A5002662217- Radiomics and Machine Learning in Medical Imaging
- COVID-19 diagnosis using AI
- Radiology practices and education
- Quantum Information and Cryptography
- Hepatocellular Carcinoma Treatment and Prognosis
- Retinal Development and Disorders
- Photoreceptor and optogenetics research
- Quantum Mechanics and Applications
- Advanced X-ray and CT Imaging
- MRI in cancer diagnosis
- Social Media in Health Education
- Liver Disease Diagnosis and Treatment
- Laser-Matter Interactions and Applications
- Artificial Intelligence in Healthcare and Education
- Neural dynamics and brain function
- Network Security and Intrusion Detection
- Lung Cancer Diagnosis and Treatment
- Internet Traffic Analysis and Secure E-voting
- AI in cancer detection
- Conferences and Exhibitions Management
- Pulsars and Gravitational Waves Research
- Quantum Computing Algorithms and Architecture
- Amoebic Infections and Treatments
- Liver Disease and Transplantation
- Geophysics and Gravity Measurements
University of Arizona
2021-2024
Louisiana State University Health Sciences Center New Orleans
2019-2020
University Hospital and Clinics
2020
University of Maryland, College Park
2014-2018
Louisiana State University
2012-2013
Purpose To examine variations of convolutional neural network (CNN) performance for multiple chest radiograph diagnoses and image resolutions. Materials Methods This retrospective study examined CNN using the publicly available National Institutes Health dataset comprising 112 120 radiographic images from 30 805 patients. The architectures included ResNet34 DenseNet121. Image resolutions ranging 32 × to 600 pixels were investigated. Network training paradigms used 80% samples 20% validation....
In many forms of retinal degeneration, photoreceptors die but inner circuits remain intact. the rd1 mouse, an established model for blinding diseases, spontaneous activity in coupled network AII amacrine and ON cone bipolar cells leads to rhythmic bursting ganglion cells. Since such could impair and/or cortical responses restored photoreceptor function, understanding its nature is important developing treatments pathologies. Here we analyzed a compartmental wild-type mouse cell predict that...
We develop an improvement to the weak laser pulse BB84 scheme for quantum key distribution, which utilizes entanglement improve security of and enhance its resilience photon-number-splitting attack. This protocol relies on non-commutation phase number detect eavesdropper performing non-demolition measurement photon number. The potential advantages disadvantages this are compared coherent decoy state protocol.
Reliable timing of cortical spikes in response to visual events is crucial representing inputs the brain. Spikes primary cortex (V1) need occur at same time within a repeated stimulus. Two classical mechanisms are employed by enhance reliable timing. First, neurons respond reliably restricted set stimuli through their preference for certain patterns membrane potential due intrinsic properties. Second, intracortical networking excitatory and inhibitory induces lateral inhibition that,...
Our goal was to analyze radiology report text for chest radiographs (CXRs) identify imaging findings that have the most impact on length and complexity. Identifying these can highlight opportunities designing CXR AI systems which increase radiologist efficiency. We retrospectively analyzed from 210,025 MIMIC-CXR reports 168,949 our local institution collected 2019 2022. Fifty-nine categories of finding keywords were extracted using natural language processing (NLP), their assessed linear...
We develop an improvement to the weak laser pulse BB84 scheme for quantum key distribution, which utilizes entanglement improve security of and enhance its resilience photon-number-splitting attack. This protocol relies on non-commutation photon phase number detect eavesdropper performing non-demolition measurement number. The potential advantages disadvantages this are compared coherent decoy state protocol.
We describe a novel method for analyzing neural data that uses combination of Markov transition matrices and Kullback-Leibler divergence to characterize spike history patterns.For this method, the interspike intervals (ISIs) are divided into bins by quantiles, matrix is computed ISI sequence.This then compared another constructed under assumption independent spiking.We compute between