Free papers, posters, e-posters and videos are all welcome. Online submission is open until Jul 31, 2024 (Wednesday). Only the abstract submitter will be notified of the results.
Free papers, posters, e-posters and videos are all welcome. Online submission is open until Jul 31, 2024 (Wednesday). Only the abstract submitter will be notified of the results.
苏州艾尔兴医疗技术有限公司，成立于2014年3月，国家高新技术企业；江苏省民营科技企业；科技型中小企业；苏州市瞪羚计划入库企业；苏州市艾尔兴青少年近视防控工程技术研究中心。专注研究青少年视力健康问题的解决方案，旗下4家医疗器械生产工厂；1家互联网医院，投资1家海外分公司。
企业愿景：让天下青少年无近视，注册商标“艾尔兴”“eyerising”，是潜心数十年打造的视康品牌。
公司科研队伍强大，由浙江大学苏州工业研究院视力健康研究中心作技术支持。拥有眼科权威专家、眼科主任医生、电子、光学、机械、自动化及通讯等多方面专业研究人员。主要从事新型眼科医疗器械方向的技术开发应用。
国际眼科权威专家：何明光，二级教授，博士生导师，香港理工大学视觉科学研究中心主任，广州中山大学中山眼科教授，国家重点实验室杰出PI ，墨尔本大学眼科教授，为公司首席医学官，由他带领的医学研发团队，为公司作医学技术支持。
医学部有3位常驻眼科主任医生。软硬件开发团队共23位成员，其中硕士6人，本科14人，其中3位是姑苏重点产业紧缺人才。
目前已获授权专利118件，其中发明8件（美国1件+国内7件）、实用新型95件、外观设计15件；软著6件；申请中20件：发明12件（国外4件），实新8件。
独立开发了一系列基于医疗物联网的高精尖技术方案，包括青少年视力自测系统、近视弱视综合治疗仪、视力训练引导仪；青少年视力数据云服务平台，搭载艾尔兴互联网医院，可实现线上问诊、视力数据分析、近视辅助治疗、数据存储、回溯分析等功能，对青少年视力问题，可实现早发现，早控制，早治疗的目的。
核心产品：艾尔兴近视弱视治疗仪，又名哺光仪（取自补充光营养，近视不再涨的理念）拥有国内医疗器械注册证，并拿到欧盟CE、英国、澳大利亚、新西兰、马来西亚、土耳其、越南，多个国家的注册证。
产品运用低强度单波长红光控制近视技术，原理及效果：通过从户外太阳光中分离出对眼睛有益的特定波长红光，照射在视网膜上，促进多巴胺的分泌，同时增加脉络膜血管网含氧量，改善眼底血液微循环，以实现抑制眼轴过度增长，从根本上控制近视增涨的目的。
国内眼科排名第一的广州中山眼科中心的临床试验数据显示，坚持使用艾尔兴哺光仪能有效控制眼轴增长。且使用方便，仅需1天2次，1次3分钟。
科研十余年，已入驻全国多家知名大型眼科专业医疗机构并开展临床科研合作，如广州中山眼科、四川大学华西医院、上海眼病防治中心、南京医科大学附属眼科医院等。全国数十家眼科研究单位用艾尔兴产品做的临床研究，在国内外期刊上已发表的科研文献，将近20余篇。
2022年7月由全国38位权威眼科专家形成了：《重复低强度红光照射辅助治疗儿童青少年近视专家共识》。
2022年，参与国家重点研发计划“常见多发病防治研究”专项“常见致盲眼病的生物标志物和数字智能化精准防治研究”项目，课题：病理性近视发生、进展和致盲性并发症的早期识别与干预。
2023年参与：国标《眼保健服务安全规范》起草。
在全国建立了20多个省级视力服务中心，上百个地市级视力服务中心，形成了全国营销网络，注册用户16万+。是华厦集团、上海新视界集团、爱尔眼科、理想眼科的供应商。
Intalight was founded by a group of scientists and industry veterans of Silicon Valley in 2014. In 2015, the company’s base of operations moved to mainland China. There are now three sites in Silicon Valley, Shanghai and Luoyang. Intalight released the first Swept-Source OCT device that combines Deep imaging depth, Rapid sweeping speed, Extensive scan range, Accurate lesion detection and Multimodal imaging capabilities, abbreviated as DREAM OCT™. To date, over 350 units have been installed in China, more than 140 papers have been published in peer-reviewed journals based on the DREAM OCT™ technology.
Moderators: Yuanbo LIANG & Yih Chung THAM
| TIME | TITLE | PRESENTER |
| 17:00-17:07 | EyeGPT: Ophthalmic Assistant with Large Language Models | Xiaolan CHEN |
| 17:07-17:14 | Prospective Evaluation of Continually Pre-trained Models for Endocrine and Metabolic Diseases Screening via Retinomics: A Retrospective, Prospective, Multicentre Study | Xiayin ZHANG |
| 17:14-17:21 | Towards Regulatory Generative AI in Ophthalmology Healthcare: A Security and Privacy Perspective | Yueye WANG |
| 17:21-17:28 | Comparative Analysis of Large Language Models for Cataract Care | Harry SU |
| 17:28-17:35 | General and Chinese-specific Large Language Models’ Performance for Myopia-related Queries in China | Zehua JIANG |
| 17:35-17:42 | FFA-GPT: Automatic Fundus Fluorescein Angiography Image Interpretation with Large Language Models | Xiaolan CHEN |
| 17:42-17:49 | The Use of Large Language Models in Ophthalmology: A Scoping Review on Current Use-Cases and the Potential Pitfalls | Alva LIM |
| 17:49-17:56 | Comparison of Generative AI-Based Learning versus Text-Only Learning in Ophthalmology among Medical Students – a Non-Randomized Study | Tharini SENTHAMIZH |
Moderators: Benjamin XU & Xinyuan ZHANG
| TIME | TITLE | PRESENTER |
| 11:00-11:08 | ChatFFA: An Interactive Chat System for Visual Question Answering on Fundus Fluorescein Angiography Images | Xiaolan CHEN |
| 11:08-11:16 | Unveiling Choroidal Vascular Fingerprints: Automatic Segmentation and Multi-dimensional Feature Quantification on Indocyanine Green Angiography via Deep Learning | Ruoyu CHEN |
| 11:16-11:24 | Using Optical Coherence Tomography to Evaluate Diabetic Retinal Neurodegeneration in Patients with Referable and Non-referable Diabetic Retinopathy | Adrian LEE |
| 11:24-11:32 | Novel Quantitative Analysis of Anterior Chamber Inflammation Based on a Deep Learning Model Using Anterior Segment Optical Coherence Tomography Images for Diagnosis and Precise Assessment of Intraocular Inflammatory Diseases | Ye DAI |
| 11:32-11:40 | Quantifying Macular Cone Mosaic Metrics by Adaptive Optics Retinal Camera to Enhance Diagnosis Efficiency in High Myopia Patients | Ke-Yu LIU |
| 11:40-11:48 | Hessian-Attentive feature enhanced convolutional neural networkfor OCT image denoising | Jie GAO |
| 11:48-11:56 | Assistance of Artificial Intelligence in Diagnosis of Vitreoretinal Lymphoma on Optical Coherence Tomography | Aidi LIN |
| 11:56-12:04 | Detection of Stardust Sign in SSOCT Images Using Deep Learning | Mao TANABE |
Moderators: Padmaja RANI & Raba THAPA
| TIME | TITLE | PRESENTER |
| 09:00-09:08 | An Integrated Model to Use AI and Teleophthalmology to Screen Glaucoma in a Low Resource Setting | Malinda DE SILVA |
| 09:08-09:16 | Supporting Diabetic Macular Edema Triage Screening by a Deep Learning-based OCT Image Analysis: a Prospective Study | Shuyi ZHANG |
| 09:16-09:24 | Ultra-Widefield Fundus Imaging for Diabetic Retinopathy Challenge 2024 (UWF4DR) | Bin SHENG |
| 09:24-09:32 | Converting Ultra-Widefield Fundus Photography to Ultra-Widefield Fluorescein Angiography via UWAFA-GAN for Diabetic Retinopathy Screening | Zhicong XU |
| 09:32-09:40 | Effectiveness, Cost-Effectiveness and Cost-Utility of a Tiered Artificial Intelligence-Enabled Diabetic Eye Care (AID-Eye) Model Starting from Primary Health Care in Rural China | Xiaochen MA |
| 09:40-09:48 | An Oculomics Approach: Retinal Vascular Characteristics Modeling for High-Precision Diagnosis of Mild Non-Proliferative Diabetic Retinopathy | Peng XIAO |
| 09:48-09:56 | Assessment of Mild Cognitive Impairment via a Retinal-Imaging-Based Deep Learning Model through Majority Voting | Herbert HUI |
| 09:56-10:04 | Development and Validation of a Deep Learning Platform for Detecting Multiple Retinal Fundus Diseases | Mingzhi ZHANG |
| 10:04-10:12 | Development and Validation of a Deep Learning Algorithm for Detection of Orbital Disease Using Ocular Images from Multi-center Populations | Chaoyu LEI |
| 10:12-10:20 | Development and Validation of a Deep Learning Model to Predict the Occurrence and Severity of Retinopathy of Prematurity | Qiaowei WU |
| 10:20-10:28 | Mild Cognitive Impairment Screening Based on FusionNet and Ensemble Learning-based Artificial Intelligence System for Alzheimer’s Disease | Andy NG |
Moderators: Lingping CEN & Masahiro MIURA
| TIME | TITLE | PRESENTER |
| 17:00-17:08 | EyeCLIP: A Visual–Language Foundation Model for Multi-Modal Ophthalmology Image Analysis | Mingguang HE |
| 17:08-17:16 | Fine-tuning RETFound for Glaucoma Detection from Color Fundus Photographs | Hin Yin CHAN |
| 17:16-17:24 | Augmenting Glaucoma Screening: Real-World Validation of Medios AI Across Multiple Ethnicities and Device-Agnostic Capabilities | Divya RAO |
| 17:24-17:32 | Artificial Intelligence-based database for prediction of protein structure and their alterations in ocular diseases | Mingzhi ZHANG |
| 17:32-17:40 | Efficiency and Safety of Automated Label Cleaning on Multimodal Retinal Images | Tian LIN |
| 17:40-17:48 | Digital Ruler of Strabismus: Smartphone-Based Artificial Intelligence for Strabismus Measurement and Diagnosis | Ruixin WANG |
| 17:48-17:56 | Empowering Universal Self-Screening for Malignant Ocular Rare Tumors Using Smartphones | Shaowei BI |
Moderators: Tin AUNG & Chun ZHANG
| TIME | TITLE | PRESENTER |
| 13:00-13:09 | Digital Gonioscopy Based on Three-dimensional Anterior-Segment OCT: An International Multicenter Study | Zefeng YANG |
| 13:09-13:18 | Universal Bluetooth Integrated Electronic Eyedrop Sleeve : A Novel Compliance Monitoring System for Glaucoma Patients | Neeraj ISRANI |
| 13:18-13:27 | Glaucoma Upgrade Intervention Decision-making Enhancer (GUIDE): A Machine Learning-based Telemedicine Solution | Kezheng XU |
| 13:27-13:36 | Comparative Study on the Performance of Melbourne RapidFields Web-browser Perimeter to the Humphrey Field Analyzer in Chinese Glaucoma Patients | De-Fu CHEN |
| 13:36-13:45 | Predicting Optic Nerve Head Biomechanical Response to Intraocular Pressure Using Patient-Specific Modeling and Machine Learning | Xiaofei WANG |
| 13:45-13:54 | Visual Field Patterns of Open-Angle Glaucoma and Potential Associations with Long-term Progression Risks: A Machine-Learning Perspective | Yu-Tzu PING |
| 13:54-14:03 | Ciliary Process to Lens Distance in Primary Angle-Closure Glaucoma and its Relationship with Shallow Anterior Chamber: Insights from Ocular Magnetic Resonance Imaging | Yuanbo LIANG |
| 14:03-14:12 | Optic Nerve Head Abnormalities in Non-pathologic High Myopia and the Relationship with Visual Field | Jingwen JIANG |
| 14:12-14:21 | Optic Nerve Head Perfusion in Lateral Decubitus Position in Patients with Asymmetrical Normal Tension Glaucoma and Obstructive Sleep Apnoea | Tin A TUN |
| 14:21-14:30 | Research on the rehabilitative effects of long-term virtual reality visual training on glaucoma-related visual function impairments | Yan LU |