Genomic loci influence patterns of structural covariance in the human brain.

Normal and pathologic neurobiological processes influence brain morphology in coordinated ways that give rise to patterns of structural covariance (PSC) across brain regions and individuals during brain aging and diseases. The genetic underpinnings of these patterns remain largely unknown. We apply a stochastic multivariate factorization method to a diverse population of 50,699 individuals (12 studies and 130 sites) and derive data-driven, multi-scale PSCs of regional brain size. PSCs were significantly correlated with 915 genomic loci in the discovery set, 617 of which are newly identified, and 72% were independently replicated. Key pathways influencing PSCs involve reelin signaling, apoptosis, neurogenesis, and appendage development, while pathways of breast cancer indicate potential interplays between brain metastasis and PSCs associated with neurodegeneration and dementia. Using support vector machines, multi-scale PSCs effectively derive imaging signatures of several brain diseases. Our results elucidate genetic and biological underpinnings that influence structural covariance patterns in the human brain.

Contribution of MRI for the Early Diagnosis of Parkinsonism in Patients with Diagnostic Uncertainty.

BACKGROUND: International clinical criteria are the reference for the diagnosis of degenerative parkinsonism in clinical research, but they may lack sensitivity and specificity in the early stages. OBJECTIVES: To determine whether magnetic resonance imaging (MRI) analysis, through visual reading or machine-learning approaches, improves diagnostic accuracy compared with clinical diagnosis at an early stage in patients referred for suspected degenerative parkinsonism. MATERIALS: Patients with initial diagnostic uncertainty between Parkinson's disease (PD), progressive supranuclear palsy (PSP), and multisystem atrophy (MSA), with brain MRI performed at the initial visit (V1) and available 2-year follow-up (V2), were included. We evaluated the accuracy of the diagnosis established based on: (1) the international clinical diagnostic criteria for PD, PSP, and MSA at V1 ("Clin1"); (2) MRI visual reading blinded to the clinical diagnosis ("MRI"); (3) both MRI visual reading and clinical criteria at V1 ("MRI and Clin1"), and (4) a machine-learning algorithm ("Algorithm"). The gold standard diagnosis was established by expert consensus after a 2-year follow-up. RESULTS: We recruited 113 patients (53 with PD, 31 with PSP, and 29 with MSA). Considering the whole population, compared with clinical criteria at the initial visit ("Clin1": balanced accuracy, 66.2%), MRI visual reading showed a diagnostic gain of 14.3% ("MRI": 80.5%; P = 0.01), increasing to 19.2% when combined with the clinical diagnosis at the initial visit ("MRI and Clin1": 85.4%; P < 0.0001). The algorithm achieved a diagnostic gain of 9.9% ("Algorithm": 76.1%; P = 0.08). CONCLUSION: Our study shows the use of MRI analysis, whether by visual reading or machine-learning methods, for early differentiation of parkinsonism. © 2024 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Contrast-enhanced to non-contrast-enhanced image translation to exploit a clinical data warehouse of T1-weighted brain MRI.

BACKGROUND: Clinical data warehouses provide access to massive amounts of medical images, but these images are often heterogeneous. They can for instance include images acquired both with or without the injection of a gadolinium-based contrast agent. Harmonizing such data sets is thus fundamental to guarantee unbiased results, for example when performing differential diagnosis. Furthermore, classical neuroimaging software tools for feature extraction are typically applied only to images without gadolinium. The objective of this work is to evaluate how image translation can be useful to exploit a highly heterogeneous data set containing both contrast-enhanced and non-contrast-enhanced images from a clinical data warehouse. METHODS: We propose and compare different 3D U-Net and conditional GAN models to convert contrast-enhanced T1-weighted (T1ce) into non-contrast-enhanced (T1nce) brain MRI. These models were trained using 230 image pairs and tested on 77 image pairs from the clinical data warehouse of the Greater Paris area. RESULTS: Validation using standard image similarity measures demonstrated that the similarity between real and synthetic T1nce images was higher than between real T1nce and T1ce images for all the models compared. The best performing models were further validated on a segmentation task. We showed that tissue volumes extracted from synthetic T1nce images were closer to those of real T1nce images than volumes extracted from T1ce images. CONCLUSION: We showed that deep learning models initially developed with research quality data could synthesize T1nce from T1ce images of clinical quality and that reliable features could be extracted from the synthetic images, thus demonstrating the ability of such methods to help exploit a data set coming from a clinical data warehouse.

Deep learning for brain disorders: from data processing to disease treatment.

In order to reach precision medicine and improve patients' quality of life, machine learning is increasingly used in medicine. Brain disorders are often complex and heterogeneous, and several modalities such as demographic, clinical, imaging, genetics and environmental data have been studied to improve their understanding. Deep learning, a subpart of machine learning, provides complex algorithms that can learn from such various data. It has become state of the art in numerous fields, including computer vision and natural language processing, and is also growingly applied in medicine. In this article, we review the use of deep learning for brain disorders. More specifically, we identify the main applications, the concerned disorders and the types of architectures and data used. Finally, we provide guidelines to bridge the gap between research studies and clinical routine.

Plasma microRNA signature in presymptomatic and symptomatic subjects with C9orf72-associated frontotemporal dementia and amyotrophic lateral sclerosis.

OBJECTIVE: To identify potential biomarkers of preclinical and clinical progression in chromosome 9 open reading frame 72 gene (C9orf72)-associated disease by assessing the expression levels of plasma microRNAs (miRNAs) in C9orf72 patients and presymptomatic carriers. METHODS: The PREV-DEMALS study is a prospective study including 22 C9orf72 patients, 45 presymptomatic C9orf72 mutation carriers and 43 controls. We assessed the expression levels of 2576 miRNAs, among which 589 were above noise level, in plasma samples of all participants using RNA sequencing. The expression levels of the differentially expressed miRNAs between patients, presymptomatic carriers and controls were further used to build logistic regression classifiers. RESULTS: Four miRNAs were differentially expressed between patients and controls: miR-34a-5p and miR-345-5p were overexpressed, while miR-200c-3p and miR-10a-3p were underexpressed in patients. MiR-34a-5p was also overexpressed in presymptomatic carriers compared with healthy controls, suggesting that miR-34a-5p expression is deregulated in cases with C9orf72 mutation. Moreover, miR-345-5p was also overexpressed in patients compared with presymptomatic carriers, which supports the correlation of miR-345-5p expression with the progression of C9orf72-associated disease. Together, miR-200c-3p and miR-10a-3p underexpression might be associated with full-blown disease. Four presymptomatic subjects in transitional/prodromal stage, close to the disease conversion, exhibited a stronger similarity with the expression levels of patients. CONCLUSIONS: We identified a signature of four miRNAs differentially expressed in plasma between clinical conditions that have potential to represent progression biomarkers for C9orf72-associated frontotemporal dementia and amyotrophic lateral sclerosis. This study suggests that dysregulation of miRNAs is dynamically altered throughout neurodegenerative diseases progression, and can be detectable even long before clinical onset. TRIAL REGISTRATION NUMBER: NCT02590276.

Plasma NfL levels and longitudinal change rates in C9orf72 and GRN-associated diseases: from tailored references to clinical applications.

OBJECTIVE: Neurofilament light chain (NfL) is a promising biomarker in genetic frontotemporal dementia (FTD) and amyotrophic lateral sclerosis (ALS). We evaluated plasma neurofilament light chain (pNfL) levels in controls, and their longitudinal trajectories in C9orf72 and GRN cohorts from presymptomatic to clinical stages. METHODS: We analysed pNfL using Single Molecule Array (SiMoA) in 668 samples (352 baseline and 316 follow-up) of C9orf72 and GRN patients, presymptomatic carriers (PS) and controls aged between 21 and 83. They were longitudinally evaluated over a period of >2 years, during which four PS became prodromal/symptomatic. Associations between pNfL and clinical-genetic variables, and longitudinal NfL changes, were investigated using generalised and linear mixed-effects models. Optimal cut-offs were determined using the Youden Index. RESULTS: pNfL levels increased with age in controls, from ~5 to~18 pg/mL (p<0.0001), progressing over time (mean annualised rate of change (ARC): +3.9%/year, p<0.0001). Patients displayed higher levels and greater longitudinal progression (ARC: +26.7%, p<0.0001), with gene-specific trajectories. GRN patients had higher levels than C9orf72 (86.21 vs 39.49 pg/mL, p=0.014), and greater progression rates (ARC:+29.3% vs +24.7%; p=0.016). In C9orf72 patients, levels were associated with the phenotype (ALS: 71.76 pg/mL, FTD: 37.16, psychiatric: 15.3; p=0.003) and remarkably lower in slowly progressive patients (24.11, ARC: +2.5%; p=0.05). Mean ARC was +3.2% in PS and +7.3% in prodromal carriers. We proposed gene-specific cut-offs differentiating patients from controls by decades. CONCLUSIONS: This study highlights the importance of gene-specific and age-specific references for clinical and therapeutic trials in genetic FTD/ALS. It supports the usefulness of repeating pNfL measurements and considering ARC as a prognostic marker of disease progression. TRIAL REGISTRATION NUMBERS: NCT02590276 and NCT04014673.

Automated Categorization of Parkinsonian Syndromes Using Magnetic Resonance Imaging in a Clinical Setting.

BACKGROUND: Machine learning algorithms using magnetic resonance imaging (MRI) data can accurately discriminate parkinsonian syndromes. Validation in patients recruited in routine clinical practice is missing. OBJECTIVE: The aim of this study was to assess the accuracy of a machine learning algorithm trained on a research cohort and tested on an independent clinical replication cohort for the categorization of parkinsonian syndromes. METHODS: Three hundred twenty-two subjects, including 94 healthy control subjects, 119 patients with Parkinson's disease (PD), 51 patients with progressive supranuclear palsy (PSP) with Richardson's syndrome, 35 with multiple system atrophy (MSA) of the parkinsonian variant (MSA-P), and 23 with MSA of the cerebellar variant (MSA-C), were recruited. They were divided into a training cohort (n = 179) scanned in a research environment and a replication cohort (n = 143) examined in clinical practice on different MRI systems. Volumes and diffusion tensor imaging (DTI) metrics in 13 brain regions were used as input for a supervised machine learning algorithm. To harmonize data across scanners and reduce scanner-dependent effects, we tested two types of normalizations using patient data or healthy control data. RESULTS: In the replication cohort, high accuracies were achieved using volumetry in the classification of PD-PSP, PD-MSA-C, PSP-MSA-C, and PD-atypical parkinsonism (balanced accuracies: 0.840-0.983, area under the receiver operating characteristic curves: 0.907-0.995). Performances were lower for the classification of PD-MSA-P, MSA-C-MSA-P (balanced accuracies: 0.765-0.784, area under the receiver operating characteristic curve: 0.839-0.871) and PD-PSP-MSA (balanced accuracies: 0.773). Performance using DTI was improved when normalizing by controls, but remained lower than that using volumetry alone or combined with DTI. CONCLUSIONS: A machine learning approach based on volumetry enabled accurate classification of subjects with early-stage parkinsonism, examined on different MRI systems, as part of their clinical assessment. © 2020 International Parkinson and Movement Disorder Society.

Radiological classification of dementia from anatomical MRI assisted by machine learning-derived maps.

BACKGROUND AND PURPOSE: Many artificial intelligence tools are currently being developed to assist diagnosis of dementia from magnetic resonance imaging (MRI). However, these tools have so far been difficult to integrate in the clinical routine workflow. In this work, we propose a new simple way to use them and assess their utility for improving diagnostic accuracy. MATERIALS AND METHODS: We studied 34 patients with early-onset Alzheimer's disease (EOAD), 49 with late-onset AD (LOAD), 39 with frontotemporal dementia (FTD) and 24 with depression from the pre-existing cohort CLIN-AD. Support vector machine (SVM) automatic classifiers using 3D T1 MRI were trained to distinguish: LOAD vs. Depression, FTD vs. LOAD, EOAD vs. Depression, EOAD vs. FTD. We extracted SVM weight maps, which are tridimensional representations of discriminant atrophy patterns used by the classifier to take its decisions and we printed posters of these maps. Four radiologists (2 senior neuroradiologists and 2 unspecialized junior radiologists) performed a visual classification of the 4 diagnostic pairs using 3D T1 MRI. Classifications were performed twice: first with standard radiological reading and then using SVM weight maps as a guide. RESULTS: Diagnostic performance was significantly improved by the use of the weight maps for the two junior radiologists in the case of FTD vs. EOAD. Improvement was over 10 points of diagnostic accuracy. CONCLUSION: This tool can improve the diagnostic accuracy of junior radiologists and could be integrated in the clinical routine workflow.

The White Matter Module-Hub Network of Semantics Revealed by Semantic Dementia.

Cognitive neuroscience exploring the architecture of semantics has shown that coherent supramodal concepts are computed in the anterior temporal lobes (ATL), but it is unknown how/where modular information implemented by posterior cortices (word/object/face forms) is conveyed to the ATL hub. We investigated the semantic module-hub network in healthy adults (n = 19) and in semantic dementia patients (n = 28) by combining semantic assessments of verbal and nonverbal stimuli and MRI-based fiber tracking using seeds in three module-related cortices implementing (i) written word forms (visual word form area), (ii) abstract lexical representations (posterior-superior temporal cortices), and (iii) face/object representations (face form area). Fiber tracking revealed three key tracts linking the ATL with the three module-related cortices. Correlation analyses between tract parameters and semantic scores indicated that the three tracts subserve semantics, transferring modular verbal or nonverbal object/face information to the left and right ATL, respectively. The module-hub tracts were functionally and microstructurally damaged in semantic dementia, whereas damage to non-module-specific ATL tracts (inferior longitudinal fasciculus, uncinate fasciculus) had more limited impact on semantic failure. These findings identify major components of the white matter module-hub network of semantics, and they corroborate/materialize claims of cognitive models positing direct links between modular and semantic representations. In combination with modular accounts of cognition, they also suggest that the currently prevailing "hub-and-spokes" model of semantics could be extended by incorporating an intermediate module level containing invariant representations, in addition to "spokes," which subserve the processing of a near-unlimited number of sensorimotor and speech-sound features.

Predicting PET-derived myelin content from multisequence MRI for individual longitudinal analysis in multiple sclerosis.

Multiple sclerosis (MS) is a demyelinating and inflammatory disease of the central nervous system (CNS). The demyelination process can be repaired by the generation of a new sheath of myelin around the axon, a process termed remyelination. In MS patients, the demyelination-remyelination cycles are highly dynamic. Over the years, magnetic resonance imaging (MRI) has been increasingly used in the diagnosis of MS and it is currently the most useful paraclinical tool to assess this diagnosis. However, conventional MRI pulse sequences are not specific for pathological mechanisms such as demyelination and remyelination. Recently, positron emission tomography (PET) with radiotracer [11C]PIB has become a promising tool to measure in-vivo myelin content changes which is essential to push forward our understanding of mechanisms involved in the pathology of MS, and to monitor individual patients in the context of clinical trials focused on repair therapies. However, PET imaging is invasive due to the injection of a radioactive tracer. Moreover, it is an expensive imaging test and not offered in the majority of medical centers in the world. In this work, by using multisequence MRI, we thus propose a method to predict the parametric map of [11C]PIB PET, from which we derived the myelin content changes in a longitudinal analysis of patients with MS. The method is based on the proposed conditional flexible self-attention GAN (CF-SAGAN) which is specifically adjusted for high-dimensional medical images and able to capture the relationships between the spatially separated lesional regions during the image synthesis process. Jointly applying the sketch-refinement process and the proposed attention regularization that focuses on the MS lesions, our approach is shown to outperform the state-of-the-art methods qualitatively and quantitatively. Specifically, our method demonstrated a superior performance for the prediction of myelin content at voxel-wise level. More important, our method for the prediction of myelin content changes in patients with MS shows similar clinical correlations to the PET-derived gold standard indicating the potential for clinical management of patients with MS.

Machine learning for classification and prediction of brain diseases: recent advances and upcoming challenges.

PURPOSE OF REVIEW: Machine learning is an artificial intelligence technique that allows computers to perform a task without being explicitly programmed. Machine learning can be used to assist diagnosis and prognosis of brain disorders. Although the earliest articles date from more than ten years ago, research increases at a very fast pace. RECENT FINDINGS: Recent works using machine learning for diagnosis have moved from classification of a given disease versus controls to differential diagnosis. Intense research has been devoted to the prediction of the future patient state. Although a lot of earlier works focused on neuroimaging as data source, the current trend is on the integration of multimodal data. In terms of targeted diseases, dementia remains dominant but approaches have been developed for a wide variety of neurological and psychiatric diseases. SUMMARY: Machine learning is extremely promising for assisting diagnosis and prognosis in brain disorders. Nevertheless, we argue that key challenges remain to be addressed by the community for bringing these tools in clinical routine: good practices regarding validation and reproducible research need to be more widely adopted; extensive generalization studies are required; interpretable models are needed to overcome the limitations of black-box approaches.

A unified framework for association and prediction from vertex-wise grey-matter structure.

The recent availability of large-scale neuroimaging cohorts facilitates deeper characterisation of the relationship between phenotypic and brain architecture variation in humans. Here, we investigate the association (previously coined morphometricity) of a phenotype with all 652,283 vertex-wise measures of cortical and subcortical morphology in a large data set from the UK Biobank (UKB; N = 9,497 for discovery, N = 4,323 for replication) and the Human Connectome Project (N = 1,110). We used a linear mixed model with the brain measures of individuals fitted as random effects with covariance relationships estimated from the imaging data. We tested 167 behavioural, cognitive, psychiatric or lifestyle phenotypes and found significant morphometricity for 58 phenotypes (spanning substance use, blood assay results, education or income level, diet, depression, and cognition domains), 23 of which replicated in the UKB replication set or the HCP. We then extended the model for a bivariate analysis to estimate grey-matter correlation between phenotypes, which revealed that body size (i.e., height, weight, BMI, waist and hip circumference, body fat percentage) could account for a substantial proportion of the morphometricity (confirmed using a conditional analysis), providing possible insight into previous MRI case-control results for psychiatric disorders where case status is associated with body mass index. Our LMM framework also allowed to predict some of the associated phenotypes from the vertex-wise measures, in two independent samples. Finally, we demonstrated additional new applications of our approach (a) region of interest (ROI) analysis that retain the vertex-wise complexity; (b) comparison of the information retained by different MRI processings.

Presymptomatic spinal cord pathology in c9orf72 mutation carriers: A longitudinal neuroimaging study.

OBJECTIVE: C9orf72 hexanucleotide repeats expansions account for almost half of familial amyotrophic lateral sclerosis (ALS) and frontotemporal dementia (FTD) cases. Recent imaging studies in asymptomatic C9orf72 carriers have demonstrated cerebral white (WM) and gray matter (GM) degeneration before the age of 40 years. The objective of this study was to characterize cervical spinal cord (SC) changes in asymptomatic C9orf72 hexanucleotide carriers. METHODS: Seventy-two asymptomatic individuals were enrolled in a prospective study of first-degree relatives of ALS and FTD patients carrying the c9orf72 hexanucleotide expansion. Forty of them carried the pathogenic mutation (C9+ ). Each subject underwent quantitative cervical cord imaging. Structural GM and WM metrics and diffusivity parameters were evaluated at baseline and 18 months later. Data were analyzed in C9+ and C9- subgroups, and C9+ subjects were further stratified by age. RESULTS: At baseline, significant WM atrophy was detected at each cervical vertebral level in C9+ subjects older than 40 years without associated changes in GM and diffusion tensor imaging parameters. At 18-month follow-up, WM atrophy was accompanied by significant corticospinal tract (CST) fractional anisotropy (FA) reductions. Intriguingly, asymptomatic C9+ subjects older than 40 years with family history of ALS (as opposed to FTD) also exhibited significant CST FA reduction at baseline. INTERPRETATION: Cervical SC imaging detects WM atrophy exclusively in C9+ subjects older than 40 years, and progressive CST FA reductions can be identified on 18-month follow-up. Cervical SC magnetic resonance imaging readily captures presymptomatic pathological changes and disease propagation in c9orf72-associated conditions. ANN NEUROL 2019;86:158-167.

Cognitive inhibition impairments in presymptomatic C9orf72 carriers.

OBJECTIVE: To investigate cognitive inhibition in presymptomatic C9orf72 mutation carriers (C9+) and its associated neuroanatomical correlates. METHODS: Thirty-eight presymptomatic C9orf72 mutation carriers (C9+, mean age 38.2±8.0 years) and 22 C9- controls from the PREV-DEMALS cohort were included in this study. They underwent a cognitive inhibition assessment with the Hayling Sentence Completion Test (HSCT; time to completion (part B-part A); error score in part B) as well as a 3D MRI. RESULTS: C9+ individuals younger than 40 years had higher error scores (part B) but equivalent HSCT time to completion (part B-part A) compared to C9- individuals. C9+ individuals older than 40 years had both higher error scores and longer time to completion. HSCT time to completion significantly predicted the proximity to estimated clinical conversion from presymptomatic to symptomatic phase in C9+ individuals (based on the average age at onset of affected relatives in the family). Anatomically, we found that HSCT time to completion was associated with the integrity of the cerebellum. CONCLUSION: The HSCT represents a good marker of cognitive inhibition impairments in C9+ and of proximity to clinical conversion. This study also highlights the key role of the cerebellum in cognitive inhibition.

Neurite density is reduced in the presymptomatic phase of C9orf72 disease.

OBJECTIVE: To assess the added value of neurite orientation dispersion and density imaging (NODDI) compared with conventional diffusion tensor imaging (DTI) and anatomical MRI to detect changes in presymptomatic carriers of chromosome 9 open reading frame 72 (C9orf72) mutation. METHODS: The PREV-DEMALS (Predict to Prevent Frontotemporal Lobar Degeneration and Amyotrophic Lateral Sclerosis) study is a prospective, multicentre, observational study of first-degree relatives of individuals carrying the C9orf72 mutation. Sixty-seven participants (38 presymptomatic C9orf72 mutation carriers (C9+) and 29 non-carriers (C9-)) were included in the present cross-sectional study. Each participant underwent one single-shell, multishell diffusion MRI and three-dimensional T1-weighted MRI. Volumetric measures, DTI and NODDI metrics were calculated within regions of interest. Differences in white matter integrity, grey matter volume and free water fraction between C9+ and C9- individuals were assessed using linear mixed-effects models. RESULTS: Compared with C9-, C9+ demonstrated white matter abnormalities in 10 tracts with neurite density index and only 5 tracts with DTI metrics. Effect size was significantly higher for the neurite density index than for DTI metrics in two tracts. No tract had a significantly higher effect size for DTI than for NODDI. For grey matter cortical analysis, free water fraction was increased in 13 regions in C9+, whereas 11 regions displayed volumetric atrophy. CONCLUSIONS: NODDI provides higher sensitivity and greater tissue specificity compared with conventional DTI for identifying white matter abnormalities in the presymptomatic C9orf72 carriers. Our results encourage the use of neurite density as a biomarker of the preclinical phase. TRIAL REGISTRATION NUMBER: NCT02590276.

Multi-modal brain fingerprinting: A manifold approximation based framework.

This work presents an efficient framework, based on manifold approximation, for generating brain fingerprints from multi-modal data. The proposed framework represents images as bags of local features which are used to build a subject proximity graph. Compact fingerprints are obtained by projecting this graph in a low-dimensional manifold using spectral embedding. Experiments using the T1/T2-weighted MRI, diffusion MRI, and resting-state fMRI data of 945 Human Connectome Project subjects demonstrate the benefit of combining multiple modalities, with multi-modal fingerprints more discriminative than those generated from individual modalities. Results also highlight the link between fingerprint similarity and genetic proximity, monozygotic twins having more similar fingerprints than dizygotic or non-twin siblings. This link is also reflected in the differences of feature correspondences between twin/sibling pairs, occurring in major brain structures and across hemispheres. The robustness of the proposed framework to factors like image alignment and scan resolution, as well as the reproducibility of results on retest scans, suggest the potential of multi-modal brain fingerprinting for characterizing individuals in a large cohort analysis.

Reproducible evaluation of classification methods in Alzheimer's disease: Framework and application to MRI and PET data.

A large number of papers have introduced novel machine learning and feature extraction methods for automatic classification of Alzheimer's disease (AD). However, while the vast majority of these works use the public dataset ADNI for evaluation, they are difficult to reproduce because different key components of the validation are often not readily available. These components include selected participants and input data, image preprocessing and cross-validation procedures. The performance of the different approaches is also difficult to compare objectively. In particular, it is often difficult to assess which part of the method (e.g. preprocessing, feature extraction or classification algorithms) provides a real improvement, if any. In the present paper, we propose a framework for reproducible and objective classification experiments in AD using three publicly available datasets (ADNI, AIBL and OASIS). The framework comprises: i) automatic conversion of the three datasets into a standard format (BIDS); ii) a modular set of preprocessing pipelines, feature extraction and classification methods, together with an evaluation framework, that provide a baseline for benchmarking the different components. We demonstrate the use of the framework for a large-scale evaluation on 1960 participants using T1 MRI and FDG PET data. In this evaluation, we assess the influence of different modalities, preprocessing, feature types (regional or voxel-based features), classifiers, training set sizes and datasets. Performances were in line with the state-of-the-art. FDG PET outperformed T1 MRI for all classification tasks. No difference in performance was found for the use of different atlases, image smoothing, partial volume correction of FDG PET images, or feature type. Linear SVM and L2-logistic regression resulted in similar performance and both outperformed random forests. The classification performance increased along with the number of subjects used for training. Classifiers trained on ADNI generalized well to AIBL and OASIS. All the code of the framework and the experiments is publicly available: general-purpose tools have been integrated into the Clinica software (www.clinica.run) and the paper-specific code is available at: https://gitlab.icm-institute.org/aramislab/AD-ML.

Fiberprint: A subject fingerprint based on sparse code pooling for white matter fiber analysis.

White matter characterization studies use the information provided by diffusion magnetic resonance imaging (dMRI) to draw cross-population inferences. However, the structure, function, and white matter geometry vary across individuals. Here, we propose a subject fingerprint, called Fiberprint, to quantify the individual uniqueness in white matter geometry using fiber trajectories. We learn a sparse coding representation for fiber trajectories by mapping them to a common space defined by a dictionary. A subject fingerprint is then generated by applying a pooling function for each bundle, thus providing a vector of bundle-wise features describing a particular subject's white matter geometry. These features encode unique properties of fiber trajectories, such as their density along prominent bundles. An analysis of data from 861 Human Connectome Project subjects reveals that a fingerprint based on approximately 3000 fiber trajectories can uniquely identify exemplars from the same individual. We also use fingerprints for twin/sibling identification, our observations consistent with the twin data studies of white matter integrity. Our results demonstrate that the proposed Fiberprint can effectively capture the variability in white matter fiber geometry across individuals, using a compact feature vector (dimension of 50), making this framework particularly attractive for handling large datasets.

Early and protective microglial activation in Alzheimer's disease: a prospective study using 18F-DPA-714 PET imaging.

While emerging evidence suggests that neuroinflammation plays a crucial role in Alzheimer's disease, the impact of the microglia response in Alzheimer's disease remains a matter of debate. We aimed to study microglial activation in early Alzheimer's disease and its impact on clinical progression using a second-generation 18-kDa translocator protein positron emission tomography radiotracer together with amyloid imaging using Pittsburgh compound B positron emission tomography. We enrolled 96 subjects, 64 patients with Alzheimer's disease and 32 controls, from the IMABio3 study, who had both (11)C-Pittsburgh compound B and (18)F-DPA-714 positron emission tomography imaging. Patients with Alzheimer's disease were classified as prodromal Alzheimer's disease (n = 38) and Alzheimer's disease dementia (n = 26). Translocator protein-binding was measured using a simple ratio method with cerebellar grey matter as reference tissue, taking into account regional atrophy. Images were analysed at the regional (volume of interest) and at the voxel level. Translocator protein genotyping allowed the classification of all subjects in high, mixed and low affinity binders. Thirty high+mixed affinity binders patients with Alzheimer's disease were dichotomized into slow decliners (n = 10) or fast decliners (n = 20) after 2 years of follow-up. All patients with Alzheimer's disease had an amyloid positive Pittsburgh compound B positron emission tomography. Among controls, eight had positive amyloid scans (n = 6 high+mixed affinity binders), defined as amyloidosis controls, and were analysed separately. By both volumes of interest and voxel-wise comparison, 18-kDa translocator protein-binding was higher in high affinity binders, mixed affinity binders and high+mixed affinity binders Alzheimer's disease groups compared to controls, especially at the prodromal stage, involving the temporo-parietal cortex. Translocator protein-binding was positively correlated with Mini-Mental State Examination scores and grey matter volume, as well as with Pittsburgh compound B binding. Amyloidosis controls displayed higher translocator protein-binding than controls, especially in the frontal cortex. We found higher translocator protein-binding in slow decliners than fast decliners, with no difference in Pittsburgh compound B binding. Microglial activation appears at the prodromal and possibly at the preclinical stage of Alzheimer's disease, and seems to play a protective role in the clinical progression of the disease at these early stages. The extent of microglial activation appears to differ between patients, and could explain the overlap in translocator protein binding values between patients with Alzheimer's disease and amyloidosis controls.

Early life adversity is associated with a smaller hippocampus in male but not female depressed in-patients: a case-control study.

BACKGROUND: Three studies assessed the association of early life adversity (ELA) and hippocampal volumes in depressed patients, of which one was negative and the two others did not control for several potential confounding variables. Since the association of ELA and hippocampal volumes differ in male and female healthy volunteers, we investigated the association of ELA and hippocampal volumes in depressed patients, while focusing specifically on sex and controlling for several relevant socio-demographic and clinical variables. METHODS: Sixty-three depressed in-patients treated in a psychiatric setting, with a current Major Depressive Episode (MDE) and a Major Depressive Disorder (MDD) were included and assessed for ELA. Hippocampal volumes were measured with brain magnetic resonance imaging (MRI) and automatic segmentation. They were compared between patients with (n = 28) or without (n = 35) ELA. After bivariate analyses, multivariate regression analyses tested the interaction of sex and ELA on hippocampal volume and were adjusted for several potential confounding variables. The subgroups of men (n = 26) and women (n = 37) were assessed separately. RESULTS: Patients with ELA had a smaller hippocampus than those without ELA (4.65 (±1.11) cm3 versus 5.25 (±1.01) cm3), bivariate: p = 0.03, multivariate: HR = 0.40, 95%CI [0.23;0.71], p = 0.002), independently from other factors. This association was found in men (4.43 (±1.22) versus 5.67 (±0.77) cm3), bivariate: p = 0.006, multivariate HR = 0.23, 95%CI [0.06;0.82], p = 0.03) but not in women. CONCLUSION: ELA is associated with a smaller hippocampus in male but not female depressed in-patients. The reasons for this association should be investigated in further studies.