Cerebellum and social abilities: A structural and functional connectivity study in a transdiagnostic sample.

The cerebellum has been involved in social abilities and autism. Given that the cerebellum is connected to the cortex via the cerebello-thalamo-cortical loop, the connectivity between the cerebellum and cortical regions involved in social interactions, that is, the right temporo-parietal junction (rTPJ) has been studied in individuals with autism, who suffer from prototypical deficits in social abilities. However, existing studies with small samples of categorical, case-control comparisons have yielded inconsistent results due to the inherent heterogeneity of autism, suggesting that investigating how clinical dimensions are related to cerebellar-rTPJ functional connectivity might be more relevant. Therefore, our objective was to study the functional connectivity between the cerebellum and rTPJ, focusing on its association with social abilities from a dimensional perspective in a transdiagnostic sample. We analyzed structural magnetic resonance imaging (MRI) and functional MRI (fMRI) scans obtained during naturalistic films watching from a large transdiagnostic dataset, the Healthy Brain Network (HBN), and examined the association between cerebellum-rTPJ functional connectivity and social abilities measured with the social responsiveness scale (SRS). We conducted univariate seed-to-voxel analysis, multivariate canonical correlation analysis (CCA), and predictive support vector regression (SVR). We included 1404 subjects in the structural analysis (age: 10.516 ± 3.034, range: 5.822-21.820, 506 females) and 414 subjects in the functional analysis (age: 11.260 ± 3.318 years, range: 6.020-21.820, 161 females). Our CCA model revealed a significant association between cerebellum-rTPJ functional connectivity, full-scale IQ (FSIQ) and SRS scores. However, this effect was primarily driven by FSIQ as suggested by SVR and univariate seed-to-voxel analysis. We also demonstrated the specificity of the rTPJ and the influence of structural anatomy in this association. Our results suggest that there is a complex relationship between cerebellum-rTPJ connectivity, social performance and IQ. This relationship is specific to the cerebellum-rTPJ connectivity, and is largely related to structural anatomy in these two regions. PRACTITIONER POINTS: We analyzed cerebellum-right temporoparietal junction (rTPJ) connectivity in a pediatric transdiagnostic sample. We found a complex relationship between cerebellum and rTPJ connectivity, social performance and IQ. Cerebellum and rTPJ functional connectivity is related to structural anatomy in these two regions.

Exploring the potential of representation and transfer learning for anatomical neuroimaging: Application to psychiatry.

The perspective of personalized medicine for brain disorders requires efficient learning models for anatomical neuroimaging-based prediction of clinical conditions. There is now a consensus on the benefit of deep learning (DL) in addressing many medical imaging tasks, such as image segmentation. However, for single-subject prediction problems, recent studies yielded contradictory results when comparing DL with Standard Machine Learning (SML) on top of classical feature extraction. Most existing comparative studies were limited in predicting phenotypes of little clinical interest, such as sex and age, and using a single dataset. Moreover, they conducted a limited analysis of the employed image pre-processing and feature selection strategies. This paper extensively compares DL and SML prediction capacity on five multi-site problems, including three increasingly complex clinical applications in psychiatry namely schizophrenia, bipolar disorder, and Autism Spectrum Disorder (ASD) diagnosis. To compensate for the relative scarcity of neuroimaging data on these clinical datasets, we also evaluate three pre-training strategies for transfer learning from brain imaging of the general healthy population: self-supervised learning, generative modeling and supervised learning with age. Overall, we find similar performance between randomly initialized DL and SML for the three clinical tasks and a similar scaling trend for sex prediction. This was replicated on an external dataset. We also show highly correlated discriminative brain regions between DL and linear ML models in all problems. Nonetheless, we demonstrate that self-supervised pre-training on large-scale healthy population imaging datasets (N≈10k), along with Deep Ensemble, allows DL to learn robust and transferable representations to smaller-scale clinical datasets (N≤1k). It largely outperforms SML on 2 out of 3 clinical tasks both in internal and external test sets. These findings suggest that the improvement of DL over SML in anatomical neuroimaging mainly comes from its capacity to learn meaningful and useful abstract representations of the brain anatomy, and it sheds light on the potential of transfer learning for personalized medicine in psychiatry.

Attention-gated 3D CapsNet for robust hippocampal segmentation.

Purpose: The hippocampus is organized in subfields (HSF) involved in learning and memory processes and widely implicated in pathologies at different ages of life, from neonatal hypoxia to temporal lobe epilepsy or Alzheimer's disease. Getting a highly accurate and robust delineation of sub-millimetric regions such as HSF to investigate anatomo-functional hypotheses is a challenge. One of the main difficulties encountered by those methodologies is related to the small size and anatomical variability of HSF, resulting in the scarcity of manual data labeling. Recently introduced, capsule networks solve analogous problems in medical imaging, providing deep learning architectures with rotational equivariance. Nonetheless, capsule networks are still two-dimensional and unassessed for the segmentation of HSF. Approach: We released a public 3D Capsule Network (3D-AGSCaps, https://github.com/clementpoiret/3D-AGSCaps) and compared it to equivalent architectures using classical convolutions on the automatic segmentation of HSF on small and atypical datasets (incomplete hippocampal inversion, IHI). We tested 3D-AGSCaps on three datasets with manually labeled hippocampi. Results: Our main results were: (1) 3D-AGSCaps produced segmentations with a better Dice Coefficient compared to CNNs on rotated hippocampi (p=0.004, cohen's d=0.179); (2) on typical subjects, 3D-AGSCaps produced segmentations with a Dice coefficient similar to CNNs while having 15 times fewer parameters (2.285M versus 35.069M). This may greatly facilitate the study of atypical subjects, including healthy and pathological cases like those presenting an IHI. Conclusion: We expect our newly introduced 3D-AGSCaps to allow a more accurate and fully automated segmentation on atypical populations, small datasets, as well as on and large cohorts where manual segmentations are nearly intractable.

Longitudinal MicroRNA Signature of Conversion to Psychosis.

BACKGROUND AND HYPOTHESIS: The emergence of psychosis in ultra-high-risk subjects (UHR) is influenced by gene-environment interactions that rely on epigenetic mechanisms such as microRNAs. However, whether they can be relevant pathophysiological biomarkers of psychosis' onset remains unknown. STUDY DESIGN: We present a longitudinal study of microRNA expression, measured in plasma by high-throughput sequencing at baseline and follow-up, in a prospective cohort of 81 UHR, 35 of whom developed psychosis at follow-up (converters). We combined supervised machine learning and differential graph analysis to assess the relative weighted contribution of each microRNA variation to the difference in outcome and identify outcome-specific networks. We then applied univariate models to the resulting microRNA variations common to both strategies, to interpret them as a function of demographic and clinical covariates. STUDY RESULTS: We identified 207 microRNA variations that significantly contributed to the classification. The differential network analysis found 276 network-specific correlations of microRNA variations. The combination of both strategies identified 25 microRNAs, whose gene targets were overrepresented in cognition and schizophrenia genome-wide association studies findings. Interpretable univariate models further supported the relevance of miR-150-5p and miR-3191-5p variations in psychosis onset, independent of age, sex, cannabis use, and medication. CONCLUSIONS: In this first longitudinal study of microRNA variation during conversion to psychosis, we combined 2 methodologically independent data-driven strategies to identify a dynamic epigenetic signature of the emergence of psychosis that is pathophysiologically relevant.

Prediction of post-traumatic stress disorder in family members of ICU patients: a machine learning approach.

PURPOSE: Post-traumatic stress disorder (PTSD) can affect family members of patients admitted to the intensive care unit (ICU). Easily accessible patient's and relative's information may help develop accurate risk stratification tools to direct relatives at higher risk of PTSD toward appropriate management. METHODS: PTSD was measured 90 days after ICU discharge using validated instruments (Impact of Event Scale and Impact of Event Scale-Revised) in 2374 family members. Various supervised machine learning approaches were used to predict PTSD in family members and evaluated on an independent held-out test dataset. To better understand variables' contributions to PTSD predicted probability, we used machine learning interpretability methods on the best predictive algorithm. RESULTS: Non-linear ensemble learning tree-based methods showed better predictive performances (Random Forest-area under curve, AUC = 0.73 [0.68-0.77] and XGBoost-AUC = 0.73 [0.69-0.78]) than regularized linear models, kernel-based models, or deep learning models. In the best performing algorithm, most important features that positively contributed to PTSD's predicted probability were all non-modifiable factors, namely, lower patient's age, longer duration of ICU stay, relative's female sex, lower relative's age, relative being a spouse/child, and patient's death in ICU. A sensitivity analysis in bereaved relatives did not alter the algorithm's predictive performance. CONCLUSION: We propose a machine learning-based approach to predict PTSD in relatives of ICU patients at an individual level. In this model, PTSD is mostly influenced by non-modifiable factors.

Asynchronous neural maturation predicts transition to psychosis.

AIM: Neuroimaging-based machine-learning predictions of psychosis onset rely on the hypothesis that structural brain anomalies may reflect the underlying pathophysiology. Yet, current predictors remain difficult to interpret in light of brain structure. Here, we combined an advanced interpretable supervised algorithm and a model of neuroanatomical age to identify the level of brain maturation of the regions most predictive of psychosis. METHODS: We used the voxel-based morphometry of a healthy control dataset (N = 2024) and a prospective longitudinal UHR cohort (N = 82), of which 27 developed psychosis after one year. In UHR, psychosis was predicted at one year using Elastic-Net-Total-Variation (Enet-TV) penalties within a five-fold cross-validation, providing an interpretable map of distinct predictive regions. Using both the whole brain and each predictive region separately, a brain age predictor was then built and validated in 1605 controls, externally tested in 419 controls from an independent cohort, and applied in UHR. Brain age gaps were computed as the difference between chronological and predicted age, providing a proxy of whole-brain and regional brain maturation. RESULTS: Psychosis prediction was performant with 80 ± 4% of area-under-curve and 69 ± 5% of balanced accuracy (P < 0.001), and mainly leveraged volumetric increases in the ventromedial prefrontal cortex and decreases in the left precentral gyrus and the right orbitofrontal cortex. These regions were predicted to have delayed and accelerated maturational patterns, respectively. CONCLUSION: By combining an interpretable supervised model of conversion to psychosis with a brain age predictor, we showed that inter-regional asynchronous brain maturation underlines the predictive signature of psychosis.

A fast and robust hippocampal subfields segmentation: HSF revealing lifespan volumetric dynamics.

The hippocampal subfields, pivotal to episodic memory, are distinct both in terms of cyto- and myeloarchitectony. Studying the structure of hippocampal subfields in vivo is crucial to understand volumetric trajectories across the lifespan, from the emergence of episodic memory during early childhood to memory impairments found in older adults. However, segmenting hippocampal subfields on conventional MRI sequences is challenging because of their small size. Furthermore, there is to date no unified segmentation protocol for the hippocampal subfields, which limits comparisons between studies. Therefore, we introduced a novel segmentation tool called HSF short for hippocampal segmentation factory, which leverages an end-to-end deep learning pipeline. First, we validated HSF against currently used tools (ASHS, HIPS, and HippUnfold). Then, we used HSF on 3,750 subjects from the HCP development, young adults, and aging datasets to study the effect of age and sex on hippocampal subfields volumes. Firstly, we showed HSF to be closer to manual segmentation than other currently used tools (p < 0.001), regarding the Dice Coefficient, Hausdorff Distance, and Volumetric Similarity. Then, we showed differential maturation and aging across subfields, with the dentate gyrus being the most affected by age. We also found faster growth and decay in men than in women for most hippocampal subfields. Thus, while we introduced a new, fast and robust end-to-end segmentation tool, our neuroanatomical results concerning the lifespan trajectories of the hippocampal subfields reconcile previous conflicting results.

Understanding the relationship between cerebellar structure and social abilities.

BACKGROUND: The cerebellum contains more than 50% of all neurons in the brain and is involved in a broad range of cognitive functions, including social communication and social cognition. Inconsistent atypicalities in the cerebellum have been reported in individuals with autism compared to controls suggesting the limits of categorical case control comparisons. Alternatively, investigating how clinical dimensions are related to neuroanatomical features, in line with the Research Domain Criteria approach, might be more relevant. We hypothesized that the volume of the "cognitive" lobules of the cerebellum would be associated with social difficulties. METHODS: We analyzed structural MRI data from a large pediatric and transdiagnostic sample (Healthy Brain Network). We performed cerebellar parcellation with a well-validated automated segmentation pipeline (CERES). We studied how social communication abilities-assessed with the social component of the Social Responsiveness Scale (SRS)-were associated with the cerebellar structure, using linear mixed models and canonical correlation analysis. RESULTS: In 850 children and teenagers (mean age 10.8 ± 3 years; range 5-18 years), we found a significant association between the cerebellum, IQ and social communication performance in our canonical correlation model. LIMITATIONS: Cerebellar parcellation relies on anatomical boundaries, which does not overlap with functional anatomy. The SRS was originally designed to identify social impairments associated with autism spectrum disorders. CONCLUSION: Our results unravel a complex relationship between cerebellar structure, social performance and IQ and provide support for the involvement of the cerebellum in social and cognitive processes.

Enhancing fetal alcohol spectrum disorders diagnosis with a classifier based on the intracerebellar gradient of volumetric undersizing.

In fetal alcohol spectrum disorders (FASD), brain growth deficiency is a hallmark of subjects both with fetal alcohol syndrome (FAS) and with non-syndromic FASD (NS-FASD, i.e., those without specific diagnostic features). However, although the cerebellum was suggested to be more severely undersized than the rest of the brain, it has not yet been given a specific place in the FASD diagnostic criteria where neuroanatomical features still count for little if anything in diagnostic specificity. We applied a combination of cerebellar segmentation tools on a 1.5 T 3DT1 brain MRI dataset from a monocentric population of 89 FASD (52 FAS, 37 NS-FASD) and 126 typically developing controls (6-20 years old), providing 8 volumes: cerebellum, vermis and 3 lobes (anterior, posterior, inferior), plus total brain volume. After adjustment of confounders, the allometric scaling relationship between these cerebellar volumes (Vi ) and the total brain or cerebellum volume (Vt ) was fitted (Vi = bVt a ), and the effect of group (FAS, control) on allometric scaling was evaluated. We then estimated for each cerebellar volume in the FAS population the deviation from the typical scaling (v DTS) learned in the controls. Lastly, we trained and tested two classifiers to discriminate FAS from controls, one based on the total cerebellum v DTS only, the other based on all the cerebellar v DTS, comparing their performance both in the FAS and the NS-FASD group. Allometric scaling was significantly different between FAS and control group for all the cerebellar volumes (p < .001). We confirmed the excess of total cerebellum volume deficit (v DTS = -10.6%) and revealed an antero-inferior-posterior gradient of volumetric undersizing in the hemispheres (-12.4%, 1.1%, 2.0%, respectively) and the vermis (-16.7%, -9.2%, -8.6%, repectively). The classifier based on the intracerebellar gradient of v DTS performed more efficiently than the one based on total cerebellum v DTS only (AUC = 92% vs. 82%, p = .001). Setting a high probability threshold for >95% specificity of the classifiers, the gradient-based classifier identified 35% of the NS-FASD to have a FAS cerebellar phenotype, compared to 11% with the cerebellum-only classifier (pFISHER = 0.027). In a large series of FASD, this study details the volumetric undersizing within the cerebellum at the lobar and vermian level using allometric scaling, revealing an anterior-inferior-posterior gradient of vulnerability to prenatal alcohol exposure. It also strongly suggests that this intracerebellar gradient of volumetric undersizing may be a reliable neuroanatomical signature of FAS that could be used to improve the specificity of the diagnosis of NS-FASD.

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.

OpenBHB: a Large-Scale Multi-Site Brain MRI Data-set for Age Prediction and Debiasing.

Prediction of chronological age from neuroimaging in the healthy population is an important issue because the deviations from normal brain age may highlight abnormal trajectories towards brain disorders. As a first step, ML models have emerged to predict chronological age from brain MRI, as a proxy measure of biological age. However, there is currently no consensus w.r.t which Machine Learning (ML) model is best suited for this task, largely because of a lack of public benchmark. Furthermore, new large emerging population neuroimaging datasets are often biased by the acquisition center images are coming from. This bias heavily deteriorates models generalization capacities, especially for Deep Learning (DL) algorithms that are known to overfit rapidly on the simplest features (known as simplicity bias). Here we propose a new public benchmarking resource, namely Open Big Healthy Brains (OpenBHB), along with a challenge for both brain age prediction and site-effect removal through a representation learning framework. OpenBHB is large-scale, gathering >5K 3D T1 brain MRI from Healthy Controls (HC) and highly multi-sites, aggregating >60 centers worldwide and 10 studies. OpenBHB is expected to grow both in terms of available modalities and number of subjects. All OpenBHB datasets are uniformly preprocessed, including quality check, with container technologies that consist in: 3D Voxel-Based Morphometry maps (VBM from CAT12), quasi-raw (simple linear alignment of images), and Surface-Based Morphometry indices (SBM, from FreeSurfer). The OpenBHB challenge is permanent and we provide all tools, materials and tutorials for participants to easily submit and benchmark their model against each other on a public leaderboard.

Brain anomalies in early psychosis: From secondary to primary psychosis.

Brain anomalies are frequently found in early psychoses. Although they may remain undetected for many years, their interpretation is critical for differential diagnosis. In secondary psychoses, their identification may allow specific management. They may also shed light on various pathophysiological aspects of primary psychoses. Here we reviewed cases of secondary psychoses associated with brain anomalies, reported over a 20-year period in adolescents and young adults aged 13-30 years old. We considered age at first psychotic symptoms, relevant medical history, the nature of psychiatric symptoms, clinical red flags, the nature of the brain anomaly reported, and the underlying disease. We discuss the relevance of each brain area in light of normal brain function, recent case-control studies, and postulated pathophysiology. We show that anomalies in all regions, whether diffuse, multifocal, or highly localized, may lead to psychosis, without necessarily being associated with non-psychiatric symptoms. This underlines the interest of neuroimaging in the initial workup, and supports the hypothesis of psychosis as a global network dysfunction that involves many different regions.

Decoding Activity in Broca's Area Predicts the Occurrence of Auditory Hallucinations Across Subjects.

BACKGROUND: Functional magnetic resonance imaging (fMRI) capture aims at detecting auditory-verbal hallucinations (AVHs) from continuously recorded brain activity. Establishing efficient capture methods with low computational cost that easily generalize between patients remains a key objective in precision psychiatry. To address this issue, we developed a novel automatized fMRI-capture procedure for AVHs in patients with schizophrenia (SCZ). METHODS: We used a previously validated but labor-intensive personalized fMRI-capture method to train a linear classifier using machine learning techniques. We benchmarked the performances of this classifier on 2320 AVH periods versus resting-state periods obtained from SCZ patients with frequent symptoms (n = 23). We characterized patterns of blood oxygen level-dependent activity that were predictive of AVH both within and between subjects. Generalizability was assessed with a second independent sample gathering 2000 AVH labels (n = 34 patients with SCZ), while specificity was tested with a nonclinical control sample performing an auditory imagery task (840 labels, n = 20). RESULTS: Our between-subject classifier achieved high decoding accuracy (area under the curve = 0.85) and discriminated AVH from rest and verbal imagery. Optimizing the parameters on the first schizophrenia dataset and testing its performance on the second dataset led to an out-of-sample area under the curve of 0.85 (0.88 for the converse test). We showed that AVH detection critically depends on local blood oxygen level-dependent activity patterns within Broca's area. CONCLUSIONS: Our results demonstrate that it is possible to reliably detect AVH states from fMRI blood oxygen level-dependent signals in patients with SCZ using a multivariate decoder without performing complex preprocessing steps. These findings constitute a crucial step toward brain-based treatments for severe drug-resistant hallucinations.

Irritability Is Associated With Decreased Cortical Surface Area and Anxiety With Decreased Gyrification During Brain Development.

Background: Brain development is of utmost importance for the emergence of psychiatric disorders, as the most severe of them arise before 25 years old. However, little is known regarding how early transdiagnostic symptoms, in a dimensional framework, are associated with cortical development. Anxiety and irritability are central vulnerability traits for subsequent mood and anxiety disorders. In this study, we investigate how these dimensions are related to structural changes in the brain to understand how they may increase the transition risk to full-blown disorders. Methods: We used the opportunity of an open access developmental cohort, the Healthy Brain Network, to investigate associations between cortical surface markers and irritability and anxiety scores as measured by parents and self-reports. Results: We found that in 658 young people (with a mean age of 11.6) the parental report of irritability is associated with decreased surface area in the bilateral rostral prefrontal cortex and the precuneus. Furthermore, parental reports of anxiety were associated with decreased local gyrification index in the anterior cingulate cortex and dorsomedial prefrontal cortex. Conclusions: These results are consistent with current models of emotion regulation network maturation, showing decreased surface area or gyrification index in regions associated with impaired affective control in mood and anxiety disorders. Our results highlight how dimensional traits may increase vulnerability for these disorders.

Lithium prevents grey matter atrophy in patients with bipolar disorder: an international multicenter study.

BACKGROUND: Lithium (Li) is the gold standard treatment for bipolar disorder (BD). However, its mechanisms of action remain unknown but include neurotrophic effects. We here investigated the influence of Li on cortical and local grey matter (GM) volumes in a large international sample of patients with BD and healthy controls (HC). METHODS: We analyzed high-resolution T1-weighted structural magnetic resonance imaging scans of 271 patients with BD type I (120 undergoing Li) and 316 HC. Cortical and local GM volumes were compared using voxel-wise approaches with voxel-based morphometry and SIENAX using FSL. We used multiple linear regression models to test the influence of Li on cortical and local GM volumes, taking into account potential confounding factors such as a history of alcohol misuse. RESULTS: Patients taking Li had greater cortical GM volume than patients without. Patients undergoing Li had greater regional GM volumes in the right middle frontal gyrus, the right anterior cingulate gyrus, and the left fusiform gyrus in comparison with patients not taking Li. CONCLUSIONS: Our results in a large multicentric sample support the hypothesis that Li could exert neurotrophic and neuroprotective effects limiting pathological GM atrophy in key brain regions associated with BD.

Accumulation of Lithium in the Hippocampus of Patients With Bipolar Disorder: A Lithium-7 Magnetic Resonance Imaging Study at 7 Tesla.

BACKGROUND: Lithium (Li) is a first-line treatment for bipolar disorder (BD). To study its cerebral distribution and association with plasma concentrations, we used 7Li magnetic resonance imaging at 7T in euthymic patients with BD treated with Li carbonate for at least 2 years. METHODS: Three-dimensional 7Li magnetic resonance imaging scans (N = 21) were acquired with an ultra-short echo-time sequence using a non-Cartesian k-space sampling scheme. Lithium concentrations ([Li]) were estimated using a phantom replacement approach accounting for differential T1 and T2 relaxation effects. In addition to the determination of mean regional [Li] from 7 broad anatomical areas, voxel- and parcellation-based group analyses were conducted for the first time for 7Li magnetic resonance imaging. RESULTS: Using unprecedented spatial sensitivity and specificity, we were able to confirm the heterogeneity of the brain Li distribution and its interindividual variability, as well as the strong correlation between plasma and average brain [Li] ([Li]B ≈ 0.40 × [Li]P, R = .74). Remarkably, our statistical analysis led to the identification of a well-defined and significant cluster corresponding closely to the left hippocampus for which high Li content was displayed consistently across our cohort. CONCLUSIONS: This observation could be of interest considering 1) the major role of the hippocampus in emotion processing and regulation, 2) the consistent atrophy of the hippocampus in untreated patients with BD, and 3) the normalization effect of Li on gray matter volumes. This study paves the way for the elucidation of the relationship between Li cerebral distribution and its therapeutic response, notably in newly diagnosed patients with BD.

Neocortical morphometry in Huntington's disease: Indication of the coexistence of abnormal neurodevelopmental and neurodegenerative processes.

Huntington's disease (HD) is an inherited, autosomal dominant disorder that is characteristically thought of as a degenerative disorder. Despite cellular and molecular grounds suggesting HD could also impact normal development, there has been scarce systems-level data obtained from in vivo human studies supporting this hypothesis. Sulcus-specific morphometry analysis may help disentangle the contribution of coexisting neurodegenerative and neurodevelopmental processes, but such an approach has never been used in HD. Here, we investigated cortical sulcal depth, related to degenerative process, as well as cortical sulcal length, related to developmental process, in early-stage HD and age-matched healthy controls. This morphometric analysis revealed significant differences in the HD participants compared with the healthy controls bilaterally in the central and intra-parietal sulcus, but also in the left intermediate frontal sulcus and calcarine fissure. As the primary visual cortex is not connected to the striatum, the latter result adds to the increasing in vivo evidence for primary cortical degeneration in HD. Those sulcal measures that differed between HD and healthy populations were mainly atrophy-related, showing shallower sulci in HD. Conversely, the sulcal morphometry also revealed a crucial difference in the imprint of the Sylvian fissure that could not be related to loss of grey matter volume: an absence of asymmetry in the length of this fissure in HD. Strong asymmetry in that cortical region is typically observed in healthy development. As the formation of the Sylvian fissure appears early in utero, and marked asymmetry is specifically found in this area of the neocortex in newborns, this novel finding likely indicates the foetal timing of a disease-specific, genetic interplay with neurodevelopment.

Will machine learning applied to neuroimaging in bipolar disorder help the clinician? A critical review and methodological suggestions.

OBJECTIVES: The existence of anatomofunctional brain abnormalities in bipolar disorder (BD) is now well established by magnetic resonance imaging (MRI) studies. To create diagnostic and prognostic tools, as well as identifying biologically valid subtypes of BD, research has recently turned towards the use of machine learning (ML) techniques. We assessed both supervised ML and unsupervised ML studies in BD to evaluate their robustness, reproducibility and the potential need for improvement. METHOD: We systematically searched for studies using ML algorithms based on MRI data of patients with BD until February 2019. RESULT: We identified 47 studies, 45 using supervised ML techniques and 2 including unsupervised ML analyses. Among supervised studies, 43 focused on diagnostic classification. The reported accuracies for classification of BD ranged between (a) 57% and 100%, for BD vs healthy controls; (b) 49.5% and 93.1% for BD vs patients with major depressive disorder; and (c) 50% and 96.2% for BD vs patients with schizophrenia. Reported accuracies for discriminating subjects genetically at risk for BD (either from control or from patients with BD) ranged between 64.3% and 88.93%. CONCLUSIONS: Although there are strong methodological limitations in previous studies and an important need for replication in large multicentric samples, the conclusions of our review bring hope of future computer-aided diagnosis of BD and pave the way for other applications, such as treatment response prediction. To reinforce the reliability of future results we provide methodological suggestions for good practice in conducting and reporting MRI-based ML studies in BD.

Using structural MRI to identify bipolar disorders - 13 site machine learning study in 3020 individuals from the ENIGMA Bipolar Disorders Working Group.

Bipolar disorders (BDs) are among the leading causes of morbidity and disability. Objective biological markers, such as those based on brain imaging, could aid in clinical management of BD. Machine learning (ML) brings neuroimaging analyses to individual subject level and may potentially allow for their diagnostic use. However, fair and optimal application of ML requires large, multi-site datasets. We applied ML (support vector machines) to MRI data (regional cortical thickness, surface area, subcortical volumes) from 853 BD and 2167 control participants from 13 cohorts in the ENIGMA consortium. We attempted to differentiate BD from control participants, investigated different data handling strategies and studied the neuroimaging/clinical features most important for classification. Individual site accuracies ranged from 45.23% to 81.07%. Aggregate subject-level analyses yielded the highest accuracy (65.23%, 95% CI = 63.47-67.00, ROC-AUC = 71.49%, 95% CI = 69.39-73.59), followed by leave-one-site-out cross-validation (accuracy = 58.67%, 95% CI = 56.70-60.63). Meta-analysis of individual site accuracies did not provide above chance results. There was substantial agreement between the regions that contributed to identification of BD participants in the best performing site and in the aggregate dataset (Cohen's Kappa = 0.83, 95% CI = 0.829-0.831). Treatment with anticonvulsants and age were associated with greater odds of correct classification. Although short of the 80% clinically relevant accuracy threshold, the results are promising and provide a fair and realistic estimate of classification performance, which can be achieved in a large, ecologically valid, multi-site sample of BD participants based on regional neurostructural measures. Furthermore, the significant classification in different samples was based on plausible and similar neuroanatomical features. Future multi-site studies should move towards sharing of raw/voxelwise neuroimaging data.