Constructing personalized characterizations of structural brain aberrations in patients with dementia using explainable artificial intelligence.

Deep learning approaches for clinical predictions based on magnetic resonance imaging data have shown great promise as a translational technology for diagnosis and prognosis in neurological disorders, but its clinical impact has been limited. This is partially attributed to the opaqueness of deep learning models, causing insufficient understanding of what underlies their decisions. To overcome this, we trained convolutional neural networks on structural brain scans to differentiate dementia patients from healthy controls, and applied layerwise relevance propagation to procure individual-level explanations of the model predictions. Through extensive validations we demonstrate that deviations recognized by the model corroborate existing knowledge of structural brain aberrations in dementia. By employing the explainable dementia classifier in a longitudinal dataset of patients with mild cognitive impairment, we show that the spatially rich explanations complement the model prediction when forecasting transition to dementia and help characterize the biological manifestation of disease in the individual brain. Overall, our work exemplifies the clinical potential of explainable artificial intelligence in precision medicine.

From Complexity to Precision-Charting Decision-Making Through Normative Modeling.

This Viewpoint synthesizes data-driven and theory-driven approaches to normative modeling.

Diagnostic accuracy of brain age prediction in a memory clinic population and comparison with clinically available volumetric measures.

The aim of this study was to assess the diagnostic validity of a deep learning-based method estimating brain age based on magnetic resonance imaging (MRI) and to compare it with volumetrics obtained using NeuroQuant (NQ) in a clinical cohort. Brain age prediction was performed on minimally processed MRI data using deep convolutional neural networks and an independent training set. The brain age gap (difference between chronological and biological age) was calculated, and volumetrics were performed in 110 patients with dementia (Alzheimer's disease, frontotemporal dementia (FTD), and dementia with Lewy bodies), and 122 with non-dementia (subjective and mild cognitive impairment). Area-under-the-curve (AUC) based on receiver operating characteristics and logistic regression analyses were performed. The mean age was 67.1 (9.5) years and 48.7% (113) were females. The dementia versus non-dementia sensitivity and specificity of the volumetric measures exceeded 80% and yielded higher AUCs compared to BAG. The explained variance of the prediction of diagnostic stage increased when BAG was added to the volumetrics. Further, BAG separated patients with FTD from other dementia etiologies with > 80% sensitivity and specificity. NQ volumetrics outperformed BAG in terms of diagnostic discriminatory power but the two methods provided complementary information, and BAG discriminated FTD from other dementia etiologies.

Regional, circuit and network heterogeneity of brain abnormalities in psychiatric disorders.

The substantial individual heterogeneity that characterizes people with mental illness is often ignored by classical case-control research, which relies on group mean comparisons. Here we present a comprehensive, multiscale characterization of the heterogeneity of gray matter volume (GMV) differences in 1,294 cases diagnosed with one of six conditions (attention-deficit/hyperactivity disorder, autism spectrum disorder, bipolar disorder, depression, obsessive-compulsive disorder and schizophrenia) and 1,465 matched controls. Normative models indicated that person-specific deviations from population expectations for regional GMV were highly heterogeneous, affecting the same area in <7% of people with the same diagnosis. However, these deviations were embedded within common functional circuits and networks in up to 56% of cases. The salience-ventral attention system was implicated transdiagnostically, with other systems selectively involved in depression, bipolar disorder, schizophrenia and attention-deficit/hyperactivity disorder. Phenotypic differences between cases assigned the same diagnosis may thus arise from the heterogeneous localization of specific regional deviations, whereas phenotypic similarities may be attributable to the dysfunction of common functional circuits and networks.

Fine-grained topographic organization within somatosensory cortex during resting-state and emotional face-matching task and its association with ASD traits.

Sensory atypicalities are particularly common in autism spectrum disorders (ASD). Nevertheless, our knowledge about the divergent functioning of the underlying somatosensory region and its association with ASD phenotype features is limited. We applied a data-driven approach to map the fine-grained variations in functional connectivity of the primary somatosensory cortex (S1) to the rest of the brain in 240 autistic and 164 neurotypical individuals from the EU-AIMS LEAP dataset, aged between 7 and 30. We estimated the S1 connection topography ('connectopy') at rest and during the emotional face-matching (Hariri) task, an established measure of emotion reactivity, and accessed its association with a set of clinical and behavioral variables. We first demonstrated that the S1 connectopy is organized along a dorsoventral axis, mapping onto the S1 somatotopic organization. We then found that its spatial characteristics were linked to the individuals' adaptive functioning skills, as measured by the Vineland Adaptive Behavior Scales, across the whole sample. Higher functional differentiation characterized the S1 connectopies of individuals with higher daily life adaptive skills. Notably, we detected significant differences between rest and the Hariri task in the S1 connectopies, as well as their projection maps onto the rest of the brain suggesting a task-modulating effect on S1 due to emotion processing. All in all, variation of adaptive skills appears to be reflected in the brain's mesoscale neural circuitry, as shown by the S1 connectivity profile, which is also differentially modulated during rest and emotional processing.

Genetic architecture of brain age and its causal relations with brain and mental disorders.

The difference between chronological age and the apparent age of the brain estimated from brain imaging data-the brain age gap (BAG)-is widely considered a general indicator of brain health. Converging evidence supports that BAG is sensitive to an array of genetic and nongenetic traits and diseases, yet few studies have examined the genetic architecture and its corresponding causal relationships with common brain disorders. Here, we estimate BAG using state-of-the-art neural networks trained on brain scans from 53,542 individuals (age range 3-95 years). A genome-wide association analysis across 28,104 individuals (40-84 years) from the UK Biobank revealed eight independent genomic regions significantly associated with BAG (p < 5 × 10-8) implicating neurological, metabolic, and immunological pathways - among which seven are novel. No significant genetic correlations or causal relationships with BAG were found for Parkinson's disease, major depressive disorder, or schizophrenia, but two-sample Mendelian randomization indicated a causal influence of AD (p = 7.9 × 10-4) and bipolar disorder (p = 1.35 × 10-2) on BAG. These results emphasize the polygenic architecture of brain age and provide insights into the causal relationship between selected neurological and neuropsychiatric disorders and BAG.

Mapping Normative Trajectories of Cognitive Function and Its Relation to Psychopathology Symptoms and Genetic Risk in Youth.

Background: Adolescence hosts a sharp increase in the incidence of mental disorders. The prodromal phases are often characterized by cognitive deficits that predate disease onset by several years. Characterization of cognitive performance in relation to normative trajectories may have value for early risk assessment and monitoring. Methods: Youth aged 8 to 21 years (N = 6481) from the Philadelphia Neurodevelopmental Cohort were included. Performance scores from a computerized neurocognitive battery were decomposed using principal component analysis, yielding a general cognitive score. Items reflecting various aspects of psychopathology from self-report questionnaires and collateral caregiver information were decomposed using independent component analysis, providing individual domain scores. Using normative modeling and Bayesian statistics, we estimated normative trajectories of cognitive function and tested for associations between cognitive deviance and psychopathological domain scores. In addition, we tested for associations with polygenic scores for mental and behavioral disorders often involving cognition, including schizophrenia, bipolar disorder, attention-deficit/hyperactivity disorder, and Alzheimer's disease. Results: More negative normative cognitive deviations were associated with higher general psychopathology burden and domains reflecting positive and prodromal psychosis, attention problems, norm-violating behavior, and anxiety. In addition, better performance was associated with higher joint burden of depression, suicidal ideation, and negative psychosis symptoms. The analyses revealed no evidence for associations with polygenic scores. Conclusions: Our results show that cognitive performance is associated with general and specific domains of psychopathology in youth. These findings support the close links between cognition and psychopathology in youth and highlight the potential of normative modeling for early risk assessment.

Shared pattern of impaired social communication and cognitive ability in the youth brain across diagnostic boundaries.

BACKGROUND: Abnormalities in brain structure are shared across diagnostic categories. Given the high rate of comorbidity, the interplay of relevant behavioural factors may also cross these classic boundaries. METHODS: We aimed to detect brain-based dimensions of behavioural factors using canonical correlation and independent component analysis in a clinical youth sample (n = 1732, 64 % male, age: 5-21 years). RESULTS: We identified two correlated patterns of brain structure and behavioural factors. The first mode reflected physical and cognitive maturation (r = 0.92, p = .005). The second mode reflected lower cognitive ability, poorer social skills, and psychological difficulties (r = 0.92, p = .006). Elevated scores on the second mode were a common feature across all diagnostic boundaries and linked to the number of comorbid diagnoses independently of age. Critically, this brain pattern predicted normative cognitive deviations in an independent population-based sample (n = 1253, 54 % female, age: 8-21 years), supporting the generalisability and external validity of the reported brain-behaviour relationships. CONCLUSIONS: These results reveal dimensions of brain-behaviour associations across diagnostic boundaries, highlighting potent disorder-general patterns as the most prominent. In addition to providing biologically informed patterns of relevant behavioural factors for mental illness, this contributes to a growing body of evidence in favour of transdiagnostic approaches to prevention and intervention.

Processing of social and monetary rewards in autism spectrum disorders.

BACKGROUND: Reward processing has been proposed to underpin the atypical social feature of autism spectrum disorder (ASD). However, previous neuroimaging studies have yielded inconsistent results regarding the specificity of atypicalities for social reward processing in ASD. AIMS: Utilising a large sample, we aimed to assess reward processing in response to reward type (social, monetary) and reward phase (anticipation, delivery) in ASD. METHOD: Functional magnetic resonance imaging during social and monetary reward anticipation and delivery was performed in 212 individuals with ASD (7.6-30.6 years of age) and 181 typically developing participants (7.6-30.8 years of age). RESULTS: Across social and monetary reward anticipation, whole-brain analyses showed hypoactivation of the right ventral striatum in participants with ASD compared with typically developing participants. Further, region of interest analysis across both reward types yielded ASD-related hypoactivation in both the left and right ventral striatum. Across delivery of social and monetary reward, hyperactivation of the ventral striatum in individuals with ASD did not survive correction for multiple comparisons. Dimensional analyses of autism and attention-deficit hyperactivity disorder (ADHD) scores were not significant. In categorical analyses, post hoc comparisons showed that ASD effects were most pronounced in participants with ASD without co-occurring ADHD. CONCLUSIONS: Our results do not support current theories linking atypical social interaction in ASD to specific alterations in social reward processing. Instead, they point towards a generalised hypoactivity of ventral striatum in ASD during anticipation of both social and monetary rewards. We suggest this indicates attenuated reward seeking in ASD independent of social content and that elevated ADHD symptoms may attenuate altered reward seeking in ASD.

Age-related brain deviations and aggression.

BACKGROUND: Disruptive behavior disorders (DBD) are heterogeneous at the clinical and the biological level. Therefore, the aims were to dissect the heterogeneous neurodevelopmental deviations of the affective brain circuitry and provide an integration of these differences across modalities. METHODS: We combined two novel approaches. First, normative modeling to map deviations from the typical age-related pattern at the level of the individual of (i) activity during emotion matching and (ii) of anatomical images derived from DBD cases (n = 77) and controls (n = 52) aged 8-18 years from the EU-funded Aggressotype and MATRICS consortia. Second, linked independent component analysis to integrate subject-specific deviations from both modalities. RESULTS: While cases exhibited on average a higher activity than would be expected for their age during face processing in regions such as the amygdala when compared to controls these positive deviations were widespread at the individual level. A multimodal integration of all functional and anatomical deviations explained 23% of the variance in the clinical DBD phenotype. Most notably, the top marker, encompassing the default mode network (DMN) and subcortical regions such as the amygdala and the striatum, was related to aggression across the whole sample. CONCLUSIONS: Overall increased age-related deviations in the amygdala in DBD suggest a maturational delay, which has to be further validated in future studies. Further, the integration of individual deviation patterns from multiple imaging modalities allowed to dissect some of the heterogeneity of DBD and identified the DMN, the striatum and the amygdala as neural signatures that were associated with aggression.

Closing the life-cycle of normative modeling using federated hierarchical Bayesian regression.

Clinical neuroimaging data availability has grown substantially in the last decade, providing the potential for studying heterogeneity in clinical cohorts on a previously unprecedented scale. Normative modeling is an emerging statistical tool for dissecting heterogeneity in complex brain disorders. However, its application remains technically challenging due to medical data privacy issues and difficulties in dealing with nuisance variation, such as the variability in the image acquisition process. Here, we approach the problem of estimating a reference normative model across a massive population using a massive multi-center neuroimaging dataset. To this end, we introduce a federated probabilistic framework using hierarchical Bayesian regression (HBR) to complete the life-cycle of normative modeling. The proposed model provides the possibilities to learn, update, and adapt the model parameters on decentralized neuroimaging data. Our experimental results confirm the superiority of HBR in deriving more accurate normative ranges on large multi-site neuroimaging datasets compared to the current standard methods. In addition, our approach provides the possibility to recalibrate and reuse the learned model on local datasets and even on datasets with very small sample sizes. The proposed method will facilitate applications of normative modeling as a medical tool for screening the biological deviations in individuals affected by complex illnesses such as mental disorders.

Deviations from normative brain white and gray matter structure are associated with psychopathology in youth.

Combining imaging modalities and metrics that are sensitive to various aspects of brain structure and maturation may help identify individuals that show deviations in relation to same-aged peers, and thus benefit early-risk-assessment for mental disorders. We used one timepoint multimodal brain imaging, cognitive, and questionnaire data from 1280 eight- to twenty-one-year-olds from the Philadelphia Neurodevelopmental Cohort. We estimated age-related gray and white matter properties and estimated individual deviation scores using normative modeling. Next, we tested for associations between the estimated deviation scores, and with psychopathology domain scores and cognition. More negative deviations in DTI-based fractional anisotropy (FA) and the first principal eigenvalue of the diffusion tensor (L1) were associated with higher scores on psychosis positive and prodromal symptoms and general psychopathology. A more negative deviation in cortical thickness (CT) was associated with a higher general psychopathology score. Negative deviations in global FA, surface area, L1 and CT were also associated with poorer cognitive performance. No robust associations were found between the deviation scores based on CT and DTI. The low correlations between the different multimodal magnetic resonance imaging-based deviation scores suggest that psychopathological burden in adolescence can be mapped onto partly distinct neurobiological features.

Accommodating site variation in neuroimaging data using normative and hierarchical Bayesian models.

The potential of normative modeling to make individualized predictions from neuroimaging data has enabled inferences that go beyond the case-control approach. However, site effects are often confounded with variables of interest in a complex manner and can bias estimates of normative models, which has impeded the application of normative models to large multi-site neuroimaging data sets. In this study, we suggest accommodating for these site effects by including them as random effects in a hierarchical Bayesian model. We compared the performance of a linear and a non-linear hierarchical Bayesian model in modeling the effect of age on cortical thickness. We used data of 570 healthy individuals from the ABIDE (autism brain imaging data exchange) data set in our experiments. In addition, we used data from individuals with autism to test whether our models are able to retain clinically useful information while removing site effects. We compared the proposed single stage hierarchical Bayesian method to several harmonization techniques commonly used to deal with additive and multiplicative site effects using a two stage regression, including regressing out site and harmonizing for site with ComBat, both with and without explicitly preserving variance caused by age and sex as biological variation of interest, and with a non-linear version of ComBat. In addition, we made predictions from raw data, in which site has not been accommodated for. The proposed hierarchical Bayesian method showed the best predictive performance according to multiple metrics. Beyond that, the resulting z-scores showed little to no residual site effects, yet still retained clinically useful information. In contrast, performance was particularly poor for the regression model and the ComBat model in which age and sex were not explicitly modeled. In all two stage harmonization models, predictions were poorly scaled, suffering from a loss of more than 90% of the original variance. Our results show the value of hierarchical Bayesian regression methods for accommodating site variation in neuroimaging data, which provides an alternative to harmonization techniques. While the approach we propose may have broad utility, our approach is particularly well suited to normative modeling where the primary interest is in accurate modeling of inter-subject variation and statistical quantification of deviations from a reference model.

Cerebellar Atypicalities in Autism?

BACKGROUND: The cerebellum contains more than 50% of the brain's neurons and is involved in social cognition. Cerebellar anatomical atypicalities have repeatedly been reported in individuals with autism. However, studies have yielded inconsistent findings, likely because of a lack of statistical power, and did not capture the clinical and neuroanatomical diversity of autism. Our aim was to better understand cerebellar anatomy and its diversity in autism. METHODS: We studied cerebellar gray matter morphology in 274 individuals with autism and 219 control subjects of a multicenter European cohort, EU-AIMS LEAP (European Autism Interventions-A Multicentre Study for Developing New Medications; Longitudinal European Autism Project). To ensure the robustness of our results, we conducted lobular parcellation of the cerebellum with 2 different pipelines in addition to voxel-based morphometry. We performed statistical analyses with linear, multivariate (including normative modeling), and meta-analytic approaches to capture the diversity of cerebellar anatomy in individuals with autism and control subjects. Finally, we performed a dimensional analysis of cerebellar anatomy in an independent cohort of 352 individuals with autism-related symptoms. RESULTS: We did not find any significant difference in the cerebellum when comparing individuals with autism and control subjects using linear models. In addition, there were no significant deviations in our normative models in the cerebellum in individuals with autism. Finally, we found no evidence of cerebellar atypicalities related to age, IQ, sex, or social functioning in individuals with autism. CONCLUSIONS: Despite positive results published in the last decade from relatively small samples, our results suggest that there is no striking difference in cerebellar anatomy of individuals with autism.

The normative modeling framework for computational psychiatry.

Normative modeling is an emerging and innovative framework for mapping individual differences at the level of a single subject or observation in relation to a reference model. It involves charting centiles of variation across a population in terms of mappings between biology and behavior, which can then be used to make statistical inferences at the level of the individual. The fields of computational psychiatry and clinical neuroscience have been slow to transition away from patient versus 'healthy' control analytic approaches, probably owing to a lack of tools designed to properly model biological heterogeneity of mental disorders. Normative modeling provides a solution to address this issue and moves analysis away from case-control comparisons that rely on potentially noisy clinical labels. Here we define a standardized protocol to guide users through, from start to finish, normative modeling analysis using the Predictive Clinical Neuroscience toolkit (PCNtoolkit). We describe the input data selection process, provide intuition behind the various modeling choices and conclude by demonstrating several examples of downstream analyses that the normative model may facilitate, such as stratification of high-risk individuals, subtyping and behavioral predictive modeling. The protocol takes ~1-3 h to complete.

Deep neural networks learn general and clinically relevant representations of the ageing brain.

The discrepancy between chronological age and the apparent age of the brain based on neuroimaging data - the brain age delta - has emerged as a reliable marker of brain health. With an increasing wealth of data, approaches to tackle heterogeneity in data acquisition are vital. To this end, we compiled raw structural magnetic resonance images into one of the largest and most diverse datasets assembled (n=53542), and trained convolutional neural networks (CNNs) to predict age. We achieved state-of-the-art performance on unseen data from unknown scanners (n=2553), and showed that higher brain age delta is associated with diabetes, alcohol intake and smoking. Using transfer learning, the intermediate representations learned by our model complemented and partly outperformed brain age delta in predicting common brain disorders. Our work shows we can achieve generalizable and biologically plausible brain age predictions using CNNs trained on heterogeneous datasets, and transfer them to clinical use cases.

Charting brain growth and aging at high spatial precision.

Defining reference models for population variation, and the ability to study individual deviations is essential for understanding inter-individual variability and its relation to the onset and progression of medical conditions. In this work, we assembled a reference cohort of neuroimaging data from 82 sites (N=58,836; ages 2-100) and used normative modeling to characterize lifespan trajectories of cortical thickness and subcortical volume. Models are validated against a manually quality checked subset (N=24,354) and we provide an interface for transferring to new data sources. We showcase the clinical value by applying the models to a transdiagnostic psychiatric sample (N=1985), showing they can be used to quantify variability underlying multiple disorders whilst also refining case-control inferences. These models will be augmented with additional samples and imaging modalities as they become available. This provides a common reference platform to bind results from different studies and ultimately paves the way for personalized clinical decision-making.

Boosting Schizophrenia Genetics by Utilizing Genetic Overlap With Brain Morphology.

BACKGROUND: Schizophrenia is a complex polygenic disorder with subtle, distributed abnormalities in brain morphology. There are indications of shared genetic architecture between schizophrenia and brain measures despite low genetic correlations. Through the use of analytical methods that allow for mixed directions of effects, this overlap may be leveraged to improve our understanding of underlying mechanisms of schizophrenia and enrich polygenic risk prediction outcome. METHODS: We ran a multivariate genome-wide analysis of 175 brain morphology measures using data from 33,735 participants of the UK Biobank and analyzed the results in a conditional false discovery rate together with schizophrenia genome-wide association study summary statistics of the Psychiatric Genomics Consortium (PGC) Wave 3. We subsequently created a pleiotropy-enriched polygenic score based on the loci identified through the conditional false discovery rate approach and used this to predict schizophrenia in a nonoverlapping sample of 743 individuals with schizophrenia and 1074 healthy controls. RESULTS: We found that 20% of the loci and 50% of the genes significantly associated with schizophrenia were also associated with brain morphology. The conditional false discovery rate analysis identified 428 loci, including 267 novel loci, significantly associated with brain-linked schizophrenia risk, with functional annotation indicating high relevance for brain tissue. The pleiotropy-enriched polygenic score explained more variance in liability than conventional polygenic scores across several scenarios. CONCLUSIONS: Our results indicate strong genetic overlap between schizophrenia and brain morphology with mixed directions of effect. The results also illustrate the potential of exploiting polygenetic overlap between brain morphology and mental disorders to boost discovery of brain tissue-specific genetic variants and its use in polygenic risk frameworks.

A randomised controlled trial (MindChamp) of a mindfulness-based intervention for children with ADHD and their parents.

BACKGROUND: Family mindfulness-based intervention (MBI) for child attention-deficit/hyperactivity disorder (ADHD) targets child self-control, parenting and parental mental health, but its effectiveness is still unclear. METHODS: MindChamp is a pre-registered randomised controlled trial comparing an 8-week family MBI (called 'MYmind') in addition to care-as-usual (CAU) (n = 55) with CAU-only (n = 48). Children aged 8-16 years with remaining ADHD symptoms after CAU were enrolled together with a parent. Primary outcome was post-treatment parent-rated child self-control deficits (BRIEF); post hoc, Reliable Change Indexes were explored. Secondary child outcomes included ADHD symptoms (parent/teacher-rated Conners' and SWAN; teacher-rated BRIEF), other psychological symptoms (parent/teacher-rated), well-being (parent-rated) and mindfulness (self-rated). Secondary parent outcomes included self-ratings of ADHD symptoms, other psychological symptoms, well-being, self-compassion and mindful parenting. Assessments were conducted at post-treatment, 2- and 6-month follow-up. RESULTS: Relative to CAU-only, MBI+CAU resulted in a small, statistically non-significant post-treatment improvement on the BRIEF (intention-to-treat: d = 0.27, p = .18; per protocol: d = 0.33, p = .11). Significantly more children showed reliable post-treatment improvement following MBI+CAU versus CAU-only (32% versus 11%, p < .05, Number-Needed-to-Treat = 4.7). ADHD symptoms significantly reduced post-treatment according to parent (Conners' and SWAN) and teacher ratings (BRIEF) per protocol. Only parent-rated hyperactivity impulsivity (SWAN) remained significantly reduced at 6-month follow-up. Post-treatment group differences on other secondary child outcomes were consistently favour of MBI+CAU, but mostly non-significant; no significant differences were found at follow-ups. Regarding parent outcomes, significant post-treatment improvements were found for their own ADHD symptoms, well-being and mindful parenting. At follow-ups, some significant effects remained (ADHD symptoms, mindful parenting), some additional significant effects appeared (other psychological symptoms, self-compassion) and others disappeared/remained non-significant. CONCLUSIONS: Family MBI+CAU did not outperform CAU-only in reducing child self-control deficits on a group level but more children reliably improved. Effects on parents were larger and more durable. When CAU for ADHD is insufficient, family MBI could be a valuable addition.

Phenotyping the Preterm Brain: Characterizing Individual Deviations From Normative Volumetric Development in Two Large Infant Cohorts.

The diverse cerebral consequences of preterm birth create significant challenges for understanding pathogenesis or predicting later outcome. Instead of focusing on describing effects common to the group, comparing individual infants against robust normative data offers a powerful alternative to study brain maturation. Here we used Gaussian process regression to create normative curves characterizing brain volumetric development in 274 term-born infants, modeling for age at scan and sex. We then compared 89 preterm infants scanned at term-equivalent age with these normative charts, relating individual deviations from typical volumetric development to perinatal risk factors and later neurocognitive scores. To test generalizability, we used a second independent dataset comprising of 253 preterm infants scanned using different acquisition parameters and scanner. We describe rapid, nonuniform brain growth during the neonatal period. In both preterm cohorts, cerebral atypicalities were widespread, often multiple, and varied highly between individuals. Deviations from normative development were associated with respiratory support, nutrition, birth weight, and later neurocognition, demonstrating their clinical relevance. Group-level understanding of the preterm brain disguises a large degree of individual differences. We provide a method and normative dataset that offer a more precise characterization of the cerebral consequences of preterm birth by profiling the individual neonatal brain.