|
审核状态: Project audit state: |
通过审核 Successful |
|
注册号: Registration number: |
ChiCTR2500111230 |
|
最近更新日期: Date of Last Refreshed on: |
2025-10-28 11:46:29 |
|
注册时间: Date of Registration: |
2025-10-28 00:00:00 |
|
注册号状态: |
预注册 |
|
Registration Status: |
Prospective registration |
|
注册题目: |
基于SAM模型的冠状动脉FFR智能评估模型构建与验证 |
|
Public title: |
Development and Validation of a SAM-Based Artificial Intelligence Model for Fractional Flow Reserve Assessment from Invasive Coronary Angiography |
|
注册题目简写: |
|
|
English Acronym: |
|
|
研究课题的正式科学名称: |
基于SAM模型的冠状动脉FFR智能评估模型构建与验证 |
|
Scientific title: |
Development and Validation of a SAM-Based Artificial Intelligence Model for Fractional Flow Reserve Assessment from Invasive Coronary Angiography |
|
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: |
艾虎 |
研究负责人: |
艾虎 |
|
Applicant: |
Ai Hu |
Study leader: |
Ai Hu |
|
申请注册联系人电话: Applicant telephone: |
+86 10 8513 2535 |
研究负责人电话:
Study leader's |
+86 10 8513 2535 |
|
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: |
aihumd@aliyun.com |
研究负责人电子邮件: Study leader's E-mail: |
aihumd@aliyun.com |
|
申请单位网址(自愿提供): Applicant website(voluntary supply): |
Peking University |
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: |
东城区东单大华路1号 |
研究负责人通讯地址: |
东城区东单大华路1号 |
|
Applicant address: |
No. 1 Dahua Road, Dongdan, Dongcheng District, Beijing |
Study leader's address: |
No. 1 Dahua Road, Dongdan, Dongcheng District, Beijing |
|
申请注册联系人邮政编码: Applicant postcode: |
100730 |
研究负责人邮政编码: Study leader's postcode: |
100730 |
|
申请人所在单位: |
北京医院 |
||
|
Applicant's institution: |
Beijing Hospital |
||
|
研究负责人所在单位: |
北京医院 |
||
|
Affiliation of the Leader: |
Beijing Hospital |
||
|
是否获伦理委员会批准: |
是 |
||
|
Approved by ethic committee: |
Yes |
||
|
伦理委员会批件文号: Approved No. of ethic committee: |
2025BJYYEC-KY223-01 |
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: |
北京医院伦理委员会 |
||
|
Name of the ethic committee: |
Beijing Hospital Ethics Committee |
||
|
伦理委员会批准日期: Date of approved by ethic committee: |
2025-10-15 00:00:00 | ||
|
伦理委员会联系人: |
侯文静 |
||
|
Contact Name of the ethic committee: |
Hou Wenjing |
||
|
伦理委员会联系地址: |
北京市东城区东单大华路1号 |
||
|
Contact Address of the ethic committee: |
No. 1 Dahua Road, Dongdan, Dongcheng District, Beijing |
||
|
伦理委员会联系人电话: Contact phone of the ethic committee: |
+86 10 8513 2535 |
伦理委员会联系人邮箱: Contact email of the ethic committee: |
|
|
研究实施负责(组长)单位: |
北京医院 |
||||||||||||||||||||||
|
Primary sponsor: |
Beijing Hospital |
||||||||||||||||||||||
|
研究实施负责(组长)单位地址: |
北京市东城区东单大华路1号 |
||||||||||||||||||||||
|
Primary sponsor's address: |
No. 1 Dahua Road, Dongdan, Dongcheng District, Beijing |
||||||||||||||||||||||
|
试验主办单位(项目批准或申办者): Secondary sponsor: |
|
||||||||||||||||||||||
|
经费或物资来源: |
北京医院 |
||||||||||||||||||||||
|
Source(s) of funding: |
Beijing hospital |
||||||||||||||||||||||
|
研究疾病: |
冠心病 |
||||||||||||||||||||||
|
Target disease: |
CAD |
||||||||||||||||||||||
|
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: |
本研究计划应用卷积神经网络技术与血管影像分割技术建立人工智能血流储备分数模型(Artificial Intelligence derived Fraction Flow Reserve,AI-FFR),并同有创压力导丝的FFR进行对比,评估AI-FFR的诊断性能。 |
||||||||||||||||||||||
|
Objectives of Study: |
This study will apply convolutional neural networks combined with vascular image segmentation to develop an artificial-intelligence-derived fractional flow reserve model (AI-FFR) and evaluate its diagnostic performance against invasive pressure-wire FFR. |
||||||||||||||||||||||
|
药物成份或治疗方案详述: |
|
||||||||||||||||||||||
|
Description for medicine or protocol of treatment in detail: |
|
||||||||||||||||||||||
|
纳入标准: |
1.年龄在18岁及以上,80岁以下; 2.冠脉造影显示冠脉狭窄程度40%-90%. |
||||||||||||||||||||||
|
Inclusion criteria |
1. Age 18–80 years. 2. Coronary angiography showing stenosis of 40–90 % in at least one epicardial vessel. |
||||||||||||||||||||||
|
排除标准: |
1.冠状动脉造影显示造影剂不充盈; 2.血管重叠或目标血管严重扭曲无法完全暴露病变位置; 3.图像质量较差无法清晰辨认; 4.慢性完全性闭塞. |
||||||||||||||||||||||
|
Exclusion criteria: |
1. Inadequate contrast opacification of the target vessel. 2. Severe vessel overlap or excessive tortuosity precluding full visualization of the lesion. 3. Sub-optimal image quality that prevents clear identification of the lumen. 4. Chronic total occlusion (CTO) of the target vessel. |
||||||||||||||||||||||
|
研究实施时间: Study execute time: |
从 From 2025-07-31 00:00:00至 To 2027-12-31 00:00:00 |
征募观察对象时间: Recruiting time: |
从 From 2025-11-01 00:00:00 至 To 2026-10-01 00:00:00 |
|
诊断试验: Diagnostic Tests: |
|
||||||||||||||||||||||||||||
|
研究实施地点: Countries of recruitment and research settings: |
|
||||||||||||||||||||||||||||
|
测量指标: Outcomes: |
|
|
采集人体标本:
Collecting sample(s)
|
|
|
征募研究对象情况: Recruiting status: |
尚未开始 Not yet recruiting |
年龄范围: Participant age: |
|
||||||
|
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): |
无 |
||||||||
|
Randomization Procedure (please state who generates the random number sequence and by what method): |
not applicable |
||||||||
|
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 |
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): |
无 |
|
The way of sharing IPD”(include metadata and protocol, If use web-based public database, please provide the url): |
no |
|
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: |
本研究的数据管理由北京医院临床研究机构统一负责。临床资料通过北京医 院临床研究系统录入和管理,AI-FFR的训练与验证在中国科学院大学高性能计算中心私有云平台进行。冠脉造影图像由导管室造影机直接以DICOM格式输出,导丝FFR数值由压力分析仪自动记录并以XML文件导出,所有 XCA图像(血管造影)均以医学数字成像与通信(DICOM)格式存储和传输,用于进一步分析。XCA图像通常包含患者姓名、检查日期、图像模式和设备型号等元数据,为保护隐私,除帧序列外,删除其余元数据。数据质控包括二次录入与一致性比对,对10%随机病例进行双人录入核查,差异率≤0.5%为合格;源数据核查由质控员每月抽查10%病例,核对导管室记录、实验室报告与EDC一致性;影像质控由两名高年资介入医师盲法重标狭窄帧,κ≥0.8视为合格。所有数据均存放于加密服务器,实行权限分级与操作日志记录,确保数据安全、完整与可追溯。 |
|
Data collection and Management (A standard data collection and management system include a CRF and an electronic data capture: |
Data management is centrally handled by the Clinical Research Organization of Beijing Hospital. Clinical data are entered and managed through the hospital’s clinical research system; AI-FFR training and validation are performed on the private cloud platform of the High-Performance Computing Center, University of Chinese Academy of Sciences. Coronary angiograms are exported in DICOM format directly from the catheterisation-lab angiography units, and wire-based FFR values are automatically recorded by the pressure analyser and exported as XML files. All XCA images are stored and transferred in DICOM format for downstream analysis. These files originally contain metadata including patient name, examination date, modality and device model; for privacy protection, all metadata except the frame sequence are removed. Data-quality control comprises double entry and consistency checks: 10 % of cases are randomly selected for independent dual entry, with a discrepancy rate ≤ 0.5 % considered acceptable. Source-data verification is conducted monthly by quality-control officers who review 10 % of cases against catheterisation-lab records and laboratory reports to ensure EDC consistency. Image quality is verified by two senior interventional physicians who re-label stenosis frames in a blinded manner; an inter-observer κ ≥ 0.8 is required. All data reside on encrypted servers with role-based access and full audit trails to guarantee security, integrity and traceability. |
|
数据与安全监察委员会: Data and Safety Monitoring Committee: |
暂未确定/Not yet |