A5101452766- Retinal Imaging and Analysis
- Retinal Diseases and Treatments
- Retinal and Optic Conditions
- Glaucoma and retinal disorders
- Radiomics and Machine Learning in Medical Imaging
- Ultrasound Imaging and Elastography
- Lung Cancer Treatments and Mutations
- Breast Lesions and Carcinomas
- Antiplatelet Therapy and Cardiovascular Diseases
- MRI in cancer diagnosis
- Transcranial Magnetic Stimulation Studies
- Ultrasonics and Acoustic Wave Propagation
- Renal cell carcinoma treatment
- Cardiac Imaging and Diagnostics
- Cancer Genomics and Diagnostics
- Connective Tissue Growth Factor Research
- Ophthalmology and Visual Impairment Studies
- Medical Imaging Techniques and Applications
- Malaria Research and Control
- Cancer, Hypoxia, and Metabolism
- Adipose Tissue and Metabolism
- Muscle Physiology and Disorders
- Mosquito-borne diseases and control
- Advanced MRI Techniques and Applications
- Functional Brain Connectivity Studies
Harbin Medical University
2011-2025
Third Affiliated Hospital of Harbin Medical University
2019-2025
Donghua University
2025
First Affiliated Hospital of Xinjiang Medical University
2025
Xinjiang Medical University
2025
Hubei University of Chinese Medicine
2025
Hubei Provincial Hospital of Traditional Chinese Medicine
2025
Jiangjin Central Hospital
2024
Nanyang Technological University
2012-2023
Vision Medicals (China)
2020-2023
As availability of precision therapies expands, a well-validated circulating cell-free DNA (cfDNA)-based comprehensive genomic profiling assay has the potential to provide considerable value as complement tissue-based testing ensure potentially life-extending are administered patients most likely benefit. Additional data supporting clinical validity cfDNA-based is necessary inform optimal use these assays in clinic. The FoundationOne®Liquid CDx pan-cancer that was recently approved by FDA....
The goal of this study was to describe the development and validation an artificial intelligence-based, deep learning algorithm (DLA) for detection referable diabetic retinopathy (DR).A DLA using a convolutional neural network developed automated vision-threatening DR (preproliferative or worse, macular edema, both). tested by set 106,244 nonstereoscopic retinal images. A panel ophthalmologists graded severity in photographs included internal data sets (n = 71,043); reference standard...
FoundationOne®CDx (F1CDx) is a United States (US) Food and Drug Administration (FDA)-approved companion diagnostic test to identify patients who may benefit from treatment in accordance with the approved therapeutic product labeling for 28 drug therapies. F1CDx utilizes next-generation sequencing (NGS)-based comprehensive genomic profiling (CGP) technology examine 324 cancer genes solid tumors. reports known likely pathogenic short variants (SVs), copy number alterations (CNAs), select...
Aim To develop a deep learning (DL) model that predicts age from fundus images (retinal age) and to investigate the association between retinal gap predicted by DL minus chronological mortality risk. Methods A total of 80 169 taken 46 969 participants in UK Biobank with reasonable quality were included this study. Of these, 19 200 11 052 without prior medical history at baseline examination used train validate for prediction using fivefold cross-validation. 35 913 remaining 917 had available...
Retinal microvasculature is a unique window for predicting and monitoring major cardiovascular diseases, but high throughput tools based on deep learning in-detail retinal vessel analysis are lacking. As such, we aim to develop validate an artificial intelligence system (Retina-based Microvascular Health Assessment System, RMHAS) fully automated segmentation quantification of the microvasculature.RMHAS achieved good accuracy across datasets with diverse eye conditions image resolutions,...
Humoral and tumoral factors collectively promote cancer-induced skeletal muscle wasting by increasing protein degradation. Although several humoral proteins, namely TNFα (tumour necrosis factor α) IL (interleukin)-6, have been shown to induce wasting, there is a lack of information regarding the that contribute atrophy during cancer cachexia. Therefore, in present study, we characterized secretome C26 colon cells identify involved wasting. In show myostatin, procachectic TGFβ (transforming...
Abstract Importance Detection of early onset neovascular age‐related macular degeneration (AMD) is critical to protecting vision. Background To describe the development and validation a deep‐learning algorithm (DLA) for detection degeneration. Design Development DLA using retrospective datasets. Participants We developed trained 56 113 retinal images an additional 86 162 from independent dataset externally validate DLA. All were non‐stereoscopic retrospectively collected. Methods The...
To describe the development and validation of a smartphone-based visual acuity (VA) test called Vision at home (V@home).Three study populations (elderly Chinese, adolescent Australian groups) underwent distance near VA testing using standard Early Treatment Diabetic Retinopathy Study (ETDRS) charts V@home device; all tests used tumbling E optotypes. were repeated with one eye, selected randomly. Distance was measured monocularly 2 m, binocularly 40 cm. Participants also completed...
Purpose: To develop and validate a fully automated program for choroidal structure analysis within 1500-µm-wide region of interest centered on the fovea (deep learning–based assessment [DCAP]). Methods: A total 2162 fovea-centered radial swept-source optical coherence tomography (SS-OCT) B-scans from 162 myopic children with cycloplegic spherical equivalent refraction ranging −1.00 to −5.00 diopters were collected DCAP. Medical Transformer network Small Attention U-Net used automatically...
Existing studies report very few factors influencing the mortality of infant and toddler heart failure patients during hospitalization. Due to its high rate, it is an important health issue. Therefore, this study aims explore hospitalization, establish predictive models, a scoring table. The ultimately included 544 cases patients. They were randomly divided into training set (380 cases) validation (164 in ratio 7:3. was then further death group survival for analysis indicators Using Lasso...
Transcranial electrical stimulation, as a means of neural modulation, is increasingly favored by researchers. The distribution and magnitude the electric field generated within brain may directly affect results modulation. Therefore, it important to clarify change trend cortical determinants induced in endodermis at different ages during adult life cycle. In this study, we used SimNIBS software perform MR image segmentation realistic head model reconstruction on 476 individuals (aged 18 88...
Abstract Background Patients with chronic insomnia are characterized by alterations in default mode network and alpha oscillations, for which the medial parietal cortex (MPC) is a key node thus potential target interventions. Methods Fifty-six adults were randomly assigned to 2 mA, alpha-frequency (10 Hz), 30 min active or sham transcranial alternating current stimulation (tACS) applied over MPC 10 sessions completed within two weeks, followed 4- 6-week visits. The connectivity of dorsal...
Fashion sketch editing is intended to modify specific attributes of a while preserving its original integrity, thus facilitating the rapid transformation designers’ concepts into tangible designs. When fashion sketches are edited, it crucial precisely control style different parts and ensure that line connections transitions smooth natural. The presence complex diverse semantic in poses challenge focus existing attribute efforts on regions. To overcome this limitation, semantically guided...
Purpose To compare the Retina-based Microvascular Health Assessment System (RMHAS) with Integrative Vessel Analysis (IVAN) for retinal vessel caliber measurement.Methods Eligible fundus photographs from Lingtou Eye Cohort Study were obtained alongside their corresponding participant data. Vascular diameter was automatically measured using IVAN and RMHAS software, intersoftware variations assessed by intra-class correlation coefficients (ICC), 95% confidence intervals (CIs). Scatterplots...
ACM Multimedia 2021 Video Relation Understanding Challenge is the third grand challenge which aims at exploring relationship of subjects and objects appearing in videos for fine-grained high-level video understanding. Given a video, relation detection model should output serious triplet subject, predicate, object corresponding trajectories subject object. The goal this task to promote research on developing semantic understanding model, so as perform complex inferences mining visual...
To provide a self-adaptive deep learning (DL) method to automatically detect the eye laterality based on fundus images.A total of 18394 images with real-world labels were used for model development and internal validation. A separate dataset 2000 labeled manually was external DL developed fine-tuned Inception-V3 network strategy. The area under receiver operator characteristic curve (AUC) sensitivity specificity confusion matrix applied assess performance. class activation map (CAM)...
Purpose To compare the inter-camera performance and consistency of various deep learning (DL) diagnostic algorithms applied to fundus images taken from desktop Topcon portable Optain cameras.Methods Participants over 18 years age were enrolled between November 2021 April 2022. Pair-wise photographs each patient collected in a single visit; once by (used as reference camera) camera (the new target camera). These analyzed three previously validated DL models for detection diabetic retinopathy...