A5049108652- Dementia and Cognitive Impairment Research
- Advanced Neuroimaging Techniques and Applications
- Osteoarthritis Treatment and Mechanisms
- Machine Learning in Healthcare
- Health, Environment, Cognitive Aging
- Radiomics and Machine Learning in Medical Imaging
- Infrared Thermography in Medicine
- Medical Imaging and Analysis
- Plasmonic and Surface Plasmon Research
- Musculoskeletal synovial abnormalities and treatments
- Brain Tumor Detection and Classification
- Medical Image Segmentation Techniques
- Image and Signal Denoising Methods
- Traditional Chinese Medicine Studies
- Nanowire Synthesis and Applications
- Cryptographic Implementations and Security
- Cerebrospinal fluid and hydrocephalus
- Total Knee Arthroplasty Outcomes
- Acute Ischemic Stroke Management
- Network Security and Intrusion Detection
- Advanced biosensing and bioanalysis techniques
- Force Microscopy Techniques and Applications
- Artificial Intelligence in Healthcare
- Advanced Malware Detection Techniques
- Mental Health Research Topics
Boston University
2018-2023
Texas A&M University
2016
Alzheimer's disease is the primary cause of dementia worldwide, with an increasing morbidity burden that may outstrip diagnosis and management capacity as population ages. Current methods integrate patient history, neuropsychological testing MRI to identify likely cases, yet effective practices remain variably applied lacking in sensitivity specificity. Here we report interpretable deep learning strategy delineates unique signatures from multimodal inputs MRI, age, gender, Mini-Mental State...
Worldwide, there are nearly 10 million new cases of dementia annually, which Alzheimer's disease (AD) is the most common. New measures needed to improve diagnosis individuals with cognitive impairment due various etiologies. Here, we report a deep learning framework that accomplishes multiple diagnostic steps in successive fashion identify persons normal cognition (NC), mild (MCI), AD, and non-AD dementias (nADD). We demonstrate range models capable accepting flexible combinations routinely...
Abstract Introduction Our aim was to investigate if the accuracy of diagnosing mild cognitive impairment (MCI) using Mini–Mental State Examination (MMSE) and logical memory (LM) test could be enhanced by adding MRI data. Methods Data individuals with normal cognition MCI were obtained from National Alzheimer Coordinating Center database (n = 386). Deep learning models trained on slices combined generate a fused model different voting techniques predict versus MCI. Two multilayer perceptron...
Abstract Background Generative adversarial networks (GAN) can produce images of improved quality but their ability to augment image-based classification is not fully explored. We evaluated if a modified GAN learn from magnetic resonance imaging (MRI) scans multiple field strengths enhance Alzheimer’s disease (AD) performance. Methods T1-weighted brain MRI 151 participants the Disease Neuroimaging Initiative (ADNI), who underwent both 1.5-Tesla (1.5-T) and 3-Tesla at same time were selected...
Abstract Two-dimensional (2D) materials beyond graphene such as transition metal dichalcogenides (TMDs) have unique mechanical, optical and electronic properties with promising applications in flexible devices, catalysis sensing. Optical imaging of TMDs using photoluminescence Raman spectroscopy can reveal the effects structure, strain, doping, edge states surface functionalization from to bioscience. However, signals are inherently weak so far been limited spatial resolution a few hundred...
In computer systems, information leaks from the physical hardware through side-channel signals such as power draw. We can exploit these to infer state of ongoing computational tasks without having direct access device. This paper investigates application recent deep learning techniques analysis in both classification machine and anomaly detection. use real data collected three different devices: an Arduino, a Raspberry Pi, Siemens PLC. For we compare performance Multi-Layer Perceptron Long...
Quantifying the risk of progression to Alzheimer's disease (AD) could help identify persons who benefit from early interventions. We used data Disease Neuroimaging Initiative (ADNI, n = 544, discovery cohort) and National Coordinating Center (NACC, 508, validation cohort), subdividing individuals with mild cognitive impairment (MCI) into groups based on cerebrospinal fluid amyloid-β levels identifying differential gray matter patterns. then created models that fused neural networks survival...
Utilization of 3D neuroimaging data for AD diagnosis has been great interest in recent years. Deep learning algorithms based on convolutional neural networks (CNN) are increasingly being considered analyzing MR scans to diagnose cognitively impaired individuals. Most the CNN models focus using two-dimensional (2D) slices or whole volume-based three-dimensional (3D) as inputs build binary classification models. We leveraged a series 2D and developed region (ROI)-based strategy enhance...
Abstract Background The gold standard of Alzheimer’s disease (AD) diagnosis remains histopathologic examination neuropathologic changes. However, the dependence on post‐mortem microscopic analysis limits role pathology in clinical care. Magnetic resonance imaging (MRI) is routinely used to diagnose suspected dementia (DE) due AD, but correlating neuroimaging underlying pathologic changes challenging. Herein, we report development two risk scores derived from convolutional neural network...
Abstract Quantifying heterogeneity in Alzheimer’s disease (AD) risk is critical for individualized care and management. Recent attempts to assess AD have used structural (magnetic resonance imaging (MRI)-based) or functional (Aβ tau) imaging, which focused on generating quartets of atrophy patterns protein spreading, respectively. Here we present a computational framework that facilitated the identification subtypes based their progression AD. We cerebrospinal fluid (CSF) measures Aβ from...
ABSTRACT Background and objective It remains difficult to characterize pain in knee joints with osteoarthritis solely by radiographic findings. We sought understand how advanced machine learning methods such as deep neural networks can be used analyze raw MRI scans predict bilateral pain, independent of other risk factors. Methods developed a framework associate information from slices taken the left right knees subjects Osteoarthritis Initiative pain. Model training was performed first...
Abstract Background Generative adversarial networks (GAN) can generate images of improved quality but their ability to augment image-based classification tasks is not fully explored. Purpose We evaluated if a modified GAN learn from MRI scans multiple magnetic field strength enhance Alzheimer’s disease (AD) performance. Materials and methods T1-weighted brain 151 participants the Disease Neuroimaging Initiative (ADNI), who underwent both 1.5 Tesla (1.5T) 3 imaging at same time were selected...
Two-dimensional (2D) materials beyond graphene such as transition metal dichalcogenides (TMDs) have unique mechanical, optical and electronic properties with promising applications in flexible devices, catalysis sensing. Optical imaging of TMDs using photoluminescence Raman spectroscopy can reveal the effects structure, strain, doping, defects, edge states, grain boundaries surface functionalization. However, signals are inherently weak so far been limited spatial resolution to a few hundred...
Background: Quantifying the risk of progression to Alzheimer’s disease (AD) could help identify persons who benefit from early interventions. Previous work leveraged binary classification frameworks assess using structural imaging and/or clinical factors, or alternatively, survival analyses utilizing summative measures parcellated brain regions.Methods: We developed a deep learning framework stratify with mild cognitive impairment (MCI) based on their AD non-parcellated T1-weighted MRIs....
Abstract Alzheimer’s disease (AD) is the primary cause of dementia worldwide ( 1 ), with an increasing morbidity burden that may outstrip diagnosis and management capacity as population ages. Current methods integrate patient history, neuropsychological testing magnetic resonance imaging (MRI) to identify likely cases, yet effective practices remain variably-applied lacking in sensitivity specificity 2 ). Here we report explainable deep learning strategy delineates unique AD signatures from...
Abstract Background Cerebrospinal fluid (CSF) levels of p‐tau, t‐tau, and Aβ42 are widely accepted in vivo biomarkers for Alzheimer’s Disease (AD). However, lumbar puncture comes with limitations, including severe infection, headache, bleeding at the site, a lack spatial information about regions neurodegeneration, substantial inter‐lab variability. A less invasive method based on imaging assessing AD progression can lead to insights subtypes, decrease puncture‐related morbidity, lower...