基于公共眼底图像数据库及玻璃体腔注药中心临床采集的眼底图像构建机器学习模型实现眼底疾病的预测

注册号:

Registration number:

ChiCTR2600126676 

最近更新日期:

Date of Last Refreshed on:

2026-06-13 12:01:57 

注册时间:

Date of Registration:

2026-06-13 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于公共眼底图像数据库及玻璃体腔注药中心临床采集的眼底图像构建机器学习模型实现眼底疾病的预测

Public title:

Fundus Disease Prediction using Public database and Hospital Fundus Images from Intravitreal injections center using machine learning.

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于公共眼底图像数据库及玻璃体腔注药中心临床采集的眼底图像构建机器学习模型实现眼底疾病的预测

Scientific title:

Fundus Disease Prediction using Public database and Hospital Fundus Images from Intravitreal injections center using machine learning.

研究课题代号(代码):

Study subject ID:

在二级注册机构或其它机构的注册号:

The registration number of the Partner Registry or other register:

申请注册联系人:

刘相缨 

研究负责人:

任新军 

Applicant:

Liu Xiangying 

Study leader:

Ren Xinjun 

申请注册联系人电话:

Applicant telephone:

+86 22 86428838

研究负责人电话:

Study leader's
telephone:

+86 22 86428838

申请注册联系人传真 :

Applicant Fax:

研究负责人传真:

Study leader's fax:

申请注册联系人电子邮件:

Applicant E-mail:

X.Y_Liu@outlook.com

研究负责人电子邮件:

Study leader's E-mail:

zlrxjrsy@126.com

申请单位网址(自愿提供):

Applicant website(voluntary supply):

研究负责人网址(自愿提供):

Study leader's website(voluntary supply):

申请注册联系人通讯地址:

中国天津市西青区高新技术产业开发区华苑产业区榕苑路1号

研究负责人通讯地址:

中国天津市西青区高新技术产业开发区华苑产业区榕苑路1号

Applicant address:

1 Rongyuan Road, Huayuan Industrial Zone, High-tech Industrial Development Zone, Xiqing District, Tianjin, China

Study leader's address:

1 Rongyuan Road, Huayuan Industrial Zone, High-tech Industrial Development Zone, Xiqing District, Tianjin, China

申请注册联系人邮政编码:

Applicant postcode:

研究负责人邮政编码:

Study leader's postcode:

申请人所在单位:

天津医科大学眼科医院

Applicant's institution:

Eye Hospital of Tianjin Medical University

研究负责人所在单位:

天津医科大学眼科医院

Affiliation of the Leader:

Tianjin Medical University Eye Hospital

是否获伦理委员会批准:

Approved by ethic committee:

Yes

伦理委员会批件文号:

Approved No. of ethic committee:

2026KY-29

伦理委员会批件附件:

Approved file of Ethical Committee:

查看附件View

批准本研究的伦理委员会名称:

天津医科大学眼科医院医学伦理委员会

Name of the ethic committee:

Medical Ethics Committee of Tianjin Medical University Eye Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2026-04-14 00:00:00

伦理委员会联系人:

陈卓

Contact Name of the ethic committee:

Chen Zhuo

伦理委员会联系地址:

中国天津市西青区高新技术产业开发区华苑产业区榕苑路1号

Contact Address of the ethic committee:

1 Rongyuan Road, Huayuan Industrial Zone, High-tech Industrial Development Zone, Xiqing District, Tianjin, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 22 86428817

伦理委员会联系人邮箱:

Contact email of the ethic committee:

1006425222@qq.com

研究实施负责(组长)单位:

天津医科大学眼科医院

Primary sponsor:

Tianjin Medical University Eye Hospital

研究实施负责(组长)单位地址:

中国天津市西青区高新技术产业开发区华苑产业区榕苑路1号

Primary sponsor's address:

1 Rongyuan Road, Huayuan Industrial Zone, High-tech Industrial Development Zone, Xiqing District, Tianjin, China

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

天津

市(区县):

Country:

China

Province:

Tianjin

City:

单位(医院):

天津医科大学眼科医院

具体地址:

中国天津市西青区高新技术产业开发区华苑产业区榕苑路1号

Institution
hospital:

Tianjin Medical University Eye Hospital

Address:

1 Rongyuan Road, Huayuan Industrial Zone, High-tech Industrial Development Zone, Xiqing District, Tianjin, China

经费或物资来源:

自筹

Source(s) of funding:

Self-funded

研究疾病:

糖尿病性视网膜病,视网膜静脉阻塞,黄斑水肿,脉络膜新生血管,年龄相关性黄斑变性  

Target disease:

Diabetic retinopathy, retinal vein occlusion, macular edema, choroidal neovascularization, age-related macular degeneration

研究疾病代码:

Target disease code:

研究类型:

诊断试验

Study type:

Diagnostic test

研究所处阶段:

其它 

Study phase:

N/A

研究设计:

诊断试验诊断准确性 

Study design:

Diagnostic test for accuracy 

研究目的:

依托眼底图像的直观病理特征与AI技术的高效识别优势,构建精准、高效、可推广的眼底疾病AI诊断模型,解决当前眼底疾病诊疗中存在的筛查效率低、漏诊误诊率高、基层诊疗资源不足等突出问题,为眼底疾病的早期干预、精准诊疗提供技术支撑。 具体目的: 1. 收集整理规范的眼底图像数据集,涵盖年龄相关性黄斑变性、视网膜静脉阻塞等常见眼底疾病及正常眼底图像,进行标注、预处理与数据增强,构建高质量、多样化的训练样本库,为模型训练提供可靠数据基础。 2. 优化AI模型结构,结合深度学习算法,提升模型对眼底病变特征的提取能力,实现对多种常见眼底疾病的精准分类、病变定位及严重程度分级,降低漏诊、误诊率,确保诊断准确率接近专业眼科医师水平。 3. 验证模型的实用性与泛化能力,通过眼底图像数据测试,优化模型参数,提升模型在不同设备、不同人群眼底图像中的适配性。 4. 推动模型的临床转化与基层应用,助力基层医疗机构突破专业医师短缺的局限,实现眼底疾病的大规模快速筛查,推动防盲治盲工作下沉,最终降低眼底疾病致盲率,为眼底疾病精准诊疗模式创新提供实践依据。  

Objectives of Study:

Relying on the intuitive pathological features of fundus images and the efficient recognition advantages of artificial intelligence technology, this study aims to construct an accurate, efficient and scalable AI diagnosis model for fundus diseases. It addresses prominent problems in current fundus disease diagnosis and treatment, including low screening efficiency, high rates of missed and misdiagnosis, and insufficient primary medical resources, so as to provide technical support for early intervention and precise diagnosis and treatment of fundus diseases.

药物成份或治疗方案详述:

 

Description for medicine or protocol of treatment in detail:

 

纳入标准:

Inclusion criteria

排除标准:

1.因屈光介质混浊、无法配合成像或既往接受过视网膜手术导致图像质量不佳;

Exclusion criteria:

1.Images with poor quality caused by refractive media opacity, inability to cooperate with imaging examination, or previous retinal surgery.

研究实施时间:

Study execute time:

From 2026-06-20 00:00:00 To 2027-06-30 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-06-20 00:00:00 To 2026-08-30 00:00:00

诊断试验:

Diagnostic Tests:

金标准或参考标准(即可准确诊断某疾病的单项方法或多项联合方法,在本研究中用于诊断是否有该病的临床参考标准):

专业医师对眼底图像的诊断

Gold Standard or Reference Standard (The clinical reference standards required to establish the presence or absence of the target condition in the tested population in present study):

Expert panel diagnosis based on fundus images

指标试验(即本研究的待评估诊断试验,无论为方法、生物标志物或设备,均请列出名称):

AI 眼底疾病诊断模型

Index test:

AI fundus disease diagnosis model

目标人群(可以是某种疾病患者或正常人群,详细描述其疾病特征,注意应纳入符合分布特点的全序列病例,具有良好的代表性)

需进行玻璃体腔注药的患者

例数:

Sample size:

500

Target condition (The target condition is a particular disease or disease stage that the index test will be intended to identify. Please specify the characteristics in detail; the population should has a complete spectrum and good representative):

Patients who need to receive intravitreal injections

容易混淆的疾病人群(即与目标疾病不易区分的一种或多种不同疾病,应避免采用正常人群对照的病例-对照设计):

例数:

Sample size:

0

Population with condition difficult to distinguish from the target condition, the normal population in a case-control study design should be avoid:

None

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

天津 

市(区县):

 

Country:

China

Province:

Tianjin

City:

单位(医院):

天津医科大学眼科医院 

单位级别:

三级甲等 

Institution
hospital:

Tianjin Medical University Eye Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

不可分级图像的比例及质量不佳的原因

指标类型:

次要指标

Outcome:

The proportion and poor quality of non-gradable images

Type:

Secondary indicator

测量时间点:

基线

测量方法:

AI识别

Measure time point of outcome:

Baseline

Measure method:

AI recognition

指标中文名:

与眼科医生分级相比,在EyeRoboFC图像上检测可转诊糖尿病视网膜病变的受试者工作特征曲线下面积(AUROC)

指标类型:

主要指标

Outcome:

Detection of area under the receiver operating characteristic curve (AUROC) for referrable diabetic retinopathy on EyeRoboFC images compared to ophthalmologist grading

Type:

Primary indicator

测量时间点:

拍摄后1月

测量方法:

数据分析

Measure time point of outcome:

One month after shooting

Measure method:

Data Analysis

采集人体标本:

Collecting sample(s)
from participants:

标本中文名:

组织:

Sample Name:

NA

Tissue:

人体标本去向

其它  

说明

Fate of sample:

0thers  

Note:

征募研究对象情况:

Recruiting status:

尚未开始

Not yet recruiting

年龄范围:

Participant age:

最小 Min age 18 years
最大 Max age NA years

性别:

男女均可

Gender:

Both

随机方法(请说明由何人用什么方法产生随机序列):

Randomization Procedure (please state who generates the random number sequence and by what method):

None

是否公开试验完成后的统计结果:

Calculated Results after the Study Completed public access:

不公开/Private

盲法:

Blinding:

None

是否共享原始数据:

IPD sharing

否No

共享原始数据的方式(说明:请填入公开原始数据日期和方式,如采用网络平台,需填该网络平台名称和网址):

如有获取原始数据需求,可联系项目负责人获取原始数据

The way of sharing IPD”(include metadata and protocol, If use web-based public database, please provide the url):

If you need to obtain raw data, you can contact the project leader to obtain raw data

数据采集和管理(说明:数据采集和管理由两部分组成,一为病例记录表(Case Record Form, CRF),二为电子采集和管理系统(Electronic Data Capture, EDC),如ResMan即为一种基于互联网的EDC:

1.通过机器检测获取数据,录入病例记录表;2.电子采集和管理系统;

Data collection and Management (A standard data collection and management system include a CRF and an electronic data capture:

1. Obtain data through machine detection and enter the case record form; 2. Electronic collection and management system;

数据与安全监察委员会:

Data and Safety Monitoring Committee:

无/No

注册人:

Name of Registration:

 2026-06-13 12:01:43