Multiomics analysis to explore blood metabolite biomarkers in an Alzheimer's Disease Neuroimaging Initiative cohort.

Alzheimer's disease (AD) is a neurodegenerative disease that commonly causes dementia. Identifying biomarkers for the early detection of AD is an emerging need, as brain dysfunction begins two decades before the onset of clinical symptoms. To this end, we reanalyzed untargeted metabolomic mass spectrometry data from 905 patients enrolled in the AD Neuroimaging Initiative (ADNI) cohort using MS-DIAL, with 1,304,633 spectra of 39,108 unique biomolecules. Metabolic profiles of 93 hydrophilic metabolites were determined. Additionally, we integrated targeted lipidomic data (4873 samples from 1524 patients) to explore candidate biomarkers for predicting progressive mild cognitive impairment (pMCI) in patients diagnosed with AD within two years using the baseline metabolome. Patients with lower ergothioneine levels had a 12% higher rate of AD progression with the significance of P = 0.012 (Wald test). Furthermore, an increase in ganglioside (GM3) and decrease in plasmalogen lipids, many of which are associated with apolipoprotein E polymorphism, were confirmed in AD patients, and the higher levels of lysophosphatidylcholine (18:1) and GM3 d18:1/20:0 showed 19% and 17% higher rates of AD progression, respectively (Wald test: P = 3.9 × 10-8 and 4.3 × 10-7). Palmitoleamide, oleamide, diacylglycerols, and ether lipids were also identified as significantly altered metabolites at baseline in patients with pMCI. The integrated analysis of metabolites and genomics data showed that combining information on metabolites and genotypes enhances the predictive performance of AD progression, suggesting that metabolomics is essential to complement genomic data. In conclusion, the reanalysis of multiomics data provides new insights to detect early development of AD pathology and to partially understand metabolic changes in age-related onset of AD.

A bilateral filtering-based image enhancement for Alzheimer disease classification using CNN.

This study aims to develop an optimally performing convolutional neural network to classify Alzheimer's disease into mild cognitive impairment, normal controls, or Alzheimer's disease classes using a magnetic resonance imaging dataset. To achieve this, we focused the study on addressing the challenge of image noise, which impacts the performance of deep learning models. The study introduced a scheme for enhancing images to improve the quality of the datasets. Specifically, an image enhancement algorithm based on histogram equalization and bilateral filtering techniques was deployed to reduce noise and enhance the quality of the images. Subsequently, a convolutional neural network model comprising four convolutional layers and two hidden layers was devised for classifying Alzheimer's disease into three (3) distinct categories, namely mild cognitive impairment, Alzheimer's disease, and normal controls. The model was trained and evaluated using a 10-fold cross-validation sampling approach with a learning rate of 0.001 and 200 training epochs at each instance. The proposed model yielded notable results, such as an accuracy of 93.45% and an area under the curve value of 0.99 when trained on the three classes. The model further showed superior results on binary classification compared with existing methods. The model recorded 94.39%, 94.92%, and 95.62% accuracies for Alzheimer's disease versus normal controls, Alzheimer's disease versus mild cognitive impairment, and mild cognitive impairment versus normal controls classes, respectively.

Computational limits to the legibility of the imaged human brain.

Our knowledge of the organisation of the human brain at the population-level is yet to translate into power to predict functional differences at the individual-level, limiting clinical applications and casting doubt on the generalisability of inferred mechanisms. It remains unknown whether the difficulty arises from the absence of individuating biological patterns within the brain, or from limited power to access them with the models and compute at our disposal. Here we comprehensively investigate the resolvability of such patterns with data and compute at unprecedented scale. Across 23 810 unique participants from UK Biobank, we systematically evaluate the predictability of 25 individual biological characteristics, from all available combinations of structural and functional neuroimaging data. Over 4526 GPU*hours of computation, we train, optimize, and evaluate out-of-sample 700 individual predictive models, including fully-connected feed-forward neural networks of demographic, psychological, serological, chronic disease, and functional connectivity characteristics, and both uni- and multi-modal 3D convolutional neural network models of macro- and micro-structural brain imaging. We find a marked discrepancy between the high predictability of sex (balanced accuracy 99.7%), age (mean absolute error 2.048 years, R2 0.859), and weight (mean absolute error 2.609Kg, R2 0.625), for which we set new state-of-the-art performance, and the surprisingly low predictability of other characteristics. Neither structural nor functional imaging predicted an individual's psychology better than the coincidence of common chronic disease (p < 0.05). Serology predicted chronic disease (p < 0.05) and was best predicted by it (p < 0.001), followed by structural neuroimaging (p < 0.05). Our findings suggest either more informative imaging or more powerful models will be needed to decipher individual level characteristics from the human brain. We make our models and code openly available.

A Multiscale Closed-Loop Neurotoxicity Model of Alzheimer's Disease Progression Explains Functional Connectivity Alterations.

The accumulation of amyloid-ß (Aß) and hyperphosphorylated-tau (hp-tau) are two classical histopathological biomarkers in Alzheimer's disease (AD). However, their detailed interactions with the electrophysiological changes at the meso- and macroscale are not yet fully understood. We developed a mechanistic multiscale model of AD progression, linking proteinopathy to its effects on neural activity and vice-versa. We integrated a heterodimer model of prion-like protein propagation and a brain network model of Jansen-Rit neural masses derived from human neuroimaging data whose parameters varied due to neurotoxicity. Results showed that changes in inhibition guided the electrophysiological alterations found in AD, and these changes were mainly attributed to Aß effects. Additionally, we found a causal disconnection between cellular hyperactivity and interregional hypersynchrony contrary to previous beliefs. Finally, we demonstrated that early Aß and hp-tau depositions' location determine the spatiotemporal profile of the proteinopathy. The presented model combines the molecular effects of both Aß and hp-tau together with a mechanistic protein propagation model and network effects within a closed-loop model. This holds the potential to enlighten the interplay between AD mechanisms on various scales, aiming to develop and test novel hypotheses on the contribution of different AD-related variables to the disease evolution.

ANTsX neuroimaging-derived structural phenotypes of UK Biobank.

UK Biobank is a large-scale epidemiological resource for investigating prospective correlations between various lifestyle, environmental, and genetic factors with health and disease progression. In addition to individual subject information obtained through surveys and physical examinations, a comprehensive neuroimaging battery consisting of multiple modalities provides imaging-derived phenotypes (IDPs) that can serve as biomarkers in neuroscience research. In this study, we augment the existing set of UK Biobank neuroimaging structural IDPs, obtained from well-established software libraries such as FSL and FreeSurfer, with related measurements acquired through the Advanced Normalization Tools Ecosystem. This includes previously established cortical and subcortical measurements defined, in part, based on the Desikan-Killiany-Tourville atlas. Also included are morphological measurements from two recent developments: medial temporal lobe parcellation of hippocampal and extra-hippocampal regions in addition to cerebellum parcellation and thickness based on the Schmahmann anatomical labeling. Through predictive modeling, we assess the clinical utility of these IDP measurements, individually and in combination, using commonly studied phenotypic correlates including age, fluid intelligence, numeric memory, and several other sociodemographic variables. The predictive accuracy of these IDP-based models, in terms of root-mean-squared-error or area-under-the-curve for continuous and categorical variables, respectively, provides comparative insights between software libraries as well as potential clinical interpretability. Results demonstrate varied performance between package-based IDP sets and their combination, emphasizing the need for careful consideration in their selection and utilization.

Sparse Deep Neural Network for Encoding and Decoding the Structural Connectome.

Brain state classification by applying deep learning techniques on neuroimaging data has become a recent topic of research. However, unlike domains where the data is low dimensional or there are large number of available training samples, neuroimaging data is high dimensional and has few training samples. To tackle these issues, we present a sparse feedforward deep neural architecture for encoding and decoding the structural connectome of the human brain. We use a sparsely connected element-wise multiplication as the first hidden layer and a fixed transform layer as the output layer. The number of trainable parameters and the training time is significantly reduced compared to feedforward networks. We demonstrate superior performance of this architecture in encoding the structural connectome implicated in Alzheimer's disease (AD) and Parkinson's disease (PD) from DTI brain scans. For decoding, we propose recursive feature elimination (RFE) algorithm based on DeepLIFT, layer-wise relevance propagation (LRP), and Integrated Gradients (IG) algorithms to remove irrelevant features and thereby identify key biomarkers associated with AD and PD. We show that the proposed architecture reduces 45.1% and 47.1% of the trainable parameters compared to a feedforward DNN with an increase in accuracy by 2.6 % and 3.1% for cognitively normal (CN) vs AD and CN vs PD classification, respectively. We also show that the proposed RFE method leads to a further increase in accuracy by 2.1% and 4% for CN vs AD and CN vs PD classification, while removing approximately 90% to 95% irrelevant features. Furthermore, we argue that the biomarkers (i.e., key brain regions and connections) identified are consistent with previous literature. We show that relevancy score-based methods can yield high discriminative power and are suitable for brain decoding. We also show that the proposed approach led to a reduction in the number of trainable network parameters, an increase in classification accuracy, and a detection of brain connections and regions that were consistent with earlier studies.

Comprehensive analysis of synthetic learning applied to neonatal brain MRI segmentation.

Brain segmentation from neonatal MRI images is a very challenging task due to large changes in the shape of cerebral structures and variations in signal intensities reflecting the gestational process. In this context, there is a clear need for segmentation techniques that are robust to variations in image contrast and to the spatial configuration of anatomical structures. In this work, we evaluate the potential of synthetic learning, a contrast-independent model trained using synthetic images generated from the ground truth labels of very few subjects. We base our experiments on the dataset released by the developmental Human Connectome Project, for which high-quality images are available for more than 700 babies aged between 26 and 45 weeks postconception. First, we confirm the impressive performance of a standard UNet trained on a few volumes, but also confirm that such models learn intensity-related features specific to the training domain. We then confirm the robustness of the synthetic learning approach to variations in image contrast. However, we observe a clear influence of the age of the baby on the predictions. We improve the performance of this model by enriching the synthetic training set with realistic motion artifacts and over-segmentation of the white matter. Based on extensive visual assessment, we argue that the better performance of the model trained on real T2w data may be due to systematic errors in the ground truth. We propose an original experiment allowing us to show that learning from real data will reproduce any systematic bias affecting the training set, while synthetic models can avoid this limitation. Overall, our experiments confirm that synthetic learning is an effective solution for segmenting neonatal brain MRI. Our adapted synthetic learning approach combines key features that will be instrumental for large multisite studies and clinical applications.

Cellular data extraction from multiplexed brain imaging data using self-supervised Dual-loss Adaptive Masked Autoencoder.

Reliable large-scale cell detection and segmentation is the fundamental first step to understanding biological processes in the brain. The ability to phenotype cells at scale can accelerate preclinical drug evaluation and system-level brain histology studies. The impressive advances in deep learning offer a practical solution to cell image detection and segmentation. Unfortunately, categorizing cells and delineating their boundaries for training deep networks is an expensive process that requires skilled biologists. This paper presents a novel self-supervised Dual-Loss Adaptive Masked Autoencoder (DAMA) for learning rich features from multiplexed immunofluorescence brain images. DAMA's objective function minimizes the conditional entropy in pixel-level reconstruction and feature-level regression. Unlike existing self-supervised learning methods based on a random image masking strategy, DAMA employs a novel adaptive mask sampling strategy to maximize mutual information and effectively learn brain cell data. To the best of our knowledge, this is the first effort to develop a self-supervised learning method for multiplexed immunofluorescence brain images. Our extensive experiments demonstrate that DAMA features enable superior cell detection, segmentation, and classification performance without requiring many annotations. In addition, to examine the generalizability of DAMA, we also experimented on TissueNet, a multiplexed imaging dataset comprised of two-channel fluorescence images from six distinct tissue types, captured using six different imaging platforms. Our code is publicly available at https://github.com/hula-ai/DAMA.

Exploring morphological similarity and randomness in Alzheimer's disease using adjacent grey matter voxel-based structural analysis.

BACKGROUND: Alzheimer's disease is characterized by large-scale structural changes in a specific pattern. Recent studies developed morphological similarity networks constructed by brain regions similar in structural features to represent brain structural organization. However, few studies have used local morphological properties to explore inter-regional structural similarity in Alzheimer's disease. METHODS: Here, we sourced T1-weighted MRI images of 342 cognitively normal participants and 276 individuals with Alzheimer's disease from the Alzheimer's Disease Neuroimaging Initiative database. The relationships of grey matter intensity between adjacent voxels were defined and converted to the structural pattern indices. We conducted the information-based similarity method to evaluate the structural similarity of structural pattern organization between brain regions. Besides, we examined the structural randomness on brain regions. Finally, the relationship between the structural randomness and cognitive performance of individuals with Alzheimer's disease was assessed by stepwise regression. RESULTS: Compared to cognitively normal participants, individuals with Alzheimer's disease showed significant structural pattern changes in the bilateral posterior cingulate gyrus, hippocampus, and olfactory cortex. Additionally, individuals with Alzheimer's disease showed that the bilateral insula had decreased inter-regional structural similarity with frontal regions, while the bilateral hippocampus had increased inter-regional structural similarity with temporal and subcortical regions. For the structural randomness, we found significant decreases in the temporal and subcortical areas and significant increases in the occipital and frontal regions. The regression analysis showed that the structural randomness of five brain regions was correlated with the Mini-Mental State Examination scores of individuals with Alzheimer's disease. CONCLUSIONS: Our study suggested that individuals with Alzheimer's disease alter micro-structural patterns and morphological similarity with the insula and hippocampus. Structural randomness of individuals with Alzheimer's disease changed in temporal, frontal, and occipital brain regions. Morphological similarity and randomness provide valuable insight into brain structural organization in Alzheimer's disease.

Development and Characterization of a Novel Carbon-11 Labeled Positron Emission Tomography Radiotracer for Neuroimaging of Sirtuin 1 with Benzoxazine-Based Compounds.

Introduction: Sirtuins (SIRTs) comprise a group of histone deacetylase enzymes crucial for regulating metabolic pathways and contributing significantly to various disease mechanisms. Sirtuin 1 (SIRT1), among the seven known mammalian homologs, is extensively investigated and understood, playing a key role in neurodegenerative disorders and cancer. This study focuses on potential as a therapeutic target for conditions such as Parkinson's disease (PD), Huntington's disease (HD), and Alzheimer's disease (AD). Methods: Utilizing positron emission tomography (PET) as a noninvasive molecular imaging modality, we aimed to expedite the validation of a promising sirtuin 1 inhibitor for clinical trials. However, the absence of a validated sirtuin 1 PET radiotracer impedes clinical translation. We present the development of [11C]1, and 11C-labeled benzoxazine-based derivative, as a lead imaging probe. The radiosynthesis of [11C]1 resulted in a radiochemical yield of 31 ± 4%. Results: Baseline studies demonstrated that [11C]1 exhibited excellent blood-brain barrier (BBB) penetration capability, with uniform accumulation throughout various brain regions. Self-blocking studies revealed that introducing an unlabeled compound 1, effectively blocking sirtuin 1, led to a substantial reduction in whole-brain uptake, emphasizing the in vivo specificity of [11C]1 for sirtuin 1. Discussion: The development of [11C]1 provides a valuable tool for noninvasive imaging investigations in rodent models with aberrant sirtuin 1 expression. This novel radiotracer holds promise for advancing our understanding of sirtuin 1's role in disease mechanisms and may facilitate the validation of sirtuin 1 inhibitors in clinical trials.

An Analysis of Loss Functions for Heavily Imbalanced Lesion Segmentation.

Heavily imbalanced datasets are common in lesion segmentation. Specifically, the lesions usually comprise less than 5% of the whole image volume when dealing with brain MRI. A common solution when training with a limited dataset is the use of specific loss functions that rebalance the effect of background and foreground voxels. These approaches are usually evaluated running a single cross-validation split without taking into account other possible random aspects that might affect the true improvement of the final metric (i.e., random weight initialisation or random shuffling). Furthermore, the evolution of the effect of the loss on the heavily imbalanced class is usually not analysed during the training phase. In this work, we present an analysis of different common loss metrics during training on public datasets dealing with brain lesion segmentation in heavy imbalanced datasets. In order to limit the effect of hyperparameter tuning and architecture, we chose a 3D Unet architecture due to its ability to provide good performance on different segmentation applications. We evaluated this framework on two public datasets and we observed that weighted losses have a similar performance on average, even though heavily weighting the gradient of the foreground class gives better performance in terms of true positive segmentation.

Natural Fat Nanoemulsions for Enhanced Optical Coherence Tomography Neuroimaging and Tumor Imaging in the Second Near-Infrared Window.

Optical coherence tomography (OCT) imaging mainly uses backscattered light to visualize the structural and functional information on biological tissues. In particular, OCT angiography can not only map the capillary networks but also capture the blood flow in the tissue microenvironment, making it a good candidate for neuroimaging and tumor imaging in vivo and in real time. To further improve the detection accuracy of cancer or brain disorders, it is essential to develop a natural and nontoxic contrast agent for enhanced OCT imaging in the second near-infrared (NIR-II) window. In this study, a superior biocompatible and highly scattering NIR-II fat nanoemulsion was constructed to improve OCT imaging contrast and depth for monitoring the vascular network changes of the cerebral cortex or tumor. In vivo experimental results demonstrated that a natural fat nanoemulsion can serve as an excellent probe for enhanced OCT neuroimaging and tumor imaging.

Brain MR image simulation for deep learning based medical image analysis networks.

BACKGROUND AND OBJECTIVE: As large sets of annotated MRI data are needed for training and validating deep learning based medical image analysis algorithms, the lack of sufficient annotated data is a critical problem. A possible solution is the generation of artificial data by means of physics-based simulations. Existing brain simulation data is limited in terms of anatomical models, tissue classes, fixed tissue characteristics, MR sequences and overall realism. METHODS: We propose a realistic simulation framework by incorporating patient-specific phantoms and Bloch equations-based analytical solutions for fast and accurate MRI simulations. A large number of labels are derived from open-source high-resolution T1w MRI data using a fully automated brain classification tool. The brain labels are taken as ground truth (GT) on which MR images are simulated using our framework. Moreover, we demonstrate that the T1w MR images generated from our framework along with GT annotations can be utilized directly to train a 3D brain segmentation network. To evaluate our model further on larger set of real multi-source MRI data without GT, we compared our model to existing brain segmentation tools, FSL-FAST and SynthSeg. RESULTS: Our framework generates 3D brain MRI for variable anatomy, sequence, contrast, SNR and resolution. The brain segmentation network for WM/GM/CSF trained only on T1w simulated data shows promising results on real MRI data from MRBrainS18 challenge dataset with a Dice scores of 0.818/0.832/0.828. On OASIS data, our model exhibits a close performance to FSL, both qualitatively and quantitatively with a Dice scores of 0.901/0.939/0.937. CONCLUSIONS: Our proposed simulation framework is the initial step towards achieving truly physics-based MRI image generation, providing flexibility to generate large sets of variable MRI data for desired anatomy, sequence, contrast, SNR, and resolution. Furthermore, the generated images can effectively train 3D brain segmentation networks, mitigating the reliance on real 3D annotated data.

SUGAR: Spherical ultrafast graph attention framework for cortical surface registration.

Cortical surface registration plays a crucial role in aligning cortical functional and anatomical features across individuals. However, conventional registration algorithms are computationally inefficient. Recently, learning-based registration algorithms have emerged as a promising solution, significantly improving processing efficiency. Nonetheless, there remains a gap in the development of a learning-based method that exceeds the state-of-the-art conventional methods simultaneously in computational efficiency, registration accuracy, and distortion control, despite the theoretically greater representational capabilities of deep learning approaches. To address the challenge, we present SUGAR, a unified unsupervised deep-learning framework for both rigid and non-rigid registration. SUGAR incorporates a U-Net-based spherical graph attention network and leverages the Euler angle representation for deformation. In addition to the similarity loss, we introduce fold and multiple distortion losses to preserve topology and minimize various types of distortions. Furthermore, we propose a data augmentation strategy specifically tailored for spherical surface registration to enhance the registration performance. Through extensive evaluation involving over 10,000 scans from 7 diverse datasets, we showed that our framework exhibits comparable or superior registration performance in accuracy, distortion, and test-retest reliability compared to conventional and learning-based methods. Additionally, SUGAR achieves remarkable sub-second processing times, offering a notable speed-up of approximately 12,000 times in registering 9,000 subjects from the UK Biobank dataset in just 32 min. This combination of high registration performance and accelerated processing time may greatly benefit large-scale neuroimaging studies.

Enhancing Diagnostic Accuracy Through Neuroimaging Revisions in Pediatric Pseudotumor Cerebri Syndrome: A Cross-Sectional Study.

BACKGROUND: This cross-sectional study aimed to report all neuroimaging findings suggestive of raised intracranial pressure in children with pseudotumor cerebri syndrome (PTCS), before and after re-review by two neuroradiologists. METHODS: We included 48 children aged <18 years diagnosed with PTCS between 2016 and 2021. Clinical and radiological data were obtained from their medical files. Two neuroradiologists independently re-reviewed all neuroimages, and the average of their assessments was compared with the initial neuroimaging reports; an additional review was done to analyze inter- and intraclass correlation. RESULTS: The initial neuroimaging reports showed under-reporting of findings, with only 26 of 48 (54.1%) patients identified with abnormal reports. After revision, the proportion of the reported findings increased to 44 of 48 (91.6%). Distention of the perioptic space was the most commonly reported finding after revision (36.5 of 48; 76%). Flattening of the posterior globe and empty sella were initially under-reported but improved after revision. Moreover, several findings suggestive of increased intracranial pressure not mandated by Friedman criteria were identified, such as narrowing of the Meckel cave, posterior displacement of the pituitary stalk, and narrowing of the cavernous sinus. Analysis of associations between neuroimaging findings and demographic and clinical characteristics yielded no statistically significant results. The inter- and intraclass correlation results demonstrated a significant agreement between raters and within each rater's assessment (P < 0.05). CONCLUSIONS: This study highlights the impact of image revision in enhancing PTCS diagnosis. Intra- and interclass correlations underscore the reliability of the review process, emphasizing the importance of meticulous image analysis in clinical practice.

Neural Computation-Based Methods for the Early Diagnosis and Prognosis of Alzheimer's Disease Not Using Neuroimaging Biomarkers: A Systematic Review.

Background: The growing number of older adults in recent decades has led to more prevalent geriatric diseases, such as strokes and dementia. Therefore, Alzheimer's disease (AD), as the most common type of dementia, has become more frequent too. Background: Objective: The goals of this work are to present state-of-the-art studies focused on the automatic diagnosis and prognosis of AD and its early stages, mainly mild cognitive impairment, and predicting how the research on this topic may change in the future. Methods: Articles found in the existing literature needed to fulfill several selection criteria. Among others, their classification methods were based on artificial neural networks (ANNs), including deep learning, and data not from brain signals or neuroimaging techniques were used. Considering our selection criteria, 42 articles published in the last decade were finally selected. Results: The most medically significant results are shown. Similar quantities of articles based on shallow and deep ANNs were found. Recurrent neural networks and transformers were common with speech or in longitudinal studies. Convolutional neural networks (CNNs) were popular with gait or combined with others in modular approaches. Above one third of the cross-sectional studies utilized multimodal data. Non-public datasets were frequently used in cross-sectional studies, whereas the opposite in longitudinal ones. The most popular databases were indicated, which will be helpful for future researchers in this field. Conclusions: The introduction of CNNs in the last decade and their superb results with neuroimaging data did not negatively affect the usage of other modalities. In fact, new ones emerged.

Comparative neuroimaging of sex differences in human and mouse brain anatomy.

In vivo neuroimaging studies have established several reproducible volumetric sex differences in the human brain, but the causes of such differences are hard to parse. While mouse models are useful for understanding the cellular and mechanistic bases of sex-specific brain development, there have been no attempts to formally compare human and mouse neuroanatomical sex differences to ascertain how well they translate. Addressing this question would shed critical light on the use of the mouse as a translational model for sex differences in the human brain and provide insights into the degree to which sex differences in brain volume are conserved across mammals. Here, we use structural magnetic resonance imaging to conduct the first comparative neuroimaging study of sex-specific neuroanatomy of the human and mouse brain. In line with previous findings, we observe that in humans, males have significantly larger and more variable total brain volume; these sex differences are not mirrored in mice. After controlling for total brain volume, we observe modest cross-species congruence in the volumetric effect size of sex across 60 homologous regions (r=0.30). This cross-species congruence is greater in the cortex (r=0.33) than non-cortex (r=0.16). By incorporating regional measures of gene expression in both species, we reveal that cortical regions with greater cross-species congruence in volumetric sex differences also show greater cross-species congruence in the expression profile of 2835 homologous genes. This phenomenon differentiates primary sensory regions with high congruence of sex effects and gene expression from limbic cortices where congruence in both these features was weaker between species. These findings help identify aspects of sex-biased brain anatomy present in mice that are retained, lost, or inverted in humans. More broadly, our work provides an empirical basis for targeting mechanistic studies of sex-specific brain development in mice to brain regions that best echo sex-specific brain development in humans.

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.

[The neural basis of face-to-face communication: exploring transmission and sharing through neuroimaging].

Effective human communication is a complex process that involves transmitting and sharing information, ideas, and attitudes between two or more individuals. Researchers need to explore both transmission and sharing concepts to understand the neural basis of communication. Face-to-face communication refers to changing someone's mental state by sharing information, ideas, or attitudes. This type of communication is characterized by "mutual predictability." Scientists are working to clarify the neural basis of communication by studying how inter-individual synchronization of behavior and neural activity occurs during face-to-face communication.