- Ultrasound Imaging and Elastography
- Cardiovascular Health and Disease Prevention
- Non-Invasive Vital Sign Monitoring
- Photoacoustic and Ultrasonic Imaging
- AI in cancer detection
- Medical Imaging Techniques and Applications
- Ultrasound and Hyperthermia Applications
- Ultrasonics and Acoustic Wave Propagation
- Advanced Radiotherapy Techniques
- Radiomics and Machine Learning in Medical Imaging
- Spectroscopy Techniques in Biomedical and Chemical Research
- Digital Imaging for Blood Diseases
- Optical Imaging and Spectroscopy Techniques
- Advanced X-ray and CT Imaging
- Radiation Therapy and Dosimetry
- Advanced MRI Techniques and Applications
- Flow Measurement and Analysis
- Coronary Interventions and Diagnostics
- Blood properties and coagulation
- Cerebrovascular and Carotid Artery Diseases
- Video Surveillance and Tracking Methods
- Machine Fault Diagnosis Techniques
- Cardiovascular Disease and Adiposity
- Gene expression and cancer classification
- Anomaly Detection Techniques and Applications
Yunnan University
2017-2025
Mindray (China)
2025
Ningbo Polytechnic
2024
Shenzhen University
2017
Cornell University
2010-2011
Chinese PLA General Hospital
2011
Johns Hopkins University
2004-2007
University of California, Irvine
2005-2006
To investigate the impact of mean platelet distribution width (PDW) and volume (MPV) on prognosis patients with acute ST-segment elevation myocardial infarction (STEMI). A total 435 STEMI, admitted from November 2018 to March 2023, were included. Demographic clinical data collected medical records. Patients grouped as "High PDW" (n = 184), "Low 251), MPV" 320) 115) based cut-off values. In addition, elevated PDW MPV assigned a score 2, those in either marker received 1, without 0. Based...
Abstract Objective: Local pulse wave velocity (PWV) plays a crucial role in assessing the regional arterial elasticity. Accurate estimation of local PWV is beneficial for risk assessment and early diagnosis cardiovascular diseases. In this study, method involving incident waves based on coherent plane compounding ultrasound (IWCU) proposed to suppress reflected improve performance transit time-based estimation. 
Approach: The ultrasonic radio frequency echo signals are collected...
Idiopathic inflammatory myopathies (IIMs) are a clinically heterogeneous group of immune-mediated muscle diseases characterized by weakness and multisystem involvement. Early diagnosis IIMs can contribute to better prognosis clinical management. The classifier based on deep learning framework has proven be an effective noninvasive technique for classifying from ultrasound images. However, as the availability data is always in paucity, augmentation indispensable improve classification...
Optimizing targeted radionuclide therapy requires patient-specific estimation of organ doses. The doses are estimated from quantitative nuclear medicine imaging studies, many which involve planar whole body scans. We have previously developed the (QPlanar) processing method and demonstrated its ability to provide more accurate activity estimates than conventional geometric-mean-based (CPlanar) methods using physical phantom simulation studies. QPlanar uses maximum likelihood-expectation...
In targeted radionuclide therapy (TRT), dose estimation is essential for treatment planning and tumor response studies. Dose estimates are typically based on a time series of whole-body conjugate view planar or SPECT scans the patient acquired after administration dose. Quantifying activity in organs from these studies an part estimation. The quantitative (QPlanar) processing method involves accurate compensation image degrading factors correction organ background overlap via combination...
Complete and accurate separation of harmonic components from the ultrasonic radio frequency (RF) echo signals is essential to improve quality imaging. There are limitations in existing two commonly used methods, that is, subjectivity for high-pass filtering (S_HPF) method motion artifacts pulse inversion (S_PI) method. A novel called S_CEEMDAN, based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) algorithm, proposed adaptively separate second ultrasound...
Speckle tracking using optimum comparison frames (STO) is proposed to improve the blood flow velocity profile (BFVP) estimation based on ultrafast ultrasound with coherent plane-wave compounding. The are as far possible from reference frame image while possessing a speckle correlation above given threshold. thresholds for different kernel sizes determined via an experiment vascular-mimicking phantom. In in vitro experiments peak velocities of ranging 0.38 1.18 m/s, STO method three...
The homodyned K distribution (HK) can generally describe the ultrasound backscatter envelope statistics with parameters that have specific physical meaning. However, creating robust and reliable HK parameter estimates remains a crucial concern. maximum likelihood estimator (MLE) usually yields small variance bias in estimation. Thus, two recent studies attempted to use MLE for estimation of distribution. some statements these are not fully justified they may hinder application based on MLE....
Breast cancer is one of the cancers with highest mortality rate, which are impairing health millions women globally. Nowadays, detection method breast tumors based on ultrasound images (BUI) semi-automatic. The localization a region interest (ROI) and delineation within ROI need to be manually performed by an experienced doctor. In this work, we propose fully automatic approach semantic segmentation add contextual information in complete image interpretation avoid definition. densely...
Median ensemble empirical mode decomposition (MEEMD) represents a remarkable improvement based on the (EEMD) method for alleviating splitting and mixing problem. However, single use of median operator generates tough problems including higher reconstruction error, presence burr in products. Aiming at addressing these while catering to better time-frequency representation industrial oscillations, complementary EEMD (MCEEMD) is proposed this paper. In work, mean are skillfully combined during...
Machine vision has demonstrated effective discrimination between genuine and counterfeit cigarettes. However, the constructed identification model is limited to only a few specifications of cigarette products, its versatility constrained. Additionally, due challenges in obtaining fake cigarettes instability their features, it difficult extract representative sample features. This can severely compromise reliability method. To address these limitations, we propose novel authentication method...
The rapid development of ultrafast ultrasound imaging based on the unfocused transmission plane-wave has led to widespread attention clutter filtering technology, since discrimination between tissue and blood motion is critical for non-contrast Doppler flow. increasingly used method, i.e., singular value decomposition (SVD) essentially a black-box technique, direct rejection any vector corresponding first values will result in potential loss flow or residue activities. To cater better...
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
The fast tracking speed of Siamese-based RGB-T has garnered significant attention. However, current trackers still face certain limitations, including insufficient bounding box estimation, neglecting the interaction between positive and negative samples, complexity associated with adjusting anchors hyperparameters. To address these challenges, a novel anchor-free ranking-based localization optimized Siamese network is proposed. Firstly, to enhance estimation accuracy, boundary optimization...
Atherosclerosis is a main cause of cardiovascular and cerebrovascular diseases. Blood flow velocity profile (BFVP) usually used as an important hemodynamic index for the course atherosclerosis. Ultrasonic speckle tracking (ST) has been widely in estimation blood profile. To solve problem long time-consuming low accuracy conventional ST with global search (ST-GS), improved method based on Moth-Flame optimization (ST-MFO) proposed. Based Field II (namely, ultrasound simulator), performance...