A5101744105- Radiomics and Machine Learning in Medical Imaging
- Advanced X-ray and CT Imaging
- Advanced Neuroimaging Techniques and Applications
- Colorectal Cancer Surgical Treatments
- Advanced MRI Techniques and Applications
- COVID-19 diagnosis using AI
- Cardiac Imaging and Diagnostics
- Atomic and Subatomic Physics Research
- Cerebrospinal fluid and hydrocephalus
- Fibromyalgia and Chronic Fatigue Syndrome Research
- MRI in cancer diagnosis
- Reproductive System and Pregnancy
- Musculoskeletal pain and rehabilitation
- Genetic Neurodegenerative Diseases
- Ectopic Pregnancy Diagnosis and Management
- Colorectal Cancer Screening and Detection
- Mitochondrial Function and Pathology
- Spinal Dysraphism and Malformations
- Gynecological conditions and treatments
- Photoacoustic and Ultrasonic Imaging
- AI in cancer detection
- Photochromic and Fluorescence Chemistry
- Brain Tumor Detection and Classification
- Medical Image Segmentation Techniques
- Myofascial pain diagnosis and treatment
Central Hospital of Wuhan
2020-2024
Deyang Stomatological Hospital
2024
General Hospital of Central Theater Command
2023-2024
Siemens Healthcare (United States)
2022-2023
The First People's Hospital of Xiaoshan District, Hangzhou
2023
Sixth Affiliated Hospital of Sun Yat-sen University
2018-2021
Sun Yat-sen University
2018-2021
Siemens Healthcare (Germany)
2021
Chinese People's Liberation Army
2020
Augusta University
2011
VPS35, a major component of the retromer complex, is important for endosome-to-Golgi retrieval membrane proteins. Although implicated in Alzheimer’s disease (AD), how VPS35 regulates AD-associated pathology unknown. In this paper, we show that hemizygous deletion Vps35 Tg2576 mouse model AD led to earlier-onset AD-like phenotypes, including cognitive memory deficits, defective long-term potentiation, and impaired postsynaptic glutamatergic neurotransmission young adult age. These deficits...
BackgroundAccurate lymph nodes (LNs) assessment is important for rectal cancer (RC) staging in multiparametric magnetic resonance imaging (mpMRI). However, it incredibly time-consumming to identify all the LNs scan region. This study aims develop and validate a deep-learning-based, fully-automated node detection segmentation (auto-LNDS) model based on mpMRI.MethodsIn total, 5789 annotated (diameter ≥ 3 mm) mpMRI from 293 patients with RC single center were enrolled. Fused T2-weighted images...
Abstract Background and Hypothesis Despite the well-documented structural functional brain changes in schizophrenia, potential role of glymphatic dysfunction remains largely unexplored. This study investigates system’s function utilizing diffusion tensor imaging (DTI) to analyze water along perivascular space (ALPS), examines its correlation with clinical symptoms. Study Design A cohort consisting 43 people schizophrenia 108 healthy controls was examined. We quantified metrics x-, y-, z-axis...
Abstract To explore the possibility of predicting clinical types Corona-Virus-Disease-2019 (COVID-19) pneumonia by analyzing non-focus area lung in first chest CT image patients with COVID-19 using automatic machine learning (Auto-ML). 136 moderate and 83 severe were selected from pneumonia. The laboratory data collected for statistical analysis. texture features Non-focus extracted, then classification model was constructed these based on Auto-ML method radiomics, under curve(AUC), true...
We aimed to develop a radiomic model based on pre-treatment computed tomography (CT) predict the pathological complete response (pCR) in patients with rectal cancer after neoadjuvant treatment and tried integrate our magnetic resonance imaging (MRI)-based signature.This was secondary analysis of FOWARC randomized controlled trial. Radiomic features were extracted from portal venous-phase contrast-enhanced CT images 177 cancer. Patients randomly allocated primary validation cohort. The least...
Background Four‐dimensional (4D) flow MRI allows for the quantification of complex patterns; however, its clinical use is limited by inherently long acquisition time. Compressed sensing (CS) an acceleration technique that provides substantial reduction in Purpose To compare intracardiac measurements between conventional and CS‐based highly accelerated 4D acquisitions. Study Type Prospective. Subjects Fifty healthy volunteers (28.0 ± 7.1 years, 24 males). Field Strength/Sequence Whole heart...
In 2020, the new type of coronal pneumonitis became a pandemic in world, and has firstly been reported Wuhan, China. Chest CT is vital component diagnostic algorithm for patients with suspected or confirmed COVID-19 infection. Therefore, it necessary to conduct automatic accurate detection by chest CT.The clinical classification pneumonia was predicted Radiomics using CT.From cases our institution, 136 moderate 83 severe were screened, their laboratory data on admission collected statistical...
To compare volumetric and functional parameters of the atria derived from highly accelerated compressed sensing (CS)-based cine sequences in comparison to conventional (Conv) imaging.CS Conv were acquired 101 subjects (82 healthy volunteers (HV) 19 patients with heart failure reduced ejection fraction (HFrEF)) using a 3T MR scanner this single-center study. Time-volume analysis left (LA) right (RA) performed both evaluate atrial volumes function (total, passive, active emptying fraction)....
Abstract To study the classification efficiency of using texture feature machine learning method in distinguishing solid lung adenocarcinoma (SADC) and tuberculous granulomatous nodules (TGN) that appear as (SN) non-enhanced CT images. 200 patients with SADC TGN who underwent thoracic examination from January 2012 to October 2019 were included study, 490 eigenvalues 6 categories extracted lesions images these for learning, prediction model is established by relatively best classifier...
Abstract Background Although neuroanatomical studies correlated to fibromyalgia (FM) are gaining increasing interest, the cortical morphology of patients largely unknown, and data on gyrification scarce. The objective present study is assess in female with FM compared healthy controls (HC) using surface-based morphometry (SBM) analysis magnetic resonance imaging (MRI). Methods T1-MRIs clinical 20 HC subjects were obtained from a public set via OpenNeuro. For each subject, surface parameters...
Background Recurrent pregnancy loss (RPL) frequently links to a prolonged endometrial receptivity (ER) window, leading the implantation of non-viable embryos. Existing ER assessment methods face challenges in reliability and invasiveness. Radiomics medical imaging offers non-invasive solution for analysis, but complex, non-linear radiomic-ER relationships RPL require advanced analysis. Machine learning (ML) provides precision interpreting these datasets, although research integrating...
Background Recurrent pregnancy loss (RPL) poses significant challenges in clinical management due to an unclear etiology over half the cases. Traditional screening methods, including ultrasonographic evaluation of endometrial receptivity (ER), have been debated for their efficacy identifying high-risk individuals. Despite potential artificial intelligence, notably deep learning (DL), enhance medical imaging analysis, its application ER assessment RPL risk stratification remains...