A5005351569- Functional Brain Connectivity Studies
- Neural dynamics and brain function
- Blind Source Separation Techniques
- Brain Tumor Detection and Classification
- Advanced MRI Techniques and Applications
- Medical Image Segmentation Techniques
- Advanced Neuroimaging Techniques and Applications
- Renal and Vascular Pathologies
- Face and Expression Recognition
- Neural Networks and Applications
- Renal cell carcinoma treatment
- EEG and Brain-Computer Interfaces
- Bipolar Disorder and Treatment
- Domain Adaptation and Few-Shot Learning
- Machine Learning and ELM
- Machine Learning and Algorithms
- Remote-Sensing Image Classification
- Electrochemical Analysis and Applications
- Complex Systems and Time Series Analysis
- Neuroscience and Music Perception
- Minimally Invasive Surgical Techniques
- Bone and Dental Protein Studies
- Thermoregulation and physiological responses
- Image Retrieval and Classification Techniques
- Artificial Intelligence in Healthcare and Education
Inria Saclay - Île de France
2022
Institut national de recherche en informatique et en automatique
2022
Child Mind Institute
2018-2022
University of the Basque Country
2010-2020
Commissariat à l'Énergie Atomique et aux Énergies Alternatives
2019
CEA Paris-Saclay
2019
Nathan Kline Institute for Psychiatric Research
2019
University of Florida
2015-2017
Allen Institute for Brain Science
2017
Centro de Investigación Biomédica en Red de Salud Mental
2016
With increasing data sizes and more easily available computational methods, neurosciences rely on predictive modeling with machine learning, e.g., to extract disease biomarkers. Yet, a successful prediction may capture confounding effect correlated the outcome instead of brain features specific interest. For instance, because patients tend move in scanner than controls, imaging biomarkers condition mostly reflect head motion, leading inefficient use resources wrong interpretation
Auditory hallucinations (AH) are a symptom that is most often associated with schizophrenia, but patients other neuropsychiatric conditions, and even small percentage of healthy individuals, may also experience AH. Elucidating the neural mechanisms underlying AH in schizophrenia offer insight into pathophysiology more broadly across multiple disease conditions. In this paper, we address problem classifying without history AH, control (HC) subjects. To end, performed feature extraction from...
Adverse effects are a common burden for cancer patients, impacting their well-being and diminishing quality of life. Therefore, it is essential to have clinical decision support system that can proactively monitor patient progress prevent manage complications. This research aims thoroughly test the usability user-friendliness medical device designed managing adverse events patients healthcare professionals (HCPs). The study seeks assess how well meets both patients' HCPs' needs in real-world...
textbf{Background} Late Onset Bipolar Disorder (LOBD) is often difficult to distinguish from degenerative dementias, such as Alzheimer Disease (AD), due comorbidities and common cognitive symptoms. Moreover, LOBD prevalence in the elder population not negligible it increasing. Both pathologies share pathophysiological features related neuroinflammation. Improved means differentiate between AD subjects will help select best personalized treatment. \textbf{Objective} The aim of this study...
Multivariate mathematical morphology (MMM) aims to extend the from gray scale images whose pixels are high-dimensional vectors, such as remote sensing hyperspectral and functional magnetic resonance (fMRIs). Defining an ordering over multidimensional image data space is a fundamental issue MMM, ensure that ensuing morphological operators filters mathematically consistent. Recent approaches use outputs of two-class classifiers build reduced orderings. This paper presents applications MMM...
Hallucinations are elusive phenomena that have been associated with psychotic behavior, but a high prevalence in healthy population. Some generative mechanisms of Auditory (AH) proposed the literature, so far empirical evidence is scarce. The most widely accepted mechanism hypothesis nowadays consists faulty workings network brain areas including emotional control, audio and language processing, inhibition self-attribution signals auditive cortex. In this paper, we consider two methods to...
\textbf{Background:} Late Onset Bipolar Disorder (LOBD) is the development of (BD) at an age above 50 years old. It often difficult to differentiate from other aging dementias, such as Alzheimer's Disease (AD), because they share cognitive and behavioral impairment symptoms. \textbf{Objectives:} We look for WM tract voxel clusters showing significant differences when comparing AD versus LOBD, its correlations with systemic blood plasma biomarkers (inflammatory, neurotrophic factors,...
Predictive models applied on brain images can extract imaging biomarkers of pathologies or psychological traits. Yet, a successful prediction may be driven by confounding effect that is correlated with the interest. For instance fluid intelligence strongly impacted age; age well predicted from images; hence might have captured nothing more than biomarker aging. Here we introduce non-sparametric approach to control for in predictive model. It based crafting test set which interest independent...
Background: Late Onset Bipolar Disorder (LOBD) is the arousal of (BD) at old age (>60) without any previous history disorders. LOBD often difficult to distinguish from degenerative dementias, such as Alzheimer Disease (AD), due comorbidities and common cognitive symptoms. Moreover, prevalence increasing population aging. Biomarkers extracted blood plasma are not discriminant because both pathologies share pathophysiological features related neuroinflammation, therefore we look for anatomical...
Analysis of fMRI data, specifically resting-state is performed here from the point view a hybrid Multivariate Mathematical Morphology induced by supervised h-ordering defined on time series response Lattice Auto-associative Memories built specific voxels. The values and results morphological filters, i.e. top-hat, allow to identify some brain networks depending seed voxel value. Results set resting state images schizophrenia patients healthy controls show that these can be dependent subject...