A5072631910- EEG and Brain-Computer Interfaces
- Sleep and Wakefulness Research
- Time Series Analysis and Forecasting
- Obstructive Sleep Apnea Research
- Non-Invasive Vital Sign Monitoring
- Gaze Tracking and Assistive Technology
- Genomic variations and chromosomal abnormalities
- Genetics and Neurodevelopmental Disorders
- Autism Spectrum Disorder Research
- Machine Learning and ELM
- Genetic and rare skin diseases.
- Neural and Behavioral Psychology Studies
- Tactile and Sensory Interactions
- Cutaneous Melanoma Detection and Management
- AI in cancer detection
- Computational Physics and Python Applications
- Neural dynamics and brain function
- Neuroscience and Music Perception
- Neonatal and fetal brain pathology
- Colorectal Cancer Screening and Detection
- Sleep and Work-Related Fatigue
- Global Cancer Incidence and Screening
- Domain Adaptation and Few-Shot Learning
- Traffic Prediction and Management Techniques
- ECG Monitoring and Analysis
Laboratoire Traitement et Communication de l’Information
2017-2019
Télécom Paris
2017-2019
Stanford University
2018-2019
Université Paris-Saclay
2018-2019
Stanford Medicine
2019
SleepMed
2019
Computer Algorithms for Medicine
2017
Sleep stage classification constitutes an important preliminary exam in the diagnosis of sleep disorders. It is traditionally performed by a expert who assigns to each 30 s signal stage, based on visual inspection signals such as electroencephalograms (EEGs), electrooculograms (EOGs), electrocardiograms, and electromyograms (EMGs). We introduce here first deep learning approach for that learns end-to-end without computing spectrograms or extracting handcrafted features, exploits all...
Recent research has shown that auditory closed-loop stimulation can enhance sleep slow oscillations (SO) to improve N3 quality and cognition. Previous studies have been conducted in lab environments. The present study aimed validate assess the performance of a novel ambulatory wireless dry-EEG device (WDD), for SO during at home. WDD detect automatically send on were tested 20 young healthy subjects who slept with both miniaturized polysomnography (part 1) stimulated sham nights within...
MRI has been extensively used to identify anatomical and functional differences in Autism Spectrum Disorder (ASD). Yet, many of these findings have proven difficult replicate because studies rely on small cohorts are built complex, undisclosed, analytic choices. We conducted an international challenge predict ASD diagnosis from data, where we provided preprocessed data > 2,000 individuals. Evaluation the predictions was rigorously blinded. 146 challengers submitted prediction algorithms,...
Electroencephalography (EEG) during sleep is used by clinicians to evaluate various neurological disorders. In medicine, it relevant detect macro-events (≥ 10s) such as stages, and micro-events (≤ 2s) spindles K-complexes. Annotations of events require a trained expert, time consuming tedious process with large inter-scorer variability. Automatic algorithms have been developed types but these are event-specific. We propose deep learning method that jointly predicts locations, durations in...
Low sample size and the absence of labels on certain data limits performances predictive algorithms. To overcome this problem, it is sometimes possible to learn a model large labeled auxiliary dataset. Yet, assumes that two datasets exhibit similar statistical properties which rarely case in practice: there discrepancy between dataset, called source, dataset interest, target. Improving prediction performance target domain by reducing distribution discrepancy, source domains, known as Domain...
Much attention has been given to automatic sleep staging algorithms in past years, but the detection of discrete events studies is also crucial for precise characterization patterns and possible diagnosis disorders. We propose here a deep learning model annotation arousals leg movements. Both these are commonly seen during normal sleep, while an excessive amount either linked disrupted patterns, daytime sleepiness impacting quality life, various Our was trained on 1,485 subjects tested 1,000...
In breast cancer detection, change in findings throughout time is one of the major biomarkers for presence malignancy. Several studies have established value comparing mammograms with ones from previous examinations. Some them shown that such comparison decreases recall rate and increases biopsy yield but does not increase detection rate. This evidence brought us to do hypotheses that, as human radiologists, adding temporal context information could be beneficial also artificial intelligence...
Abstract MRI has been extensively used to identify anatomical and functional differences in Autism Spectrum Disorder (ASD). Yet, many of these findings have proven difficult replicate because studies rely on small cohorts are built complex, undisclosed, analytic choices. We conducted an international challenge predict ASD diagnosis from data, where we provided preprocessed data > 2,000 individuals. Evaluation the predictions was rigorously blinded. 146 challengers submitted prediction...
ABSTRACT Objective Recent research has shown that auditory closed-loop stimulations can enhance sleep slow oscillations (SO) to improve N3 quality and cognition. Previous studies have been conducted in a lab environment on small sample size. The present study aimed at validating assessing the performance of novel ambulatory wireless dry-EEG device (WDD), for SO during home. Material Methods WDD detect automatically send were tested 20 young healthy subjects who slept with both miniaturized...
Sleep stage classification constitutes an important preliminary exam in the diagnosis of sleep disorders. It is traditionally performed by a expert who assigns to each 30s signal stage, based on visual inspection signals such as electroencephalograms (EEG), electrooculograms (EOG), electrocardiograms (ECG) and electromyograms (EMG). We introduce here first deep learning approach for that learns end-to-end without computing spectrograms or extracting hand-crafted features, exploits all...
Electroencephalography (EEG) during sleep is used by clinicians to evaluate various neurological disorders. In medicine, it relevant detect macro-events (> 10s) such as stages, and micro-events (<2s) spindles K-complexes. Annotations of events require a trained expert, time consuming tedious process with large inter-scorer variability. Automatic algorithms have been developed types but these are event-specific. We propose deep learning method that jointly predicts locations, durations in EEG...
Background: Electroencephalography (EEG) monitors brain activity during sleep and is used to identify disorders. In medicine, clinicians interpret raw EEG signals in so-called stages, which are assigned by experts every 30s window of signal. For diagnosis, they also rely on shorter prototypical micro-architecture events exhibit variable durations shapes, such as spindles, K-complexes or arousals. Annotating traditionally performed a trained expert, making the process time consuming, tedious...
Manual analysis of nocturnal polysomnograms (PSGs) is still the standard in sleep laboratories. The process time-consuming and prone to subjective interpretation scoring rules scorer fatigue. Recent developments deep learning algorithms have shown promise for micro-event detection PSGs. We propose a modification recently published DOSED algorithm that can be utilized arousals, respiratory events leg movements, also automatically annotate start duration these events. collected event data from...