Prediction of brain age using structural magnetic resonance imaging: A comparison of accuracy and test-retest reliability of publicly available software packages.

Brain age prediction algorithms using structural magnetic resonance imaging (MRI) aim to assess the biological age of the human brain. The difference between a person's chronological age and the estimated brain age is thought to reflect deviations from a normal aging trajectory, indicating a slower or accelerated biological aging process. Several pre-trained software packages for predicting brain age are publicly available. In this study, we perform a comparison of such packages with respect to (1) predictive accuracy, (2) test-retest reliability, and (3) the ability to track age progression over time. We evaluated the six brain age prediction packages: brainageR, DeepBrainNet, brainage, ENIGMA, pyment, and mccqrnn. The accuracy and test-retest reliability were assessed on MRI data from 372 healthy people aged between 18.4 and 86.2 years (mean 38.7 ± 17.5 years). All packages showed significant correlations between predicted brain age and chronological age (r = 0.66-0.97, p < 0.001), with pyment displaying the strongest correlation. The mean absolute error was between 3.56 (pyment) and 9.54 years (ENIGMA). brainageR, pyment, and mccqrnn were superior in terms of reliability (ICC values between 0.94-0.98), as well as predicting age progression over a longer time span. Of the six packages, pyment and brainageR consistently showed the highest accuracy and test-retest reliability.

Deep phenotyping towards precision psychiatry of first-episode depression - the Brain Drugs-Depression cohort.

BACKGROUND: Major Depressive Disorder (MDD) is a heterogenous brain disorder, with potentially multiple psychosocial and biological disease mechanisms. This is also a plausible explanation for why patients do not respond equally well to treatment with first- or second-line antidepressants, i.e., one-third to one-half of patients do not remit in response to first- or second-line treatment. To map MDD heterogeneity and markers of treatment response to enable a precision medicine approach, we will acquire several possible predictive markers across several domains, e.g., psychosocial, biochemical, and neuroimaging. METHODS: All patients are examined before receiving a standardised treatment package for adults aged 18-65 with first-episode depression in six public outpatient clinics in the Capital Region of Denmark. From this population, we will recruit a cohort of 800 patients for whom we will acquire clinical, cognitive, psychometric, and biological data. A subgroup (subcohort I, n = 600) will additionally provide neuroimaging data, i.e., Magnetic Resonance Imaging, and Electroencephalogram, and a subgroup of patients from subcohort I unmedicated at inclusion (subcohort II, n = 60) will also undergo a brain Positron Emission Tomography with the [11C]-UCB-J tracer binding to the presynaptic glycoprotein-SV2A. Subcohort allocation is based on eligibility and willingness to participate. The treatment package typically lasts six months. Depression severity is assessed with the Quick Inventory of Depressive Symptomatology (QIDS) at baseline, and 6, 12 and 18 months after treatment initiation. The primary outcome is remission (QIDS ≤ 5) and clinical improvement (≥ 50% reduction in QIDS) after 6 months. Secondary endpoints include remission at 12 and 18 months and %-change in QIDS, 10-item Symptom Checklist, 5-item WHO Well-Being Index, and modified Disability Scale from baseline through follow-up. We also assess psychotherapy and medication side-effects. We will use machine learning to determine a combination of characteristics that best predict treatment outcomes and statistical models to investigate the association between individual measures and clinical outcomes. We will assess associations between patient characteristics, treatment choices, and clinical outcomes using path analysis, enabling us to estimate the effect of treatment choices and timing on the clinical outcome. DISCUSSION: The BrainDrugs-Depression study is a real-world deep-phenotyping clinical cohort study of first-episode MDD patients. TRIAL REGISTRATION: Registered at clinicaltrials.gov November 15th, 2022 (NCT05616559).

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.

Cerebral Palsy - Early Diagnosis and Intervention Trial: protocol for the prospective multicentre CP-EDIT study with focus on diagnosis, prognostic factors, and intervention.

BACKGROUND: Early diagnosis of cerebral palsy (CP) is important to enable intervention at a time when neuroplasticity is at its highest. Current mean age at diagnosis is 13 months in Denmark. Recent research has documented that an early-diagnosis set-up can lower diagnostic age in high-risk infants. The aim of the current study is to lower diagnostic age of CP regardless of neonatal risk factors. Additionally, we want to investigate if an early intervention program added to standard care is superior to standard care alone. METHODS: The current multicentre study CP-EDIT (Early Diagnosis and Intervention Trial) with the GO-PLAY intervention included (Goal Oriented ParentaL supported home ActivitY program), aims at testing the feasibility of an early diagnosis set-up and the GO-PLAY early intervention. CP-EDIT is a prospective cohort study, consecutively assessing approximately 500 infants at risk of CP. We will systematically collect data at inclusion (age 3-11 months) and follow a subset of participants (n = 300) with CP or at high risk of CP until the age of two years. The GO-PLAY early intervention will be tested in 80 infants with CP or high risk of CP. Focus is on eight areas related to implementation and perspectives of the families: early cerebral magnetic resonance imaging (MRI), early genetic testing, implementation of the General Movements Assessment method, analysis of the GO-PLAY early intervention, parental perspective of early intervention and early diagnosis, early prediction of CP, and comparative analysis of the Hand Assessment for Infants, Hammersmith Infant Neurological Examination, MRI, and the General Movements method. DISCUSSION: Early screening for CP is increasingly possible and an interim diagnosis of "high risk of CP" is recommended but not currently used in clinical care in Denmark. Additionally, there is a need to accelerate identification in mild or ambiguous cases to facilitate appropriate therapy early. Most studies on early diagnosis focus on identifying CP in infants below five months corrected age. Little is known about early diagnosis in the 50% of all CP cases that are discernible later in infancy. The current study aims at improving care of patients with CP even before they have an established diagnosis. TRIAL REGISTRATION: ClinicalTrials.gov ID 22013292 (reg. date 31/MAR/2023) for the CP-EDIT cohort and ID 22041835 (reg. date 31/MAR/2023) for the GO-PLAY trial.

Psilocybin modulation of time-varying functional connectivity is associated with plasma psilocin and subjective effects.

BACKGROUND: Psilocin, the neuroactive metabolite of psilocybin, is a serotonergic psychedelic that induces an acute altered state of consciousness, evokes lasting changes in mood and personality in healthy individuals, and has potential as an antidepressant treatment. Examining the acute effects of psilocin on resting-state time-varying functional connectivity implicates network-level connectivity motifs that may underlie acute and lasting behavioral and clinical effects. AIM: Evaluate the association between resting-state time-varying functional connectivity (tvFC) characteristics and plasma psilocin level (PPL) and subjective drug intensity (SDI) before and right after intake of a psychedelic dose of psilocybin in healthy humans. METHODS: Fifteen healthy individuals completed the study. Before and at multiple time points after psilocybin intake, we acquired 10-minute resting-state blood-oxygen-level-dependent functional magnetic resonance imaging scans. Leading Eigenvector Dynamics Analysis (LEiDA) and diametrical clustering were applied to estimate discrete, sequentially active brain states. We evaluated associations between the fractional occurrence of brain states during a scan session and PPL and SDI using linear mixed-effects models. We examined associations between brain state dwell time and PPL and SDI using frailty Cox proportional hazards survival analysis. RESULTS: Fractional occurrences for two brain states characterized by lateral frontoparietal and medial fronto-parietal-cingulate coherence were statistically significantly negatively associated with PPL and SDI. Dwell time for these brain states was negatively associated with SDI and, to a lesser extent, PPL. Conversely, fractional occurrence and dwell time of a fully connected brain state partly associated with motion was positively associated with PPL and SDI. CONCLUSION: Our findings suggest that the acute perceptual psychedelic effects induced by psilocybin may stem from drug-level associated decreases in the occurrence and duration of lateral and medial frontoparietal connectivity motifs. We apply and argue for a modified approach to modeling eigenvectors produced by LEiDA that more fully acknowledges their underlying structure. Together these findings contribute to a more comprehensive neurobiological framework underlying acute effects of serotonergic psychedelics.

Open and reproducible neuroimaging: From study inception to publication.

Empirical observations of how labs conduct research indicate that the adoption rate of open practices for transparent, reproducible, and collaborative science remains in its infancy. This is at odds with the overwhelming evidence for the necessity of these practices and their benefits for individual researchers, scientific progress, and society in general. To date, information required for implementing open science practices throughout the different steps of a research project is scattered among many different sources. Even experienced researchers in the topic find it hard to navigate the ecosystem of tools and to make sustainable choices. Here, we provide an integrated overview of community-developed resources that can support collaborative, open, reproducible, replicable, robust and generalizable neuroimaging throughout the entire research cycle from inception to publication and across different neuroimaging modalities. We review tools and practices supporting study inception and planning, data acquisition, research data management, data processing and analysis, and research dissemination. An online version of this resource can be found at https://oreoni.github.io. We believe it will prove helpful for researchers and institutions to make a successful and sustainable move towards open and reproducible science and to eventually take an active role in its future development.

Hippocampal volume changes in a pharmacological sex-hormone manipulation risk model for depression in women.

Hormone transition phases may trigger depression in some women, yet the underlying mechanisms remain elusive. In a pharmacological sex-hormone manipulation model, we previously reported that estradiol reductions, induced with a gonadotropin-releasing hormone agonist (GnRHa), provoked subclinical depressive symptoms in healthy women, especially if neocortical serotonin transporter (SERT) binding also increased. Within this model, we here evaluated if GnRHa, compared to placebo, reduced hippocampal volume, in a manner that depended on the magnitude of the estradiol decrease and SERT binding, and if this decrease translated to the emergence of subclinical depressive symptoms. Sixty-three healthy, naturally cycling women were included in a randomized, double-blind, placebo-controlled GnRHa-intervention study. We quantified the change from baseline to follow-up (n = 60) in serum estradiol (ΔEstradiol), neocortical SERT binding ([11C] DASB positron emission tomography; ΔSERT), subclinical depressive symptoms (Hamilton depression rating scale; ΔHAMD-17), and hippocampal volume (magnetic resonance imaging data analyzed in Freesurfer 7.1, ΔHippocampus). Group differences in ΔHippocampus were evaluated in a t-test. Within the GnRHa group, associations between ΔEstradiol, ΔHippocampus, and ΔHAMD-17, in addition to ΔSERT-by-ΔEstradiol interaction effects on ΔHippocampus, were evaluated with linear regression models. Mean ΔHippocampus was not significantly different between the GnRHa and placebo group. Within the GnRHa group, hippocampal volume reductions were associated with the magnitude of estradiol decrease (p = 0.04, Cohen's f2 = 0.18), controlled for baseline SERT binding, but not subclinical depressive symptoms. There was no ΔSERT-by-ΔEstradiol interaction effects on ΔHippocampus. If replicated, our data highlight a possible association between estradiol fluctuations and hippocampal plasticity, adjusted for serotonergic contributions.

A high-resolution in vivo atlas of the human brain's benzodiazepine binding site of GABAA receptors.

Gamma-aminobutyric acid (GABA) is the main inhibitory neurotransmitter in the human brain and plays a key role in several brain functions and neuropsychiatric disorders such as anxiety, epilepsy, and depression. For decades, several in vivo and ex vivo techniques have been used to highlight the mechanisms of the GABA system, however, no studies have currently combined the techniques to create a high-resolution multimodal view of the GABA system. Here, we present a quantitative high-resolution in vivo atlas of the human brain benzodiazepine receptor sites (BZR) located on postsynaptic ionotropic GABAA receptors (GABAARs), generated on the basis of in vivo [11C]flumazenil Positron Emission Tomography (PET) data. Next, based on ex vivo autoradiography data, we transform the PET-generated atlas from binding values into BZR protein density. Finally, we examine the brain regional association between BZR protein density and ex vivo mRNA expression for the 19 subunits in the GABAAR, including an estimation of the minimally required expression of mRNA levels for each subunit to translate into BZR protein. This represents the first publicly available quantitative high-resolution in vivo atlas of the spatial distribution of BZR densities in the healthy human brain. The atlas provides a unique neuroscientific tool as well as novel insights into the association between mRNA expression for individual subunits in the GABAAR and the BZR density at each location in the brain.

The structure of the serotonin system: A PET imaging study.

The human brain atlas of the serotonin (5-HT) system does not conform with commonly used parcellations of neocortex, since the spatial distribution of homogeneous 5-HT receptors and transporter is not aligned with such brain regions. This discrepancy indicates that a neocortical parcellation specific to the 5-HT system is needed. We first outline issues with an existing parcellation of the 5-HT system, and present an alternative parcellation derived from brain MR- and high-resolution PET images of five different 5-HT targets from 210 healthy controls. We then explore how well this new 5-HT parcellation can explain mRNA levels of all 5-HT genes. The parcellation derived here represents a characterization of the 5-HT system which is more stable and explains the underlying 5-HT molecular imaging data better than other atlases, and may hence be more sensitive to capture region-specific changes modulated by 5-HT.

Optimization of preprocessing strategies in Positron Emission Tomography (PET) neuroimaging: A [11C]DASB PET study.

Positron Emission Tomography (PET) is an important neuroimaging tool to quantify the distribution of specific molecules in the brain. The quantification is based on a series of individually designed data preprocessing steps (pipeline) and an optimal preprocessing strategy is per definition associated with less noise and improved statistical power, potentially allowing for more valid neurobiological interpretations. In spite of this, it is currently unclear how to design the best preprocessing pipeline and to what extent the choice of each preprocessing step in the pipeline minimizes subject-specific errors. To evaluate the impact of various preprocessing strategies, we systematically examined 384 different pipeline strategies in data from 30 healthy participants scanned twice with the serotonin transporter (5-HTT) radioligand [11C]DASB. Five commonly used preprocessing steps with two to four options were investigated: (1) motion correction (MC) (2) co-registration (3) delineation of volumes of interest (VOI's) (4) partial volume correction (PVC), and (5) kinetic modeling. To quantitatively compare and evaluate the impact of various preprocessing strategies, we used the performance metrics: test-retest bias, within- and between-subject variability, the intraclass-correlation coefficient, and global signal-to-noise ratio. We also performed a power analysis to estimate the required sample size to detect either a 5% or 10% difference in 5-HTT binding as a function of preprocessing pipeline. The results showed a complex downstream dependency between the various preprocessing steps on the performance metrics. The choice of MC had the most profound effect on 5-HTT binding, prior to the effects caused by PVC and kinetic modeling, and the effects differed across VOI's. Notably, we observed a negative bias in 5-HTT binding across test and retest in 98% of pipelines, ranging from 0 to 6% depending on the pipeline. Optimization of the performance metrics revealed a trade-off in within- and between-subject variability at the group-level with opposite effects (i.e. minimization of within-subject variability increased between-subject variability and vice versa). The sample size required to detect a given effect size was also compromised by the preprocessing strategy, resulting in up to 80% increases in sample size needed to detect a 5% difference in 5-HTT binding. This is the first study to systematically investigate and demonstrate the effect of choosing different preprocessing strategies on the outcome of dynamic PET studies. We provide a framework to show how optimal and maximally powered neuroimaging results can be obtained by choosing appropriate preprocessing strategies and we provide recommendations depending on the study design. In addition, the results contribute to a better understanding of methodological uncertainty and variability in preprocessing decisions for future group- and/or longitudinal PET studies.

A High-Resolution In Vivo Atlas of the Human Brain's Serotonin System.

The serotonin (5-hydroxytryptamine, 5-HT) system modulates many important brain functions and is critically involved in many neuropsychiatric disorders. Here, we present a high-resolution, multidimensional, in vivo atlas of four of the human brain's 5-HT receptors (5-HT1A, 5-HT1B, 5-HT2A, and 5-HT4) and the 5-HT transporter (5-HTT). The atlas is created from molecular and structural high-resolution neuroimaging data consisting of positron emission tomography (PET) and magnetic resonance imaging (MRI) scans acquired in a total of 210 healthy individuals. Comparison of the regional PET binding measures with postmortem human brain autoradiography outcomes showed a high correlation for the five 5-HT targets and this enabled us to transform the atlas to represent protein densities (in picomoles per milliliter). We also assessed the regional association between protein concentration and mRNA expression in the human brain by comparing the 5-HT density across the atlas with data from the Allen Human Brain atlas and identified receptor- and transporter-specific associations that show the regional relation between the two measures. Together, these data provide unparalleled insight into the serotonin system of the human brain. SIGNIFICANCE STATEMENT: We present a high-resolution positron emission tomography (PET)- and magnetic resonance imaging-based human brain atlas of important serotonin receptors and the transporter. The regional PET-derived binding measures correlate strongly with the corresponding autoradiography protein levels. The strong correlation enables the transformation of the PET-derived human brain atlas into a protein density map of the serotonin (5-hydroxytryptamine, 5-HT) system. Next, we compared the regional receptor/transporter protein densities with mRNA levels and uncovered unique associations between protein expression and density at high detail. This new in vivo neuroimaging atlas of the 5-HT system not only provides insight in the human brain's regional protein synthesis, transport, and density, but also represents a valuable source of information for the neuroscience community as a comparative instrument to assess brain disorders.

Comparing fully automated state-of-the-art cerebellum parcellation from magnetic resonance images.

The human cerebellum plays an essential role in motor control, is involved in cognitive function (i.e., attention, working memory, and language), and helps to regulate emotional responses. Quantitative in-vivo assessment of the cerebellum is important in the study of several neurological diseases including cerebellar ataxia, autism, and schizophrenia. Different structural subdivisions of the cerebellum have been shown to correlate with differing pathologies. To further understand these pathologies, it is helpful to automatically parcellate the cerebellum at the highest fidelity possible. In this paper, we coordinated with colleagues around the world to evaluate automated cerebellum parcellation algorithms on two clinical cohorts showing that the cerebellum can be parcellated to a high accuracy by newer methods. We characterize these various methods at four hierarchical levels: coarse (i.e., whole cerebellum and gross structures), lobe, subdivisions of the vermis, and the lobules. Due to the number of labels, the hierarchy of labels, the number of algorithms, and the two cohorts, we have restricted our analyses to the Dice measure of overlap. Under these conditions, machine learning based methods provide a collection of strategies that are efficient and deliver parcellations of a high standard across both cohorts, surpassing previous work in the area. In conjunction with the rank-sum computation, we identified an overall winning method.

Serotonin 2A receptor agonist binding in the human brain with [(11)C]Cimbi-36: Test-retest reproducibility and head-to-head comparison with the antagonist [(18)F]altanserin.

INTRODUCTION: [(11)C]Cimbi-36 is a recently developed serotonin 2A (5-HT2A) receptor agonist positron emission tomography (PET) radioligand that has been successfully applied for human neuroimaging. Here, we investigate the test-retest variability of cerebral [(11)C]Cimbi-36 PET and compare [(11)C]Cimbi-36 and the 5-HT2A receptor antagonist [(18)F]altanserin. METHODS: Sixteen healthy volunteers (mean age 23.9 ± 6.4years, 6 males) were scanned twice with a high resolution research tomography PET scanner. All subjects were scanned after a bolus of [(11)C]Cimbi-36; eight were scanned twice to determine test-retest variability in [(11)C]Cimbi-36 binding measures, and another eight were scanned after a bolus plus constant infusion with [(18)F]altanserin. Regional differences in the brain distribution of [(11)C]Cimbi-36 and [(18)F]altanserin were assessed with a correlation of regional binding measures and with voxel-based analysis. RESULTS: Test-retest variability of [(11)C]Cimbi-36 non-displaceable binding potential (BPND) was consistently <5% in high-binding regions and lower for reference tissue models as compared to a 2-tissue compartment model. We found a highly significant correlation between regional BPNDs measured with [(11)C]Cimbi-36 and [(18)F]altanserin (mean Pearson's r: 0.95 ± 0.04) suggesting similar cortical binding of the radioligands. Relatively higher binding with [(11)C]Cimbi-36 as compared to [(18)F]altanserin was found in the choroid plexus and hippocampus in the human brain. CONCLUSIONS: Excellent test-retest reproducibility highlights the potential of [(11)C]Cimbi-36 for PET imaging of 5-HT2A receptor agonist binding in vivo. Our data suggest that Cimbi-36 and altanserin both bind to 5-HT2A receptors, but in regions with high 5-HT2C receptor density, choroid plexus and hippocampus, the [(11)C]Cimbi-36 binding likely represents binding to both 5-HT2A and 5-HT2C receptors.

Relevant feature set estimation with a knock-out strategy and random forests.

Group analysis of neuroimaging data is a vital tool for identifying anatomical and functional variations related to diseases as well as normal biological processes. The analyses are often performed on a large number of highly correlated measurements using a relatively smaller number of samples. Despite the correlation structure, the most widely used approach is to analyze the data using univariate methods followed by post-hoc corrections that try to account for the data's multivariate nature. Although widely used, this approach may fail to recover from the adverse effects of the initial analysis when local effects are not strong. Multivariate pattern analysis (MVPA) is a powerful alternative to the univariate approach for identifying relevant variations. Jointly analyzing all the measures, MVPA techniques can detect global effects even when individual local effects are too weak to detect with univariate analysis. Current approaches are successful in identifying variations that yield highly predictive and compact models. However, they suffer from lessened sensitivity and instabilities in identification of relevant variations. Furthermore, current methods' user-defined parameters are often unintuitive and difficult to determine. In this article, we propose a novel MVPA method for group analysis of high-dimensional data that overcomes the drawbacks of the current techniques. Our approach explicitly aims to identify all relevant variations using a "knock-out" strategy and the Random Forest algorithm. In evaluations with synthetic datasets the proposed method achieved substantially higher sensitivity and accuracy than the state-of-the-art MVPA methods, and outperformed the univariate approach when the effect size is low. In experiments with real datasets the proposed method identified regions beyond the univariate approach, while other MVPA methods failed to replicate the univariate results. More importantly, in a reproducibility study with the well-known ADNI dataset the proposed method yielded higher stability and power than the univariate approach.

Multimodal brain age prediction using machine learning: combining structural MRI and 5-HT2AR PET-derived features.

To better assess the pathology of neurodegenerative disorders and the efficacy of neuroprotective interventions, it is necessary to develop biomarkers that can accurately capture age-related biological changes in the human brain. Brain serotonin 2A receptors (5-HT2AR) show a particularly profound age-related decline and are also reduced in neurodegenerative disorders, such as Alzheimer's disease. This study investigates whether the decline in 5-HT2AR binding, measured in vivo using positron emission tomography (PET), can be used as a biomarker for brain aging. Specifically, we aim to (1) predict brain age using 5-HT2AR binding outcomes, (2) compare 5-HT2AR-based predictions of brain age to predictions based on gray matter (GM) volume, as determined with structural magnetic resonance imaging (MRI), and (3) investigate whether combining 5-HT2AR and GM volume data improves prediction. We used PET and MR images from 209 healthy individuals aged between 18 and 85 years (mean = 38, std = 18) and estimated 5-HT2AR binding and GM volume for 14 cortical and subcortical regions. Different machine learning algorithms were applied to predict chronological age based on 5-HT2AR binding, GM volume, and the combined measures. The mean absolute error (MAE) and a cross-validation approach were used for evaluation and model comparison. We find that both the cerebral 5-HT2AR binding (mean MAE = 6.63 years, std = 0.74 years) and GM volume (mean MAE = 6.95 years, std = 0.83 years) predict chronological age accurately. Combining the two measures improves the prediction further (mean MAE = 5.54 years, std = 0.68). In conclusion, 5-HT2AR binding measured using PET might be useful for improving the quantification of a biomarker for brain aging.

The Past, Present, and Future of the Brain Imaging Data Structure (BIDS).

The Brain Imaging Data Structure (BIDS) is a community-driven standard for the organization of data and metadata from a growing range of neuroscience modalities. This paper is meant as a history of how the standard has developed and grown over time. We outline the principles behind the project, the mechanisms by which it has been extended, and some of the challenges being addressed as it evolves. We also discuss the lessons learned through the project, with the aim of enabling researchers in other domains to learn from the success of BIDS.

Neuroanatomical dimensions in medication-free individuals with major depressive disorder and treatment response to SSRI antidepressant medications or placebo.

Major depressive disorder (MDD) is a heterogeneous clinical syndrome with widespread subtle neuroanatomical correlates. Our objective was to identify the neuroanatomical dimensions that characterize MDD and predict treatment response to selective serotonin reuptake inhibitor (SSRI) antidepressants or placebo. In the COORDINATE-MDD consortium, raw MRI data were shared from international samples (N = 1,384) of medication-free individuals with first-episode and recurrent MDD (N = 685) in a current depressive episode of at least moderate severity, but not treatment-resistant depression, as well as healthy controls (N = 699). Prospective longitudinal data on treatment response were available for a subset of MDD individuals (N = 359). Treatments were either SSRI antidepressant medication (escitalopram, citalopram, sertraline) or placebo. Multi-center MRI data were harmonized, and HYDRA, a semi-supervised machine-learning clustering algorithm, was utilized to identify patterns in regional brain volumes that are associated with disease. MDD was optimally characterized by two neuroanatomical dimensions that exhibited distinct treatment responses to placebo and SSRI antidepressant medications. Dimension 1 was characterized by preserved gray and white matter (N = 290 MDD), whereas Dimension 2 was characterized by widespread subtle reductions in gray and white matter (N = 395 MDD) relative to healthy controls. Although there were no significant differences in age of onset, years of illness, number of episodes, or duration of current episode between dimensions, there was a significant interaction effect between dimensions and treatment response. Dimension 1 showed a significant improvement in depressive symptoms following treatment with SSRI medication (51.1%) but limited changes following placebo (28.6%). By contrast, Dimension 2 showed comparable improvements to either SSRI (46.9%) or placebo (42.2%) (ß = -18.3, 95% CI (-34.3 to -2.3), P = 0.03). Findings from this case-control study indicate that neuroimaging-based markers can help identify the disease-based dimensions that constitute MDD and predict treatment response.

The path toward equal performance in medical machine learning.

To ensure equitable quality of care, differences in machine learning model performance between patient groups must be addressed. Here, we argue that two separate mechanisms can cause performance differences between groups. First, model performance may be worse than theoretically achievable in a given group. This can occur due to a combination of group underrepresentation, modeling choices, and the characteristics of the prediction task at hand. We examine scenarios in which underrepresentation leads to underperformance, scenarios in which it does not, and the differences between them. Second, the optimal achievable performance may also differ between groups due to differences in the intrinsic difficulty of the prediction task. We discuss several possible causes of such differences in task difficulty. In addition, challenges such as label biases and selection biases may confound both learning and performance evaluation. We highlight consequences for the path toward equal performance, and we emphasize that leveling up model performance may require gathering not only more data from underperforming groups but also better data. Throughout, we ground our discussion in real-world medical phenomena and case studies while also referencing relevant statistical theory.