A5011575206- Retinal Imaging and Analysis
- Intraocular Surgery and Lenses
- Ophthalmology and Visual Impairment Studies
- Glaucoma and retinal disorders
- Retinal Diseases and Treatments
- Retinal and Optic Conditions
- Corneal surgery and disorders
- Connexins and lens biology
- Artificial Intelligence in Healthcare and Education
- AI in cancer detection
- Ocular Surface and Contact Lens
- Ocular Diseases and Behçet’s Syndrome
- Corneal Surgery and Treatments
- Retinopathy of Prematurity Studies
- Optical Coherence Tomography Applications
- Digital Imaging for Blood Diseases
- Radiomics and Machine Learning in Medical Imaging
- Retinal Development and Disorders
- Retinal and Macular Surgery
- Cell Image Analysis Techniques
- Healthcare Systems and Reforms
- COVID-19 diagnosis using AI
- Ophthalmology and Visual Health Research
- Machine Learning in Healthcare
- Artificial Intelligence in Healthcare
Sun Yat-sen University
2016-2025
State Key Laboratory of Ophthalmology
2021
Ten Chen Hospital
2021
Copiah-Lincoln Community College
2021
The Seventh Affiliated Hospital of Sun Yat-sen University
2019
Affiliated Eye Hospital of Wenzhou Medical College
2016
Wenzhou Medical University
2016
CC-Cruiser is an artificial intelligence (AI) platform developed for diagnosing childhood cataracts and providing risk stratification treatment recommendations. The high accuracy of was previously validated using specific datasets. objective this study to compare the diagnostic efficacy decision-making capacity between ophthalmologists in real-world clinical settings.This multicentre randomized controlled trial performed five ophthalmic clinics different areas across China. Pediatric...
BackgroundMedical artificial intelligence (AI) has entered the clinical implementation phase, although real-world performance of deep-learning systems (DLSs) for screening fundus disease remains unsatisfactory. Our study aimed to train a clinically applicable DLS diseases using data derived from real world, and externally test model photographs collected prospectively settings in which would most likely be adopted.MethodsIn this national evidence study, we trained DLS, Comprehensive AI...
Purpose To establish and validate a universal artificial intelligence (AI) platform for collaborative management of cataracts involving multilevel clinical scenarios explored an AI-based medical referral pattern to improve efficiency resource coverage. Methods The training validation datasets were derived from the Chinese Medical Alliance Artificial Intelligence, covering healthcare facilities capture modes. labelled using three-step strategy: (1) mode recognition; (2) cataract diagnosis as...
Retinal detachment can lead to severe visual loss if not treated timely. The early diagnosis of retinal improve the rate successful reattachment and results, especially before macular involvement. Manual screening is time-consuming labour-intensive, which difficult for large-scale clinical applications. In this study, we developed a cascaded deep learning system based on ultra-widefield fundus images automated detection macula-on/off discerning. performance reliable comparable an experienced...
Abstract Utilization of digital technologies for cataract screening in primary care is a potential solution addressing the dilemma between growing aging population and unequally distributed resources. Here, we propose technology-driven hierarchical (DH screening) pattern implemented China to promote equity accessibility healthcare. It consists home-based mobile artificial intelligence (AI) screening, community-based AI diagnosis, referral hospitals. We utilize decision-analytic Markov models...
BackgroundVisual function and brain decline concurrently with aging. Notably, cataract patients often present accelerated age-related decreases in function, but the underlying mechanisms are still unclear. Optical structures of anterior segment eyes, such as lens cornea, can be readily reconstructed to improve refraction vision quality. However, effects visual restoration on human structure remain largely unexplored.MethodsA prospective, controlled clinical trial was conducted. Twenty-six...
Lattice degeneration and/or retinal breaks, defined as notable peripheral lesions (NPRLs), are prone to evolving into rhegmatogenous detachment which can cause severe visual loss. However, screening NPRLs is time-consuming and labor-intensive. Therefore, we aimed develop evaluate a deep learning (DL) system for automated identifying based on ultra-widefield fundus (UWF) images.A total of 5,606 UWF images from 2,566 participants were used train verify DL system. All classified by 3...
Background: Myopia is the leading cause of visual impairment and affects millions children worldwide. Timely annual manual optometric screenings entire at-risk population improve outcomes, but screening challenging due to lack availability training assessors economic burden imposed by screenings. Recently, deep learning computer vision have shown powerful potential for disease screening. However, these techniques not been applied large-scale myopia using ocular appearance images. Methods: We...
Medical artificial intelligence (AI) has been moving from the research phase to clinical implementation. However, most AI-based models are mainly built using high-quality images preprocessed in laboratory, which is not representative of real-world settings. This dataset bias proves a major driver AI system dysfunction. Inspired by design flow cytometry, DeepFundus, deep-learning-based fundus image classifier, developed provide automated and multidimensional sorting address this data quality...
Abstract Age is closely related to human health and disease risks. However, chronologically defined age often disagrees with biological age, primarily due genetic environmental variables. Identifying effective indicators for in clinical practice self-monitoring important but currently lacking. The lens accumulates age-related changes that are amenable rapid objective assessment. Here, using photographs from 20 96-year-olds, we develop LensAge reflect aging via deep learning. correlated...
A challenge of chronic diseases that remains to be solved is how liberate patients and medical resources from the burdens long-term monitoring periodic visits. Precise management based on artificial intelligence (AI) holds great promise; however, a clinical application fully integrates prediction telehealth computing has not been achieved, further efforts are required validate its real-world benefits. Taking congenital cataract as representative, we used Bayesian deep-learning algorithms...
Background/Aims To develop a deep learning system for automated glaucomatous optic neuropathy (GON) detection using ultra-widefield fundus (UWF) images. Methods We trained, validated and externally evaluated GON based on 22 972 UWF images from 10 590 subjects that were collected at 4 different institutions in China Japan. The InceptionResNetV2 neural network architecture was used to the system. area under receiver operating characteristic curve (AUC), sensitivity specificity assess...
BackgroundApproximately 1 in 33 newborns is affected by congenital anomalies worldwide. We aimed to develop a practical model for identifying infants with high risk of cataracts (CCs), which the leading cause avoidable childhood blindness.MethodsThis case-control study was performed Zhongshan Ophthalmic Center and involved 2005 subjects, including 1274 children CCs 731 healthy controls. The CC identification models were established based on birth conditions, family medical history,...
Purpose: To develop and evaluate a deep learning (DL) system for retinal hemorrhage (RH) screening using ultra-widefield fundus (UWF) images. Methods: A total of 16,827 UWF images from 11,339 individuals were used to the DL system. Three experienced retina specialists recruited grade independently. independent data sets 3 different institutions validate effectiveness The set Zhongshan Ophthalmic Center (ZOC) was selected compare classification performance general ophthalmologists. heatmap...
Ischemic retinal diseases (IRDs) are a series of common blinding that depend on accurate fundus fluorescein angiography (FFA) image interpretation for diagnosis and treatment. An artificial intelligence system (Ai-Doctor) was developed to interpret FFA images. Ai-Doctor performed well in phase identification (area under the curve [AUC], 0.991-0.999, range), diabetic retinopathy (DR) branch vein occlusion (BRVO) (AUC, 0.979-0.992), non-perfusion area segmentation (Dice similarity coefficient...
Background/aims The aim of this study was to develop and evaluate digital ray, based on preoperative postoperative image pairs using style transfer generative adversarial networks (GANs), enhance cataractous fundus images for improved retinopathy detection. Methods For eligible cataract patients, colour photographs (CFP) ultra-wide field (UWF) were captured. Then, both the original CycleGAN a modified (C 2 ycleGAN) framework adopted generation quantitatively compared Frechet Inception...
A review of 6 years hospitalization charts from Zhongshan Ophthalmic Center (ZOC) revealed that congenital cataracts (CC) accounted for 2.39% all cataract in-patient cases and the age at surgery was decreasing before establishment Childhood Cataract Program Chinese Ministry Health (CCPMOH) in December 2010. We aimed to investigate data 4 (January 2011 2014) following CCPMOH, compared, combined with previous study period 2005 2010) generate a 10-year overview hospital-based prevalence...
Abstract This study is to evaluate the visual outcome and identify its crucial related factors in children undergoing cataract surgery for bilateral total congenital (CC). prospective included consecutive patients primary at Zhongshan Ophthalmic Center (ZOC), Guangzhou, China from Jan 2010 May 2014. Visual was estimated by best-corrected acuity (BCVA) last follow-up. Potential factors, including gender, age follow-up, surgery, surgical procedure, postoperative complications (PCs), frequency...
Purpose: To investigate tear film optical quality dynamics by analyzing the postblink temporal changes of objective scatter index (OSI). Methods: A total 109 myopic subjects without symptoms dry eye and 32 diagnosed with disease were recruited in this cross-sectional study. The right for each subject was analyzed. Serial measurements OSI performed 20 seconds interval 0.5 second using a double-pass instrument, 10 successive nonblinking immediately after blink selected to analyze dynamics....