ChiCTR2300075532 版本V1.0 版本创建时间2023/09/07 16:21:07 中国临床试验注册中心

审核状态:

Project audit state:

通过审核

Successful

注册号:

Registration number:

ChiCTR2300075532 

最近更新日期:

Date of Last Refreshed on:

2023-09-07 16:20:53 

注册时间:

Date of Registration:

2023-09-07 00:00:00 

注册号状态:

补注册

Registration Status:

Retrospective registration

注册题目:

基于深度学习的视网膜血管分割技术评估心脑血管疾病早期视网膜血管改变

Public title:

Retinal vascular segmentation technology based on deep learning to evaluate early retinal vascular changes in cardiovascular and cerebrovascular diseases

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于深度学习的视网膜血管分割技术评估心脑血管疾病早期视网膜血管改变

Scientific title:

Retinal vascular segmentation technology based on deep learning to evaluate early retinal vascular changes in cardiovascular and cerebrovascular diseases

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:

李梅爽 

研究负责人:

刘海洋 

Applicant:

Li Meishuang 

Study leader:

Liu Haiyang 

申请注册联系人电话:

Applicant telephone:

+86 188 5125 0966

研究负责人电话:

Study leader's telephone:

+86 136 8516 7216

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:

940601078@qq.com

研究负责人电子邮件:

Study leader's E-mail:

liuhaiyang86@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:

徐州市铜山区大学路269号

研究负责人通讯地址:

徐州市铜山区大学路269号

Applicant address:

No.269,Daxue Road,Tongshan District,Xuzhou

Study leader's address:

No.269,Daxue Road,Tongshan District,Xuzhou

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:

徐州市第一人民医院

Applicant's institution:

Xuzhou First People's Hospital

研究负责人所在单位:

徐州市第一人民医院

Affiliation of the Leader:

Xuzhou First People's Hospital

是否获伦理委员会批准:

是/Yes

Approved by ethic committee:

Yes

伦理委员会批件文号:

Approved No. of ethic committee:

xyy11[2023]057

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:

徐州市第一人民医院伦理审查委员会

Name of the ethic committee:

Ethical Review Committee of Xuzhou First People's Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2023-02-27 00:00:00

伦理委员会联系人:

李莉

Contact Name of the ethic committee:

Lili

伦理委员会联系地址:

徐州市铜山区大学路269号

Contact Address of the ethic committee:

No. 269, University Road, Tongshan District, Xuzhou City

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 516 6816 7579

伦理委员会联系人邮箱:

Contact email of the ethic committee:

liuhaiyang86@126.com

研究实施负责(组长)单位:

徐州市第一人民医院

Primary sponsor:

Xuzhou First People's Hospital

研究实施负责(组长)单位地址:

徐州市铜山区大学路269号

Primary sponsor's address:

No. 269, University Road, Tongshan District, Xuzhou City

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

江苏省

市(区县):

徐州市

Country:

china

Province:

Jiangsu Province

City:

Xuzhou City

单位(医院):

徐州市第一人民医院

具体地址:

徐州市铜山区大学路269号

Institution
hospital:

Xuzhou First People's Hospital

Address:

No. 269, University Road, Tongshan District, Xuzhou City

经费或物资来源:

徐州市可持续发展议程创新示范区建设项目(KC22099)

Source(s) of funding:

Xuzhou Sustainable Development Agenda Innovation Demonstration Zone Construction Project

Target disease:

Changes in retinal blood vessels due to systemic diseases

Target disease code:

研究类型:

观察性研究

Study type:

Observational study

研究所处阶段:

其它 

Study phase:

N/A

研究设计:

横断面 

Study design:

Cross-sectional 

研究目的:

本研究拟通过 DL 算法实现视网膜血管的准确分割,利用视网膜血管分割结果在早期对心脑血管疾病进行无创性预测及诊断。在此基础上探索我国健康人群的心脑血管疾病危险因素监控、干预,并建立随访体系,最终降低心脑血管疾病发生率,改善心脑血管疾病患者的生存质量,具有重要的社会意义及应用前景。  

Objectives of Study:

In this study, it is proposed to realize the accurate segmentation of retinal blood vessels by DL algorithm, and use the results of retinal vascular segmentation to make non-invasive prediction and diagnosis of cardiovascular and cerebrovascular diseases at an early stage. On this basis, it is of great social significance and application prospect to explore the monitoring and intervention of cardiovascular and cerebrovascular disease risk factors in healthy people in China, and establish a follow-up system, which ultimately reduces the incidence of cardiovascular and cerebrovascular diseases and improves the quality of life of patients with cardiovascular and cerebrovascular diseases.

药物成份或治疗方案详述:

① 视网膜血管分割技术的实现。 拟利用眼底影像数据设计一种基于深度学习的分割网络模型,该模型可实现对视网膜血管图像的有效分割。根据模型训练过程中呈现的实时效果进一步调整网络架构,优化网络性能,提升运行速度,实现对视网膜血管的端到端实时分割。 ② 提取公共数据库中心脑血管疾病患者不同时期眼底影像,进行视网膜血管分割,判定血管改变特点,建立基于分割模型的人工智能(AI)软件平台,并连接眼底影像设备。 ③ 招募初发心脑血管疾病患者,建立自有眼底图像数据集,应用 AI 眼底影像设备及OCTA检查入组心脑血管患者眼底,进一步验证 AI 检查心脑血管疾病患者视网膜微血管改变的特异性、敏感性及受试者曲线。 ④ 将 AI 眼底影像设备投放在体检中心,采集所有体检患者的眼底影像信息,建立电子数据采集系统(EDC)。设计“基于深度学习的 AI 评估视网膜血管预测心脑血管疾病模型”,预测体检患者发生心脑血管疾病的风险。应用 EDC 进行随访干预,最终验证模型预测的准确性。  

Description for medicine or protocol of treatment in detail:

(1) Realization of retinal vascular segmentation technology. A deep learning-based segmentation network model is designed using fundus image data, which can effectively segment retinal vascular images. According to the real-time effect presented during model training, the network architecture is further adjusted, the network performance is optimized, the operation speed is improved, and the end-to-end real-time segmentation of retinal blood vessels is realized. (2) Extract fundus images of patients with cerebrovascular disease at different times in the public database center, perform retinal vascular segmentation, determine the characteristics of vascular changes, establish an artificial intelligence (AI) software platform based on segmentation model, and connect fundus imaging equipment. (3) Recruit patients with new-onset cardiovascular and cerebrovascular diseases, establish their own fundus image dataset, use AI fundus imaging equipment to check the fundus of enrolled cardiovascular and cerebrovascular patients, and further verify the specificity, sensitivity and subject curve of AI to check retinal microvascular changes in patients with cardiovascular and cerebrovascular diseases. (4) Put AI fundus imaging equipment in the physical examination center, collect fundus image information of all physical examination patients, and establish an electronic data acquisition system (EDC). Design an "AI model based on deep learning to evaluate retinal blood vessels to predict cardiovascular and cerebrovascular diseases" to predict the risk of cardiovascular and cerebrovascular diseases in physical examination patients. EDC was used for follow-up intervention to ultimately validate the accuracy of model predictions.  

纳入标准:

① 自愿参与该研究且依从性良好者 。
② 年龄大于 18 周岁的正在徐州市第一人民医院治疗的初发心梗、脑梗患者。

Inclusion criteria

(1) Those who voluntarily participate in the study and have good compliance .
(2) Patients over 18 years old who are being treated in Xuzhou First People's Hospital for initial myocardial infarction or cerebral infarction .

排除标准:

① 患者屈光介质混浊不能进行眼底照相;
② 患者有除白内障外的其他内眼疾病,如青光眼、视神经炎、葡萄膜炎、黄斑变性、视网膜脱离等。患者有除白内障手术外的其他内眼手术史;
③ 患者患有除心梗、脑梗外的其他系统性血管疾病,如糖尿病、系统性红斑狼疮等。

Exclusion criteria:

(1) The patient's refractive medium is cloudy and fundus photography cannot be performed.
(2) The patient has other internal eye diseases other than cataracts, such as glaucoma, optic neuritis, uveitis, macular degeneration, retinal detachment, etc. The patient has a history of internal eye surgery other than cataract surgery.
(3) The patient suffers from other systemic vascular diseases other than myocardial infarction and cerebral infarction, such as diabetes mellitus, systemic lupus erythematosus, etc.

研究实施时间:

Study execute time:

From 2022-08-01 00:00:00 To 2024-07-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2023-03-18 00:00:00 To 2023-12-31 00:00:00  

干预措施:

Interventions:

组别:

急性脑梗死组

样本量:

100

Group:

Acute cerebral infarction group

Sample size:

干预措施:

干预措施代码:

Intervention:

None

Intervention code:

组别:

心肌缺血组

样本量:

100

Group:

Myocardial ischemia group

Sample size:

干预措施:

干预措施代码:

Intervention:

None

Intervention code:

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

江苏省 

市(区县):

徐州市 

Country:

china 

Province:

Jiangsu Province 

City:

Xuzhou City 

单位(医院):

徐州市第一人民医院 

单位级别:

三级甲等医院 

Institution
hospital:

Xuzhou First People's Hospital

Level of the institution:

Tertiary A hospital

测量指标:

Outcomes:

指标中文名:

眼底血管、黄斑区血流密度

指标类型:

主要指标

Outcome:

Fundus blood vessels, macular area blood flow density

Type:

Primary indicator

测量时间点:

入组后开始测量

测量方法:

利用深度学习法进行视网膜血管分割

Measure time point of outcome:

Measurements are started after enrollment

Measure method:

Retinal vascular segmentation by deep learning

采集人体标本:

Collecting sample(s)
from participants:

标本中文名:

组织:

Sample Name:

NO

Tissue:

人体标本去向

使用后销毁  

说明

Fate of sample:

Destruction after use  

Note:

征募研究对象情况:

Recruiting status:

正在进行

Recruiting

年龄范围:

Participant age:

最小 Min age 18 years
最大 Max age 80 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):

No

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:

是否共享原始数据:

IPD sharing

Yes

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):

公开,试验完成后6个月内上传至ResMan(http://www.medresman.org.cn/iogin.aspx)

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

Public, uploaded to ResMan (http://www.medresman.org.cn/iogin.aspx) within 6 months of completion of the trial

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:

纸质版病人信息及数据采集,excel表登记录入,采用病例记录表记录病人信息。视网膜血管信息用深度学习法分析后录入病例。

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

Paper version of patient information and data collection, excel form registration, using case record form to record patient information. Retinal vascular information was analyzed by deep learning and entered into cases.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

有/Yes

注册人:

Name of Registration:

 2023-09-07 16:20:53