A5101705907- Radiomics and Machine Learning in Medical Imaging
- Artificial Intelligence in Healthcare and Education
- Food Drying and Modeling
- Medical Imaging Techniques and Applications
- Human Pose and Action Recognition
- AI in cancer detection
- Medical Imaging and Analysis
- Hepatitis B Virus Studies
- Traumatic Brain Injury and Neurovascular Disturbances
- Musculoskeletal synovial abnormalities and treatments
- Advanced X-ray and CT Imaging
- Orthopedic Infections and Treatments
- Brain Tumor Detection and Classification
- Thyroid Cancer Diagnosis and Treatment
- Total Knee Arthroplasty Outcomes
- Artificial Intelligence in Healthcare
- Topic Modeling
- Air Quality Monitoring and Forecasting
- Air Quality and Health Impacts
- Heme Oxygenase-1 and Carbon Monoxide
- Hemoglobin structure and function
- Glutathione Transferases and Polymorphisms
- Immune responses and vaccinations
- Fire Detection and Safety Systems
- Glioma Diagnosis and Treatment
Duke University
1995-2025
Inner Mongolia University of Science and Technology
2022-2024
Duke Medical Center
1991-2024
Shihezi University
2023-2024
Ministry of Agriculture and Rural Affairs
2023-2024
Duke University Hospital
1991-2024
Shandong University
2018
Guangdong University Of Finances and Economics
2015
Guangdong University of Finance
2015
Guangdong Institute of Biological Products and Drugs
2015
To better understand the mechanisms of tissue injury during and after carbon monoxide (CO) hypoxia, we studied generation partially reduced oxygen species (PROS) in brains rats subjected to 1% CO for 30 min, then reoxygenated on air 0-180 min. By determining H2O2-dependent inactivation catalase presence 3-amino-1,2,4-triazole (ATZ), found increased H2O2 production forebrain reoxygenation. The localization brain microperoxisomes indicated an intracellular site production; subsequent studies...
This study combined an artificial neural network (ANN) with a genetic algorithm (GA) to obtain the model and optimal process parameters of drying-assisted walnut breaking. Walnuts were dried at different IR temperatures (40 °C, 45 50 55 °C) air velocities (1, 2, 3, 4 m/s) moisture contents (10%, 15%, 20%, 25%) by using air-impingement technology. Subsequently, walnuts broken in loading directions (sutural, longitudinal, vertical). The drying time (DT), specific energy consumption (SEC), high...
Peripheral artery disease (PAD) is underrecognized, undertreated, and understudied: each of these endeavors requires efficient accurate identification patients with PAD. Currently, PAD patient relies on diagnosis/procedure codes or lists diagnosed treated by specific providers in locations ways. The goal this research was to leverage natural language processing more accurately identify an electronic health record system compared a structured data-based approach.The clinical notes from cohort...
Using hot air drying (HAD) and combined infrared (IR-HAD) test devices, the kinetics, unit energy consumption, color difference values, rehydration rate, microstructure, changes in polysaccharide allantoin contents of yam slices were examined at various temperatures (50 °C, 55 60 65 70 °C). The findings demonstrated that each aforementioned parameters was significantly impacted by temperature. IR-HAD dries quicker takes less time to dry than HAD. Deff is higher HAD same temperature increases...
In this paper, the effects on drying time (Y1), color difference (Y2), unit energy consumption (Y3), polysaccharide content (Y4), rehydration ratio (Y5), and allantoin (Y6) of yam slices were investigated under different temperatures (50–70 °C), slice thicknesses (2–10 mm), radiation distances (80–160 mm). The optimal conditions determined by applying BP neural network wolf algorithm (GWO) model based response surface methodology (RMS). All above indices significantly affected (p < 0.05)....
“Just Accepted” papers have undergone full peer review and been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, proof before it is published its final version. Please note that during production of the copyedited article, errors may be discovered which could affect content. Purpose To develop evaluate an automated system extracting structured clinical information from unstructured radiology pathology reports using open-weights...
Modern bioinformatics tools for analyzing large-scale NGS datasets often need to include fast implementations of core sequence alignment algorithms in order achieve reasonable execution times. We address this by presenting the BGSA toolkit optimized popular bit-parallel global pairwise on modern microprocessors.BGSA outperforms Edlib, SeqAn and BitPAl edit distance computations Parasail, when using more general scoring schemes alignments a batch reads both standard multi-core CPUs Xeon Phi...
A drying temperature precision control system was studied to provide technical support for developing and further proving the superiority of variable-temperature process. In this study, an improved neural network (INN) proportional-integral-derivative (PID) controller (INN-PID) designed. The dynamic performance PID, PID (NN-PID) INN-PID controllers simulated with unit step signals as input in MATLAB software. set up air impingement dryer, experiment carried out verify three controllers....
Magnetic Resonance Imaging (MRI) is pivotal in radiology, offering non-invasive and high-quality insights into the human body. Precise segmentation of MRIs different organs tissues would be highly beneficial since it allow for a higher level understanding image content enable important measurements, which are essential accurate diagnosis effective treatment planning. Specifically, segmenting bones MRI more quantitative assessments musculoskeletal conditions, while such largely absent current...
To monitor the moisture content of agricultural products in drying process real time, this study applied a model combining multi-sensor fusion and convolutional neural network (CNN) to online detection. This built data acquisition platform established CNN prediction with raw monitoring load sensor, air velocity temperature tray position as input weight material output. The model’s predictive performance was compared that linear partial least squares regression (PLSR) nonlinear support vector...
Gliomas are the most common malignant primary brain tumors in adults and one of deadliest types cancer. There many challenges treatment monitoring due to genetic diversity high intrinsic heterogeneity appearance, shape, histology, response. Treatments include surgery, radiation, systemic therapies, with magnetic resonance imaging (MRI) playing a key role planning post-treatment longitudinal assessment. The 2024 Brain Tumor Segmentation (BraTS) challenge on glioma MRI will provide community...
<title>Abstract</title> Due to its high dependence on labeled data, animal pose estimation faces significant challenges in practical applications. Effectively utilizing large amounts of unlabeled data improve the accuracy has become an urgent research topic be addressed. In this paper, we propose MVCRNet, which is designed label a minimal amount at low cost, while effectively for accurate estimation. We first train initial model limited set samples, and then use generate preliminary...
In order to improve the image instance segmentation algorithm due long propagation path of underlying location information and slow speed convolutional operations in process capturing long-distance dependencies low computational efficiency, a PaFPN-SOLO is proposed this paper. By adding Non-local operation ResNet backbone, feature extraction better preserved; by using bottom-up augmentation method, more accurate position extracted on lower layers, which not only improves structure...
To address the issues of high measurement difficulty and poor accuracy in traditional cattle body methods, this study employed a multi-view stereo vision-based three-dimensional (3D) reconstruction automatic method to conduct comparative research on yellow model 47 dairy cows. An data acquisition channel equipped with multi-angle cameras was designed, keypoint recognition based YOLOv7 object detection algorithm used achieve instant 3D point cloud acquisition. reduce influence noise caused by...
Temporal action detection is one of the most important and challenging tasks in video analysis. Due to its wide application prospects, it has received extensive attention recent years. With development deep learning, great progress been made temporal behavior detection, but there are still many difficulties be solved, such as accurate proposal generation high computational cost. In this paper, learning-based methods classified according full supervision weak supervision, then representative...
Scoliosis, a prevalent condition characterized by abnormal spinal curvature leading to deformity, requires precise assessment methods for effective diagnosis and management. The Cobb angle is widely used scoliosis quantification method that measures the degree of between tilted vertebrae. Yet, manual measuring angles time-consuming labor-intensive, fraught with significant interobserver intraobserver variability. To address these challenges lack interpretability found in certain existing...