A5022256468- Functional Brain Connectivity Studies
- Advanced Neuroimaging Techniques and Applications
- Advanced MRI Techniques and Applications
- Neural dynamics and brain function
- Topic Modeling
- Advanced Text Analysis Techniques
- Biomedical Text Mining and Ontologies
- Infrared Thermography in Medicine
- Artificial Intelligence in Healthcare and Education
- HIV Research and Treatment
- Radiomics and Machine Learning in Medical Imaging
- Bone health and osteoporosis research
- EEG and Brain-Computer Interfaces
- COVID-19 diagnosis using AI
- Chemical Synthesis and Analysis
- Winter Sports Injuries and Performance
- Computational Drug Discovery Methods
- Natural Language Processing Techniques
- Alzheimer's disease research and treatments
- Advanced Memory and Neural Computing
- Advanced Neural Network Applications
- Medical Imaging and Analysis
- Privacy-Preserving Technologies in Data
- Machine Learning in Healthcare
- Medical Image Segmentation Techniques
Nvidia (United States)
2021-2023
University of Rochester
2015-2022
University of Rochester Medical Center
2015-2022
Ludwig-Maximilians-Universität München
2022
Nvidia (United Kingdom)
2021
Bellingham Technical College
2015
Manipal Academy of Higher Education
2010
Federated learning (FL) is a method used for training artificial intelligence models with data from multiple sources while maintaining anonymity, thus removing many barriers to sharing. Here we 20 institutes across the globe train FL model, called EXAM (electronic medical record (EMR) chest X-ray AI model), that predicts future oxygen requirements of symptomatic patients COVID-19 using inputs vital signs, laboratory and X-rays. achieved an average area under curve (AUC) >0.92 predicting...
Abstract Physicians make critical time-constrained decisions every day. Clinical predictive models can help physicians and administrators by forecasting clinical operational events. Existing structured data-based have limited use in everyday practice owing to complexity data processing, as well model development deployment 1–3 . Here we show that unstructured notes from the electronic health record enable training of language models, which be used all-purpose engines with low-resistance...
Glioma is one of the most common and aggressive types primary brain tumors. The accurate segmentation subcortical structures crucial to study gliomas in that it helps monitoring progression aids evaluation treatment outcomes. However, large amount required human labor makes difficult obtain manually segmented Magnetic Resonance Imaging (MRI) data, limiting use precise quantitative measurements clinical practice. In this work, we try address problem by developing a 3D Convolutional Neural...
HIV is capable of invading the brain soon after seroconversion. This ultimately can lead to deficits in multiple cognitive domains commonly referred as HIV-associated neurocognitive disorders (HAND). Clinical diagnosis such requires detailed neuropsychological assessment but clinical signs may be difficult detect during asymptomatic injury central nervous system (CNS). Therefore neuroimaging biomarkers are particular interest HAND. In this study, we constructed connectivity profiles 40...
A key challenge to gaining insight into complex systems is inferring nonlinear causal directional relations from observational time-series data. Specifically, estimating relationships between interacting components in large with only short recordings over few temporal observations remains an important, yet unresolved problem. Here, we introduce large-scale Granger causality (lsNGC) which facilitates conditional two multivariate time series conditioned on a number of confounding small...
Abstract ‘Federated Learning’ (FL) is a method to train Artificial Intelligence (AI) models with data from multiple sources while maintaining anonymity of the thus removing many barriers sharing. During SARS-COV-2 pandemic, 20 institutes collaborated on healthcare FL study predict future oxygen requirements infected patients using inputs vital signs, laboratory data, and chest x-rays, constituting “EXAM” (EMR CXR AI Model) model. EXAM achieved an average Area Under Curve (AUC) over 0.92,...
We explore a computational framework for functional connectivity analysis in resting-state MRI (fMRI) data acquired from the human brain recovering underlying network structure and understanding causality between components. Termed mutual (MCA), this involves two steps, first of which is to evaluate pair-wise cross-prediction performance fMRI pixel time series within brain. In second step, subsequently recovered affinity matrix using non-metric clustering approaches, such as so-called...
Glioma is one of the most common and aggressive types primary brain tumors. The accurate segmentation subcortical structures crucial to study gliomas in that it helps monitoring progression aids evaluation treatment outcomes. However, large amount required human labor makes difficult obtain manually segmented Magnetic Resonance Imaging (MRI) data, limiting use precise quantitative measurements clinical practice. In this work, we try address problem by developing a 3D Convolutional Neural...
Causal inquiries provide crucial insight into the advancement of scientific discoveries. In real-world studies like climatology, sensory data acquired from nodal measurements are nonlinearly related and complex. At same time, they have information millions sensors with only a few decades' temporal samples, which leads to curse dimensionality in large-scale systems. Despite rich literature on causal discovery, problem is challenging for largescale datasets. We put forth novel method that...
We introduce a multi-institutional data harvesting (MIDH) method for longitudinal observation of medical imaging utilization and reporting. By tracking both large-scale clinical results data, the MIDH approach is targeted at measuring surrogates important disease-related observational quantities over time. To quantitatively investigate its applicability, we performed retrospective study encompassing 13 healthcare systems throughout United States before after 2020 COVID-19 pandemic. Using...
Clinically Isolated Syndrome (CIS) is often considered to be the first neurological episode associated with Multiple sclerosis (MS). At an early stage inflammatory demyelination occurring in CNS can manifest as a change neuronal metabolism, multiple asymptomatic white matter lesions detected clinical MRI. Such damage may induce topological changes of brain networks, which captured by advanced functional MRI (fMRI) analysis techniques. We test this hypothesis capturing effective relationships...
Differentiating a solitary brain metastasis (METS) from glioblastoma multiforme (GBM) is an important yet difficult task using current MR imaging techniques. A final diagnosis obtained by performing stereotactic biopsy, which carries small but not insignificant risk. Distinguishing between primary and secondary malignant neoplasms critical for providing appropriate patient prognosis, management treatment planning. Devising non-invasive means of distinguishing the two would be clinically...
While the proximal femur is preferred for measuring bone mineral density (BMD) in fracture risk estimation, introduction of volumetric quantitative computed tomography has revealed stronger associations between BMD and spinal status. In this study, we propose to capture properties trabecular structure vertebrae with advanced second-order statistical features purposes assessment. For purpose, axial multi-detector CT (MDCT) images were acquired from 28 specimens using a whole-body 256-row...
About 50% of subjects infected with HIV present deficits in cognitive domains, which are known collectively as associated neurocognitive disorder (HAND). The underlying synaptodendritic damage can be captured using resting state functional MRI, has been demonstrated by a few earlier studies. Such may induce topological changes brain connectivity networks. We test this hypothesis capturing the interdependence 90 network nodes Mutual Connectivity Analysis (MCA) framework non-linear time series...
Few studies have analyzed the microstructural properties of bone in cases Osteogenenis Imperfecta (OI), or 'brittle disease'. Current approaches mainly focus on mineral density measurements as an indirect indicator strength and quality. It has been shown that would depend not only composition but also structural organization. This study aims to characterize 3D structure cortical high-resolution micro CT images. A total 40 fragments from 28 subjects (13 with OI 15 healthy controls) were...
In this study, we investigate if differences in interaction between different brain regions for subjects with autism spectrum disorder (ASD) and healthy controls can be captured using resting-state fMRI. To end, the use of mutual connectivity analysis Local Models (MCA-LM), which estimates nonlinear measures pairs time-series terms cross-predictability. These pairwise provide a high-dimensional representation profiles are used as features classification. Subsequently, perform feature...
Infection of the brain by Human Immunodeficiency Virus (HIV) causes irreversible damage to synaptic connections resulting in cognitive impairment. Patients with HIV infection, showing signs impairment multiple domains, as assessed neuropsychological testing, are said exhibit symptoms Associated Neurocognitive Disorder (HAND). In this study, we use resting-state functional MRI (fMRI) data distinguish between healthy subjects and HAND. To end, first establish a measure interaction pairs...
The advent of advanced multivariate time-series analysis methods to capture directional information flow in the brain, such as large-scale Granger causality (lsGC), has already yielded insights into healthy and diseased brain states holds promise for continued discoveries neuroscience. Here, a set functional networks was generated by applying lsGC resting-state MRI dataset comprised 20 individuals order characterize network properties across range spatial scales densities. Network vertex...