A5077056958- EEG and Brain-Computer Interfaces
- Functional Brain Connectivity Studies
- Neural dynamics and brain function
- Traumatic Brain Injury Research
- Advanced MRI Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Urological Disorders and Treatments
- Neural and Behavioral Psychology Studies
- Colorectal Cancer Screening and Detection
- Pediatric Urology and Nephrology Studies
- Advanced Neuroimaging Techniques and Applications
- Artificial Intelligence in Healthcare
- Mind wandering and attention
- Advanced X-ray and CT Imaging
- Emotion and Mood Recognition
- Neural Networks and Applications
- Genomic variations and chromosomal abnormalities
- AI in cancer detection
- Generative Adversarial Networks and Image Synthesis
- Spatial Cognition and Navigation
- Autism Spectrum Disorder Research
- Hepatocellular Carcinoma Treatment and Prognosis
- Grit, Self-Efficacy, and Motivation
- Machine Learning and Data Classification
- Genomics and Rare Diseases
Berlin Institute of Health at Charité - Universitätsmedizin Berlin
2021-2025
Humboldt-Universität zu Berlin
2021-2024
Charité - Universitätsmedizin Berlin
2021-2024
Freie Universität Berlin
2021-2024
Vector Institute
2018-2022
McMaster University
2014-2021
Grading hydronephrosis severity relies on subjective interpretation of renal ultrasound images. Deep learning algorithms classify images into categories using data-driven methods, thus presenting a promising option for grading hydronephrosis. The current study explored the potential convolutional neural networks (CNN), type deep algorithm, to grade according 5-point Society Fetal Urology (SFU) classification system, and discusses its applications in developing decision teaching aids clinical...
Neural correlates of mind wandering The ability to detect as it occurs is an important step towards improving our understanding this phenomenon and studying its effects on learning performance. Current detection methods typically rely observable behaviour in laboratory settings, which do not capture the underlying neural processes may translate well into real-world settings. We address both these issues by recording electroencephalography (EEG) simultaneously from 15 participants during live...
The traditional view of the medial temporal lobe (MTL) focuses on its role in episodic memory. However, some underlying functions MTL can be ascertained from wider supporting spatial cognition concert with parietal and prefrontal regions. is strongly implicated formation enduring allocentric representations (e.g. O'Keefe (1976); Ekstrom et al. (2003); King (2002)). According to our BBB model (Byrne (2007)), these must interact head-centered body-centered posterior cortex via a transformation...
Computational brain network modeling using The Virtual Brain (TVB) simulation platform acts synergistically with machine learning (ML) and multi-modal neuroimaging to reveal mechanisms improve diagnostics in Alzheimer's disease (AD).We enhance large-scale whole-brain TVB a cause-and-effect model linking local amyloid beta (Aβ) positron emission tomography (PET) altered excitability. We use PET magnetic resonance imaging (MRI) data from 33 participants of the Disease Neuroimaging Initiative...
OBJECTIVE. The purpose of this study is to determine the impact LI-RADS ancillary features on MRI and ascertain whether number can be reduced without compromising accuracy. MATERIALS AND METHODS. A total 222 liver observations in 81 consecutive patients were identified between August 2013 December 2018. presence or absence major was used category for LR-1 LR-5 observations. Final diagnosis established basis pathologic findings one several composite clinical reference standards. Diagnostic...
Abstract Background Existing risk evaluation tools underperform in predicting intensive care unit (ICU) admission for patients with the Coronavirus Disease 2019 (COVID-19). This study aimed to develop and evaluate an accurate calculator-free clinical tool ICU at emergency room (ER) presentation. Methods Data from COVID-19 a nationwide German cohort (March 2020-January 2023) were analyzed. Candidate predictors selected based on literature expertise. A score, within seven days of ER...
Brain-computer-interfaces allow a person to control device directly via their brain signals. Around 15-30% of people are unable BCI accurately; this is known as the illiteracy problem. However, problem may lie more with designer than user. Here we explore three potential sources variability that contribute so-called illiteracy, and solutions help overcome each one. These approaches bring us closer having individualized, open-ended BCIs. First, examine impact individual expertise. We show who...
There has been increased effort to understand the neurophysiological effects of concussion aimed move diagnosis and identification beyond current subjective behavioral assessments that suffer from poor sensitivity. Recent evidence suggests event-related potentials (ERPs) measured with electroencephalography (EEG) are persistent markers past concussions. However, as such is limited group-level analyzes, extent which they enable detection at individual-level unclear. One promising avenue...
A substantial proportion of Autism Spectrum Disorder (ASD) risk resides in de novo germline and rare inherited genetic variation. In particular, copy number variation (CNV) contributes to ASD up 10% subjects. Despite the striking degree heterogeneity, case-control studies have detected specific burden disruptive CNV for neuronal neurodevelopmental pathways. Here, we used machine learning methods classify subjects controls, based on data comprehensive gene annotations. We investigated...
Purpose: To establish reporting adherence to the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) diagnostic accuracy AI studies with highest Altmetric Attention Scores (AAS), and compare completeness of between peer-reviewed manuscripts preprints. Methods: MEDLINE, EMBASE, arXiv, bioRxiv, medRxiv were retrospectively searched 100 medical imaging journals preprint platforms AAS since release CLAIM June 24, 2021. Studies evaluated 42-item checklist comparison The impact...
We evaluate the performance of a Deep Convolutional Neural Network in grading severity prenatal hydronephrosis (PHN), one most common congenital urological anomalies, from renal ultrasound images. present results on variety classification tasks based clinically defined grades severity, including predictions whether or not an image represents case that is at high risk for further complications requiring surgical intervention with approximately 80% accuracy. The prediction rates obtained by...
We develop and approach to unsupervised semantic medical image segmentation that extends previous work with generative adversarial networks. use existing edge detection methods construct simple diagrams, train a model convert them into synthetic images, dataset of images known segmentations using variations on extracted diagrams. This is then used supervised model. test our clinical kidney ultrasound the benchmark ISIC 2018 skin lesion dataset. show more accurate than methods, performs...
Abstract The current literature presents a discordant view of mild traumatic brain injury and its effects on the human brain. This dissonance has often been attributed to heterogeneities in study populations, aetiology, acuteness, experimental paradigms and/or testing modalities. To investigate progression brain, present employed data from 93 subjects (48 healthy controls) representing both acute chronic stages injury. concussion across different were measured using two metrics functional...
Brain-computer interfaces (BCIs) allow users to control a device by interpreting their brain activity. For simplicity, these devices are designed be operated purposefully modulating specific predetermined neurophysiological signals, such as the sensorimotor rhythm. However, ability modulate given signal is highly variable across individuals, contributing inconsistent performance of BCIs for different users. These differences suggest that individuals who experience poor BCI with one class...
Neurofeedback has long been proposed as a promising form of adjunctive non-pharmaceutical treatment for variety neuropsychological disorders. However, there is much debate over its efficacy and specificity. Many suggest that specificity can only be achieved when specially trained clinician manually updates reward thresholds indicate to the trainee they are modulating their brain activity correctly, during training. We present novel fully automated thresholding algorithm called progressive...
In this study we explore the application of pattern recognition models for recognizing emotional reactions elicited by videos from electroencephalography (EEG). We show that both presence and magnitude each emotion can be predicted above chance levels with up to 88% accuracy. Furthermore, there are differences in classifiability different emotions participants, but whether a participant's data classified respect itself their EEG.
<p>There has been increased effort to understand the neurophysiological effects of concussion aimed move diagnosis and identification beyond current subjective behavioral assessments that suffer from poor sensitivity. Recent evidence suggests event-related potentials (ERPs) measured with electroencephalography (EEG) are persistent markers past concussions. However, as such is limited group-level analyzes, extent which they enable detection at individual-level unclear. One promising...
ABSTRACT INTRODUCTION Computational brain network modeling using The Virtual Brain (TVB) simulation platform acts synergistically with machine learning and multi-modal neuroimaging to reveal mechanisms improve diagnostics in Alzheimer’s disease. METHODS We enhance large-scale whole-brain TVB a cause-and-effect model linking local Amyloid β PET altered excitability. use MRI data from 33 participants of Disease Neuroimaging Initiative (ADNI3) combined frequency compositions TVB-simulated field...