A5022631295- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- Photoacoustic and Ultrasonic Imaging
- Ultrasound Imaging and Elastography
- Cerebrovascular and Carotid Artery Diseases
- Ultrasound and Hyperthermia Applications
- Cardiovascular Health and Disease Prevention
- Thyroid Cancer Diagnosis and Treatment
- Infrared Thermography in Medicine
- Cardiac Imaging and Diagnostics
- Liver Disease Diagnosis and Treatment
- Prostate Cancer Diagnosis and Treatment
- Advanced X-ray and CT Imaging
- Fetal and Pediatric Neurological Disorders
- Rheumatoid Arthritis Research and Therapies
- MRI in cancer diagnosis
- Digital Radiography and Breast Imaging
- Orthopedic Surgery and Rehabilitation
- Prostate Cancer Treatment and Research
- Shoulder Injury and Treatment
- Artificial Intelligence in Healthcare and Education
- Prenatal Screening and Diagnostics
- Congenital Heart Disease Studies
- Angiogenesis and VEGF in Cancer
- Shoulder and Clavicle Injuries
Jinan University
2016-2025
Southern University of Science and Technology
2018-2025
ShenZhen People’s Hospital
2017-2024
Second Hospital of Shandong University
2021-2023
Qilu Hospital of Shandong University
2018-2021
Western University of Health Sciences
2019-2020
Pomona College
2019
General Hospital of Guangzhou Military Command
2017
People’s Hospital of Rizhao
2009-2011
Elastography ultrasound (EUS) imaging is a vital modality. The current use of EUS faces many challenges, such as vulnerability to subjective manipulation, echo signal attenuation, and unknown risks elastic pressure in certain delicate tissues. hardware requirement also hinders the trend miniaturization equipment. Here we show cost-efficient solution by designing deep neural network synthesize virtual (V-EUS) from conventional B-mode images. A total 4580 breast tumor cases were collected 15...
The Segment Anything Model (SAM) is the first foundation model for general image segmentation. It has achieved impressive results on various natural segmentation tasks. However, medical (MIS) more challenging because of complex modalities, fine anatomical structures, uncertain and object boundaries, wide-range scales. To fully validate SAM's performance data, we collected sorted 53 open-source datasets built a large dataset with 18 84 objects, 125 object-modality paired targets, 1050K 2D...
The differentiation between benign and malignant breast tumors extends beyond morphological structures to encompass functional alterations within the nodules. combination of photoacoustic (PA) imaging radiomics unveils insights intricate details that are imperceptible naked eye. This study aims assess efficacy PA in cancer radiomics, focusing on impact peritumoral region size radiomic model accuracy. From January 2022 November 2023, data were collected from 358 patients with nodules,...
Smoking is a major preventable risk factor for atherosclerosis. However, the causative link between cigarette smoke and atherosclerosis remains to be established. The objective of this study characterize role GTP cyclohydrolase 1 (GTPCH1), rate-limiting enzyme de novo tetrahydrobiopterin (BH4) synthesis, in smoking-accelerated mechanism involved. In vitro, human umbilical vein endothelial cells were treated with nicotine, component smoke, which reduced mRNA protein levels GTPCH1 led...
Contributing to severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) clinical treatment, a drug library encompassing approximately 3,142 clinical-stage or FDA-approved small molecules is profiled identify the candidate therapeutic inhibitors targeting nucleocapsid protein (N) and spike (S) of SARS-CoV-2.16 screened candidates with higher binding affinity are evaluated via virtual screening. Comparing those under trial/temporarily used antivirus drugs (i.e., umifenovir, lopinavir),...
Abstract Background The application of artificial intelligence (AI) in the ultrasound (US) diagnosis breast cancer (BCa) is increasingly prevalent. However, impact US-probe frequencies on diagnostic efficacy AI models has not been clearly established. Objectives To explore using US-video variable US screening. Methods This study utilized different frequency US-probes (L14: range: 3.0-14.0 MHz, central 9 L9: 2.5-9.0 6.5 MHz and L13: 3.6-13.5 8 L7: 3-7 4.0 linear arrays) to collect...
We evaluated the diagnostic performance of a multimodal deep-learning (DL) model for ovarian mass differential diagnosis. This single-center retrospective study included 1,054 ultrasound (US)-detected tumors (699 benign and 355 malignant). Patients were randomly divided into training (n = 675), validation 169), testing 210) sets. The was developed using ResNet-50. Three DL-based models proposed benign-malignant classification these lesions: single-modality that only utilized US images;...
To evaluate if an automatic classification of rheumatoid arthritis (RA) metacarpophalangeal joint conditions in ultrasound images is feasible by deep learning (DL) method, to provide a more objective, automated, and fast way RA diagnosis clinical setting.DenseNet-based DL model was used both training testing are implemented TensorFlow 1.13.1 with Keras libraries. The area under curve (AUC), accuracy, sensitivity, specificity values 95% CIs were reported. statistical analysis performed using...
A novel dual-targeted cationic microbubbles help to improve gene transfection efficiency.
Abstract Background A noninvasive left ventricular (LV) pressure-strain loop (PSL) provides a new method to quantify myocardial work (MW) by combining global longitudinal strain (GLS) and LV pressure, which exerts potential advantages over traditional GLS. We studied the PSL MW in patients with type 2 diabetes mellitus (T2DM). Methods This cross-sectional study included 201 subjects (54 healthy controls 147 T2DM patients) who underwent complete two-dimensional echocardiography (2DE),...
Abstract Purpose To assess the diagnostic performance of Ultrasound Attenuation Analysis (USAT) in diagnosis and grading hepatic steatosis patients with non-alcoholic fatty liver disease (NAFLD) using Controlled Parameters (CAP) as a reference. Materials methods From February 13, 2023, to September 26, participants underwent CAP USAT examinations on same day. We used manufacturer-recommended thresholds categorize stages steatosis: stage 1 (mild) − 240 dB/m, 2 (moderate) 265 3 (severe) 295...
Accurate assessment of Rheumatoid Arthritis (RA) activity remains a challenge. Multimodal photoacoustic/ultrasound (PA/US) joint imaging emerges as novel modality capable depicting microvascularization and oxygenation levels in inflamed joints associated with RA. However, the scarcity large-scale studies limits exploration correlating status disease activity. This study aimed to explore correlation between multimodal PA/US scores RA activity, assessing its clinical applicability managing In...