Search Results - baoxin+li

23 Results Sort By:
BASH-GN: A New Machine Learning–Derived Questionnaire for Screening Obstructive Sleep Apnea
BASH-GN is a machine learning-based questionnaire designed to classify the risk of obstructive sleep apnea (OSA) by considering various risk factor subtypes. Compared with other commonly used OSA screening tools, the BASH-GN questionnaire demonstrated superior performance, making it a more effective option for identifying at-risk individuals. This questionnaire...
Published: 9/23/2024   |   Inventor(s): Ao Li, Jiayan Huo, Stuart Quan, Janet Roveda
Keywords(s):  
Category(s): Technology Classifications > Software & Information Technology > Health IT, Technology Classifications > Life Sciences > Diagnostics, Technology Classifications > Healthcare Portfolios > Sleep Disorders
A Transformer-Based Diffusion Probabilistic Model for Vital Signs Forecasting
The model proposed in this technology, Transformer-based Diffusion Probabilistic Model for Sparse Time Series Forecasting (TDSTF), is a novel deep-learning algorithm that can be used for vital signs forecasting, data synthesis, simulation, and digital twins. Trained and tested on data from over 46,000 patients, the TDSTF technology merges transformer...
Published: 8/23/2024   |   Inventor(s): Ao Li, Ping Chang, Huayu Li, Janet Roveda
Keywords(s):  
Category(s): Technology Classifications > Software & Information Technology > Health IT, Technology Classifications > Software & Information Technology > Web & Internet
MTS-LOF: Medical Time-Series Representation Learning via Occlusion-Invariant Features
Medical Time Series Representation Learning, known as MTS-LOF, uses the strengths of contrastive learning and Masked Autoencoder (MAE) methods, providing more sophisticated, context-rich representations, while also clarifying the interplay between temporal and structural dependencies in healthcare data. MTS-LOF is ideal for integration into numerous...
Published: 8/23/2024   |   Inventor(s): Ao Li, Huayu Li, Ana Carreon-Rascon
Keywords(s):  
Category(s): Technology Classifications > Software & Information Technology > Web & Internet, Technology Classifications > Software & Information Technology > Health IT
DeScoD-ECG: Deep Score-Based Diffusion Model for ECG Baseline Wander and Noise Removal
The DeScoD-ECG model is a novel electrocardiogram (ECG) baseline wander and noise removal technology that extends the current diffusion model for reconstructing electrocardiogram signals. It establishes a new benchmark in biomedical signal processing to provide a more accurate approximation of ECG signals for detection of cardiovascular irregularities....
Published: 8/23/2024   |   Inventor(s): Ao Li, Huayu Li, Gregory Ditzler, Janet Roveda
Keywords(s):  
Category(s): Technology Classifications > Software & Information Technology > Communications & Networking, Technology Classifications > Software & Information Technology > Open Source, Technology Classifications > Healthcare Portfolios > Heart and Vascular, Technology Classifications > Life Sciences > Diagnostics
Deep Learning Algorithm for Detection of Cortical Arousal During Sleep
This invention is an end-to-end deep learning algorithm to detect cortical arousals during sleep using a one-night single lead electrocardiogram (ECG) signal. It is used to accurately detect arousal in home sleep tests, by reducing the false negative rate. The model combines both convolutional neural networks (CNN) and recurrent neural networks (RNN). Background: Sleep...
Published: 8/23/2024   |   Inventor(s): Ao Li, Siteng Chen, Stuart Quan, Linda Powers, Janet Roveda
Keywords(s):  
Category(s): Technology Classifications > Healthcare Portfolios > Sleep Disorders, Technology Classifications > Software & Information Technology > Health IT
Regularization Technique for Training Vision Transformers
Transformers were originally designed for natural language processing but their application to other domains is rapidly gaining traction. In computer vision, convolution neural networks (CNNs) are the traditional choice of deep learning framework for image recognition tasks. Recently, Vision Transformers (ViTs) have been created a new benchmark by...
Published: 2/13/2024   |   Inventor(s): Baoxin Li, Sachin Chhabra
Keywords(s): Algorithm Development, Imaging, Learning, Machine Learning, PS-Computing and Information Technology
Category(s): Computing & Information Technology, Imaging, Physical Science
Self-Supervised Technique for Training Vision Transformers
Convolution neural networks (CNNs) have made tremendous progress in various image processing fields like object recognition, segmentation, etc. This progress is primarily a result of supervised training on labeled data. The features learned by such a network are highly transferable and can be used for similar tasks. However, labeling a dataset is...
Published: 2/13/2024   |   Inventor(s): Baoxin Li, Sachin Chhabra
Keywords(s): Algorithm Development, Imaging, Learning, Machine Learning, PS-Computing and Information Technology
Category(s): Computing & Information Technology, Imaging, Physical Science
Virtual Reality Neuropsychological Assessment (VRNA) System
This technology is a computerized neuropsychological assessment system to rapidly measure cognitive and behavioral abilities and impairments. This system operates by extracting multiple, simultaneous performance metrics while the patient is in a virtual reality (VR) game-like scenario. As the patient is playing this challenging VR video game, the VRNA...
Published: 8/9/2023   |   Inventor(s): William Killgore, Janet Roveda, Jerzy Rozenblit, Ao Li, Huayu Li
Keywords(s):  
Category(s): Technology Classifications > Healthcare Portfolios > Physical Medicine & Rehabilitation, Technology Classifications > Medical Devices > Diagnostic, Technology Classifications > Software & Information Technology > Health IT, Technology Classifications > Software & Information Technology > Mobile Application, Technology Classifications > Software & Information Technology > Bioinformatics, Technology Classifications > Software & Information Technology
Metabolic activity diffusion imaging (MADI): dye-free, high-resolution MRI metabolic imaging
Summary The current technology is a contrast agent-free method of metabolic imaging based on detection of Na/K ATPase activity with MRI, that provides significantly higher resolution than current approaches such as PET. Technology Overview Measuring metabolic activity in vivo can facilitate diagnoses of disease states and therapeutic responses....
Published: 1/15/2024   |   Inventor(s): Gregory Wilson, Jeffrey Maki, Charles Springer, Jr., Xin Li, William (Bill) Rooney, Brendan Moloney, Wei Huang, Tom Barbara, Eric Baker
Keywords(s): Diagnostics, Imaging, Imaging - MRI, Software, Software - Other
Category(s): Imaging, Software
A Gamma-ray Photon Counting Detector Based on Side-readout of Monolithic Scintillator Layers
Researchers at the University of Arizona have developed a gamma-ray photon counting device that works similarly to PET, but with a novel architecture that improves the accuracy and speed in determining the location of the biological targets, and is less costly to manufacture. Background: Positron Emission Tomography (PET) is a common and reliable...
Published: 11/22/2023   |   Inventor(s): Lars Furenlid, Xin Li
Keywords(s):  
Category(s): Technology Classifications > Imaging & Optics, Technology Classifications > Imaging & Optics > Medical Imaging, Technology Classifications > Imaging & Optics > Sensors and Detection
1 2 3