses, limited to the set of images presented to the individual while they are in the scanner, are subject to noise in the observed brain responses, and may vary widely across individuals. In this work, we propose a novel computational strategy, which we call NeuroGen, to overcome these limitations and develop a powerful tool for human vision neuroscience discovery. NeuroGen combines an fMRI-trained neural encoding model of human vision with a deep generative network to synthesize images predicted to achieve a target pattern of macro-scale brain activation. We demonstrate that the reduction of noise that the encoding model provides, coupled with the generative network's ability to produce images of high fidelity, results in a robust discovery architecture for visual neuroscience. By using only a small number of synthetic images created by NeuroGen, we demonstrate that we can detect and amplify differences in regional and individual human brain response patterns to visual stimuli. We then verify that these discoveries are reflected in the several thousand observed image responses measured with fMRI. We further demonstrate that NeuroGen can create synthetic images predicted to achieve regional response patterns not achievable by the best-matching natural images. The NeuroGen framework extends the utility of brain encoding models and opens up a new avenue for exploring, and possibly precisely controlling, the human visual system.

Magnetic Resonance Imaging Radiomics-Based Machine Learning Prediction of Clinically Significant Prostate Cancer in Equivocal PI-RADS 3 Lesions.

BACKGROUND: While Prostate Imaging Reporting and Data System (PI-RADS) 4 and 5 lesions typically warrant prostate biopsy and PI-RADS 1 and 2 lesions may be safely observed, PI-RADS 3 lesions are equivocal. PURPOSE: To construct and cross-validate a machine learning model based on radiomics features from T2 -weighted imaging (T2 WI) of PI-RADS 3 lesions to identify clinically significant prostate cancer (csPCa), that is, pathological Grade Group ≥ 2. STUDY TYPE: Single-center retrospective study. POPULATION: A total of 240 patients were included (training cohort, n = 188, age range 43-82 years; test cohort, n = 52, age range 41-79 years). Eligibility criteria were 1) magnetic resonance imaging (MRI)-targeted biopsy between 2015 and 2020; 2) PI-RADS 3 index lesion identified on multiparametric MRI; (3) biopsy performed within 1 year of MRI. The percentages of csPCa lesions were 10.6% and 15.4% in the training and test cohorts, respectively. FIELD STRENGTH/SEQUENCE: A 3 T; T2 WI turbo-spin echo, diffusion-weighted spin-echo echo planar imaging, dynamic contrast-enhanced MRI with time-resolved T1-weighted imaging. ASSESSMENT: Multislice volumes-of-interest (VOIs) were drawn in the PI-RADS 3 index lesions on T2 WI. A total of 107 radiomics features (first-order histogram and second-order texture) were extracted from the segmented lesions. STATISTICAL TESTS: A random forest classifier using the radiomics features as input was trained and validated for prediction of csPCa. The performance of the machine learning classifier, prostate specific antigen (PSA) density, and prostate volume for csPCa prediction was evaluated using receiver operating characteristic (ROC) analysis. RESULTS: The trained random forest classifier constructed from the T2 WI radiomics features good and statistically significant area-under-the-curves (AUCs) of 0.76 (P = 0.022) for prediction of csPCa in the test set. Prostate volume and PSA density showed moderate and nonsignificant performance (AUC 0.62, P = 0.275 and 0.61, P = 0.348, respectively) for csPCa prediction in the test set. CONCLUSION: The machine learning classifier based on T2 WI radiomic features demonstrated good performance for prediction of csPCa in PI-RADS 3 lesions. EVIDENCE LEVEL: 4 TECHNICAL EFFICACY: 2.

Correction: Phenome-wide heritability analysis of the UK Biobank.

[This corrects the article DOI: 10.1371/journal.pgen.1006711.].

Subspecialization within default mode nodes characterized in 10,000 UK Biobank participants.

The human default mode network (DMN) is implicated in several unique mental capacities. In this study, we tested whether brain-wide interregional communication in the DMN can be derived from population variability in intrinsic activity fluctuations, gray-matter morphology, and fiber tract anatomy. In a sample of 10,000 UK Biobank participants, pattern-learning algorithms revealed functional coupling states in the DMN that are linked to connectivity profiles between other macroscopical brain networks. In addition, DMN gray matter volume was covaried with white matter microstructure of the fornix. Collectively, functional and structural patterns unmasked a possible division of labor within major DMN nodes: Subregions most critical for cortical network interplay were adjacent to subregions most predictive of fornix fibers from the hippocampus that processes memories and places.

Machine Learning Prediction of Stroke Mechanism in Embolic Strokes of Undetermined Source.

BACKGROUND AND PURPOSE: One-fifth of ischemic strokes are embolic strokes of undetermined source (ESUS). Their theoretical causes can be classified as cardioembolic versus noncardioembolic. This distinction has important implications, but the categories' proportions are unknown. METHODS: Using data from the Cornell Acute Stroke Academic Registry, we trained a machine-learning algorithm to distinguish cardioembolic versus non-cardioembolic strokes, then applied the algorithm to ESUS cases to determine the predicted proportion with an occult cardioembolic source. A panel of neurologists adjudicated stroke etiologies using standard criteria. We trained a machine learning classifier using data on demographics, comorbidities, vitals, laboratory results, and echocardiograms. An ensemble predictive method including L1 regularization, gradient-boosted decision tree ensemble (XGBoost), random forests, and multivariate adaptive splines was used. Random search and cross-validation were used to tune hyperparameters. Model performance was assessed using cross-validation among cases of known etiology. We applied the final algorithm to an independent set of ESUS cases to determine the predicted mechanism (cardioembolic or not). To assess our classifier's validity, we correlated the predicted probability of a cardioembolic source with the eventual post-ESUS diagnosis of atrial fibrillation. RESULTS: Among 1083 strokes with known etiologies, our classifier distinguished cardioembolic versus noncardioembolic cases with excellent accuracy (area under the curve, 0.85). Applied to 580 ESUS cases, the classifier predicted that 44% (95% credibility interval, 39%-49%) resulted from cardiac embolism. Individual ESUS patients' predicted likelihood of cardiac embolism was associated with eventual atrial fibrillation detection (OR per 10% increase, 1.27 [95% CI, 1.03-1.57]; c-statistic, 0.68 [95% CI, 0.58-0.78]). ESUS patients with high predicted probability of cardiac embolism were older and had more coronary and peripheral vascular disease, lower ejection fractions, larger left atria, lower blood pressures, and higher creatinine levels. CONCLUSIONS: A machine learning estimator that distinguished known cardioembolic versus noncardioembolic strokes indirectly estimated that 44% of ESUS cases were cardioembolic.

Fidelity imposed network edit (FINE) for solving ill-posed image reconstruction.

Deep learning (DL) is increasingly used to solve ill-posed inverse problems in medical imaging, such as reconstruction from noisy and/or incomplete data, as DL offers advantages over conventional methods that rely on explicit image features and hand engineered priors. However, supervised DL-based methods may achieve poor performance when the test data deviates from the training data, for example, when it has pathologies not encountered in the training data. Furthermore, DL-based image reconstructions do not always incorporate the underlying forward physical model, which may improve performance. Therefore, in this work we introduce a novel approach, called fidelity imposed network edit (FINE), which modifies the weights of a pre-trained reconstruction network for each case in the testing dataset. This is achieved by minimizing an unsupervised fidelity loss function that is based on the forward physical model. FINE is applied to two important inverse problems in neuroimaging: quantitative susceptibility mapping (QSM) and under-sampled image reconstruction in MRI. Our experiments demonstrate that FINE can improve reconstruction accuracy.

Deep neural networks and kernel regression achieve comparable accuracies for functional connectivity prediction of behavior and demographics.

There is significant interest in the development and application of deep neural networks (DNNs) to neuroimaging data. A growing literature suggests that DNNs outperform their classical counterparts in a variety of neuroimaging applications, yet there are few direct comparisons of relative utility. Here, we compared the performance of three DNN architectures and a classical machine learning algorithm (kernel regression) in predicting individual phenotypes from whole-brain resting-state functional connectivity (RSFC) patterns. One of the DNNs was a generic fully-connected feedforward neural network, while the other two DNNs were recently published approaches specifically designed to exploit the structure of connectome data. By using a combined sample of almost 10,000 participants from the Human Connectome Project (HCP) and UK Biobank, we showed that the three DNNs and kernel regression achieved similar performance across a wide range of behavioral and demographic measures. Furthermore, the generic feedforward neural network exhibited similar performance to the two state-of-the-art connectome-specific DNNs. When predicting fluid intelligence in the UK Biobank, performance of all algorithms dramatically improved when sample size increased from 100 to 1000 subjects. Improvement was smaller, but still significant, when sample size increased from 1000 to 5000 subjects. Importantly, kernel regression was competitive across all sample sizes. Overall, our study suggests that kernel regression is as effective as DNNs for RSFC-based behavioral prediction, while incurring significantly lower computational costs. Therefore, kernel regression might serve as a useful baseline algorithm for future studies.

Sex classification using long-range temporal dependence of resting-state functional MRI time series.

A thorough understanding of sex differences that exist in the brains of healthy individuals is crucial for the study of neurological illnesses that exhibit phenotypic differences between males and females. Here we evaluate sex differences in regional temporal dependence of resting-state brain activity in 195 adult male-female pairs strictly matched for total grey matter volume from the Human Connectome Project. We find that males have more persistent temporal dependence in regions within temporal, parietal, and occipital cortices. Machine learning algorithms trained on regional temporal dependence measures achieve sex classification accuracies up to 81%. Regions with the strongest feature importance in the sex classification task included cerebellum, amygdala, and frontal and occipital cortices. Secondarily, we show that even after strict matching of total gray matter volume, significant volumetric sex differences persist; males have larger absolute cerebella, hippocampi, parahippocampi, thalami, caudates, and amygdalae while females have larger absolute cingulates, precunei, and frontal and parietal cortices. Sex classification based on regional volume achieves accuracies up to 85%, highlighting the importance of strict volume-matching when studying brain-based sex differences. Differential patterns in regional temporal dependence between the sexes identifies a potential neurobiological substrate or environmental effect underlying sex differences in functional brain activation patterns.

Spatial Topography of Individual-Specific Cortical Networks Predicts Human Cognition, Personality, and Emotion.

Resting-state functional magnetic resonance imaging (rs-fMRI) offers the opportunity to delineate individual-specific brain networks. A major question is whether individual-specific network topography (i.e., location and spatial arrangement) is behaviorally relevant. Here, we propose a multi-session hierarchical Bayesian model (MS-HBM) for estimating individual-specific cortical networks and investigate whether individual-specific network topography can predict human behavior. The multiple layers of the MS-HBM explicitly differentiate intra-subject (within-subject) from inter-subject (between-subject) network variability. By ignoring intra-subject variability, previous network mappings might confuse intra-subject variability for inter-subject differences. Compared with other approaches, MS-HBM parcellations generalized better to new rs-fMRI and task-fMRI data from the same subjects. More specifically, MS-HBM parcellations estimated from a single rs-fMRI session (10 min) showed comparable generalizability as parcellations estimated by 2 state-of-the-art methods using 5 sessions (50 min). We also showed that behavioral phenotypes across cognition, personality, and emotion could be predicted by individual-specific network topography with modest accuracy, comparable to previous reports predicting phenotypes based on connectivity strength. Network topography estimated by MS-HBM was more effective for behavioral prediction than network size, as well as network topography estimated by other parcellation approaches. Thus, similar to connectivity strength, individual-specific network topography might also serve as a fingerprint of human behavior.

The Shared Genetic Basis of Educational Attainment and Cerebral Cortical Morphology.

Individual differences in educational attainment are linked to differences in intelligence, and predict important social, economic, and health outcomes. Previous studies have found common genetic factors that influence educational achievement, cognitive performance and total brain volume (i.e., brain size). Here, in a large sample of participants from the UK Biobank, we investigate the shared genetic basis between educational attainment and fine-grained cerebral cortical morphological features, and associate this genetic variation with a related aspect of cognitive ability. Importantly, we execute novel statistical methods that enable high-dimensional genetic correlation analysis, and compute high-resolution surface maps for the genetic correlations between educational attainment and vertex-wise morphological measurements. We conduct secondary analyses, using the UK Biobank verbal-numerical reasoning score, to confirm that variation in educational attainment that is genetically correlated with cortical morphology is related to differences in cognitive performance. Our analyses relate the genetic overlap between cognitive ability and cortical thickness measurements to bilateral primary motor cortex as well as predominantly left superior temporal cortex and proximal regions. These findings extend our understanding of the neurobiology that connects genetic variation to individual differences in educational attainment and cognitive performance.

Phenome-wide heritability analysis of the UK Biobank.

Heritability estimation provides important information about the relative contribution of genetic and environmental factors to phenotypic variation, and provides an upper bound for the utility of genetic risk prediction models. Recent technological and statistical advances have enabled the estimation of additive heritability attributable to common genetic variants (SNP heritability) across a broad phenotypic spectrum. Here, we present a computationally and memory efficient heritability estimation method that can handle large sample sizes, and report the SNP heritability for 551 complex traits derived from the interim data release (152,736 subjects) of the large-scale, population-based UK Biobank, comprising both quantitative phenotypes and disease codes. We demonstrate that common genetic variation contributes to a broad array of quantitative traits and human diseases in the UK population, and identify phenotypes whose heritability is moderated by age (e.g., a majority of physical measures including height and body mass index), sex (e.g., blood pressure related traits) and socioeconomic status (education). Our study represents the first comprehensive phenome-wide heritability analysis in the UK Biobank, and underscores the importance of considering population characteristics in interpreting heritability.

Heritability analysis with repeat measurements and its application to resting-state functional connectivity.

Heritability, defined as the proportion of phenotypic variation attributable to genetic variation, provides important information about the genetic basis of a trait. Existing heritability analysis methods do not discriminate between stable effects (e.g., due to the subject's unique environment) and transient effects, such as measurement error. This can lead to misleading assessments, particularly when comparing the heritability of traits that exhibit different levels of reliability. Here, we present a linear mixed effects model to conduct heritability analyses that explicitly accounts for intrasubject fluctuations (e.g., due to measurement noise or biological transients) using repeat measurements. We apply the proposed strategy to the analysis of resting-state fMRI measurements-a prototypic data modality that exhibits variable levels of test-retest reliability across space. Our results reveal that the stable components of functional connectivity within and across well-established large-scale brain networks can be considerably heritable. Furthermore, we demonstrate that dissociating intra- and intersubject variation can reveal genetic influence on a phenotype that is not fully captured by conventional heritability analyses.

Ensemble learning with 3D convolutional neural networks for functional connectome-based prediction.

The specificity and sensitivity of resting state functional MRI (rs-fMRI) measurements depend on preprocessing choices, such as the parcellation scheme used to define regions of interest (ROIs). In this study, we critically evaluate the effect of brain parcellations on machine learning models applied to rs-fMRI data. Our experiments reveal an intriguing trend: On average, models with stochastic parcellations consistently perform as well as models with widely used atlases at the same spatial scale. We thus propose an ensemble learning strategy to combine the predictions from models trained on connectivity data extracted using different (e.g., stochastic) parcellations. We further present an implementation of our ensemble learning strategy with a novel 3D Convolutional Neural Network (CNN) approach. The proposed CNN approach takes advantage of the full-resolution 3D spatial structure of rs-fMRI data and fits non-linear predictive models. Our ensemble CNN framework overcomes the limitations of traditional machine learning models for connectomes that often rely on region-based summary statistics and/or linear models. We showcase our approach on a classification (autism patients versus healthy controls) and a regression problem (prediction of subject's age), and report promising results.

Multi-modal latent factor exploration of atrophy, cognitive and tau heterogeneity in Alzheimer's disease.

Individuals with Alzheimer's disease (AD) dementia exhibit significant heterogeneity across clinical symptoms, atrophy patterns, and spatial distribution of Tau deposition. Most previous studies of AD heterogeneity have focused on atypical clinical subtypes, defined subtypes with a single modality, or restricted their analyses to a priori brain regions and cognitive tests. Here, we considered a data-driven hierarchical Bayesian model to identify latent factors from atrophy patterns and cognitive deficits simultaneously, thus exploiting the rich dimensionality within each modality. Unlike most previous studies, our model allows each factor to be expressed to varying degrees within an individual, in order to reflect potential multiple co-existing pathologies. By applying our model to ADNI-GO/2 AD dementia participants, we found three atrophy-cognitive factors. The first factor was associated with medial temporal lobe atrophy, episodic memory deficits and disorientation to time/place ("MTL-Memory"). The second factor was associated with lateral temporal atrophy and language deficits ("Lateral Temporal-Language"). The third factor was associated with atrophy in posterior bilateral cortex, and visuospatial executive function deficits ("Posterior Cortical-Executive"). While the MTL-Memory and Posterior Cortical-Executive factors were discussed in previous literature, the Lateral Temporal-Language factor is novel and emerged only by considering atrophy and cognition jointly. Several analyses were performed to ensure generalizability, replicability and stability of the estimated factors. First, the factors generalized to new participants within a 10-fold cross-validation of ADNI-GO/2 AD dementia participants. Second, the factors were replicated in an independent ADNI-1 AD dementia cohort. Third, factor loadings of ADNI-GO/2 AD dementia participants were longitudinally stable, suggesting that these factors capture heterogeneity across patients, rather than longitudinal disease progression. Fourth, the model outperformed canonical correlation analysis at capturing associations between atrophy patterns and cognitive deficits. To explore the influence of the factors early in the disease process, factor loadings were estimated in ADNI-GO/2 mild cognitively impaired (MCI) participants. Although the associations between the atrophy patterns and cognitive profiles were weak in MCI compared to AD, we found that factor loadings were associated with inter-individual regional variation in Tau uptake. Taken together, these results suggest that distinct atrophy-cognitive patterns exist in typical Alzheimer's disease, and are associated with distinct patterns of Tau depositions before clinical dementia emerges.

Global signal regression strengthens association between resting-state functional connectivity and behavior.

Global signal regression (GSR) is one of the most debated preprocessing strategies for resting-state functional MRI. GSR effectively removes global artifacts driven by motion and respiration, but also discards globally distributed neural information and introduces negative correlations between certain brain regions. The vast majority of previous studies have focused on the effectiveness of GSR in removing imaging artifacts, as well as its potential biases. Given the growing interest in functional connectivity fingerprinting, here we considered the utilitarian question of whether GSR strengthens or weakens associations between resting-state functional connectivity (RSFC) and multiple behavioral measures across cognition, personality and emotion. By applying the variance component model to the Brain Genomics Superstruct Project (GSP), we found that behavioral variance explained by whole-brain RSFC increased by an average of 47% across 23 behavioral measures after GSR. In the Human Connectome Project (HCP), we found that behavioral variance explained by whole-brain RSFC increased by an average of 40% across 58 behavioral measures, when GSR was applied after ICA-FIX de-noising. To ensure generalizability, we repeated our analyses using kernel regression. GSR improved behavioral prediction accuracies by an average of 64% and 12% in the GSP and HCP datasets respectively. Importantly, the results were consistent across methods. A behavioral measure with greater RSFC-explained variance (using the variance component model) also exhibited greater prediction accuracy (using kernel regression). A behavioral measure with greater improvement in behavioral variance explained after GSR (using the variance component model) also enjoyed greater improvement in prediction accuracy after GSR (using kernel regression). Furthermore, GSR appeared to benefit task performance measures more than self-reported measures. Since GSR was more effective at removing motion-related and respiratory-related artifacts, GSR-related increases in variance explained and prediction accuracies were unlikely the result of motion-related or respiratory-related artifacts. However, it is worth emphasizing that the current study focused on whole-brain RSFC, so it remains unclear whether GSR improves RSFC-behavioral associations for specific connections or networks. Overall, our results suggest that at least in the case for young healthy adults, GSR strengthens the associations between RSFC and most (although not all) behavioral measures. Code for the variance component model and ridge regression can be found here: https://github.com/ThomasYeoLab/CBIG/tree/master/stable_projects/preprocessing/Li2019_GSR.

Polygenic Risk of Spasmodic Dysphonia is Associated With Vulnerable Sensorimotor Connectivity.

Spasmodic dysphonia (SD), or laryngeal dystonia, is an isolated task-specific dystonia of unknown causes and pathophysiology that selectively affects speech production. Using next-generation whole-exome sequencing in SD patients, we computed polygenic risk score from 1804 genetic markers based on a genome-wide association study in another form of similar task-specific focal dystonia, musician's dystonia. We further examined the associations between the polygenic risk score, resting-state functional connectivity abnormalities within the sensorimotor network, and SD clinical characteristics. We found that the polygenic risk of dystonia was significantly associated with decreased functional connectivity in the left premotor/primary sensorimotor and inferior parietal cortices in SD patients. Reduced connectivity of the inferior parietal cortex was correlated with the age of SD onset. The polygenic risk score contained a significant number of genetic variants lying near genes related to synaptic transmission and neural development. Our study identified a polygenic contribution to the overall genetic risk of dystonia in the cohort of SD patients. Associations between the polygenic risk and reduced functional connectivity of the sensorimotor and inferior parietal cortices likely represent an endophenotypic imaging marker of SD, while genes involved in synaptic transmission and neuron development may be linked to the molecular pathophysiology of this disorder.

Joint Analysis of Cortical Area and Thickness as a Replacement for the Analysis of the Volume of the Cerebral Cortex.

Cortical surface area is an increasingly used brain morphology metric that is ontogenetically and phylogenetically distinct from cortical thickness and offers a separate index of neurodevelopment and disease. However, the various existing methods for assessment of cortical surface area from magnetic resonance images have never been systematically compared. We show that the surface area method implemented in FreeSurfer corresponds closely to the exact, but computationally more demanding, mass-conservative (pycnophylactic) method, provided that images are smoothed. Thus, the data produced by this method can be interpreted as estimates of cortical surface area, as opposed to areal expansion. In addition, focusing on the joint analysis of thickness and area, we compare an improved, analytic method for measuring cortical volume to a permutation-based nonparametric combination (NPC) method. We use the methods to analyze area, thickness and volume in young adults born preterm with very low birth weight, and show that NPC analysis is a more sensitive option for studying joint effects on area and thickness, giving equal weight to variation in both of these 2 morphological features.