利用平扫胸部CT进行心脏疾病检测及诊断

注册号:

Registration number:

ChiCTR2600124626 

最近更新日期:

Date of Last Refreshed on:

2026-05-14 15:13:36 

注册时间:

Date of Registration:

2026-05-14 00:00:00 

注册号状态:

补注册

Registration Status:

Retrospective registration

注册题目:

利用平扫胸部CT进行心脏疾病检测及诊断

Public title:

Cardiac disease detection and diagnosis using non-contrast chest CT

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于平扫胸部CT的智能心脏疾病检测及诊断

Scientific title:

Detection and diagnosis of cardiac diseases based on non-contrast chest CT scans

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:

牡丹 

研究负责人:

牡丹 

Applicant:

Dan Mu 

Study leader:

Dan Mu 

申请注册联系人电话:

Applicant telephone:

+86 13305143131

研究负责人电话:

Study leader's
telephone:

+86 21 66301604

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:

mudan118@126.com

研究负责人电子邮件:

Study leader's E-mail:

mudan118@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:

中国上海市静安区延长中路301号6号楼

研究负责人通讯地址:

中国上海市静安区延长中路301号6号楼

Applicant address:

Building 6, 301 Yanchang Zhong Road, Jing 'an District, Shanghai, China

Study leader's address:

Building 6, 301 Yanchang Zhong Road, Jing 'an District, Shanghai, 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:

上海市第十人民医院

Applicant's institution:

Shanghai Tenth People's Hospital

研究负责人所在单位:

上海市第十人民医院

Affiliation of the Leader:

Shanghai Tenth People's 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:

SHSY-IEC-6.0/25K93/P01

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:

上海市第十人民医院伦理委员会

Name of the ethic committee:

Ethics Committee of Shanghai tenth People's Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2025-05-20 00:00:00

伦理委员会联系人:

袁凤

Contact Name of the ethic committee:

Feng Yuan

伦理委员会联系地址:

中国上海市静安区延长中路301号6号楼

Contact Address of the ethic committee:

Building 6, 301 Yanchang Zhong Road, Jing 'an District, Shanghai, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 21 66301604

伦理委员会联系人邮箱:

Contact email of the ethic committee:

shsyiec@126.com

研究实施负责(组长)单位:

上海市第十人民医院

Primary sponsor:

Shanghai Tenth People's Hospital

研究实施负责(组长)单位地址:

中国上海市静安区延长中路301号6号楼

Primary sponsor's address:

Building 6, 301 Yanchang Zhong Road, Jing 'an District, Shanghai, 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):

上海

市(区县):

Country:

China

Province:

Shanghai

City:

单位(医院):

上海市第十人民医院

具体地址:

中国上海市静安区延长中路301号6号楼

Institution
hospital:

Shanghai Tenth People's Hospital

Address:

Building 6, 301 Yanchang Zhong Road, Jing 'an District, Shanghai, China

经费或物资来源:

自选课题(自筹)

Source(s) of funding:

Self-selected Research Topic

研究疾病:

包括以下八种心血管疾病:心脏肥大,心包积液,冠状动脉疾病,高血压,肥厚型心肌病,扩张型心肌病,心肌炎,以及心包炎。  

Target disease:

Including the following eight cardiovascular diseases: cardiomegaly, pericardial effusion, coronary artery disease, hypertension, hypertrophic cardiomyopathy, dilated cardiomyopathy, myocarditis, and pericarditis.

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:

这项研究旨在开发一个基于人工智能(AI)的诊断系统,利用非增强胸部CT(NCCT)扫描,实现对八种常见心血管疾病(CVD)的早期筛查和准确诊断,包括以下八种心血管疾病:心脏肥大,心包积液,冠状动脉疾病,高血压,肥厚型心肌病,扩张型心肌病,心肌炎,以及心包炎。通过整合切片间超分辨率技术、NCCT到CTA的转换以及多模态数据融合,该系统旨在提高诊断的准确性,同时降低对昂贵影像学检查(如心脏MRI和CTA)的依赖,提供一种经济高效且快速的解决方案。  

Objectives of Study:

This study aims to develop an artificial intelligence (AI)-based diagnostic system utilizing non-contrast chest CT (NCCT) scans to achieve early screening and accurate diagnosis of eight common cardiovascular diseases (CVDs), including the following eight cardiovascular diseases: cardiomegaly, pericardial effusion, coronary artery disease, hypertension, hypertrophic cardiomyopathy, dilated cardiomyopathy, myocarditis, and pericarditis. By integrating inter-slice super-resolution technology, NCCT-to-CTA conversion, and multimodal data fusion, the system seeks to enhance diagnostic accuracy while reducing reliance on expensive imaging modalities (e.g., cardiac MRI and CTA), offering a cost-effective and rapid solution.

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.CT影像质量较差(包括图像模糊,运动以及金属伪影,CT层厚过大(大于10mm))。
2.患者CT数据或者心血管疾病诊断结果缺失。
3.可能存在严重的非心血管疾病干扰诊断(如肺部恶性肿瘤)。

Exclusion criteria:

1.Suboptimal CT imaging quality due to motion-induced blurring, metallic streak artifacts, and inadequate spatial resolution (slice thickness exceeding 10mm);
2.Absence of either CT datasets or confirmed CVD diagnoses;
3.Significant non-CVD comorbidities (e.g., biopsy-confirmed lung adenocarcinoma) potentially obscuring primary cardiovascular diagnoses;

研究实施时间:

Study execute time:

From 2025-06-01 00:00:00 To 2026-03-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2025-06-01 00:00:00 To 2025-12-30 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):

诊断标准:患者需具有明确的心血管疾病症状或体征,如胸痛、心悸、呼吸困难、疲劳、或其他与CVD相关的临床表现,同时基于CCTA或心脏MRI被怀疑患有八种心血管疾病之一。

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):

Diagnostic criteria: Patients must exhibit clear symptoms or signs of cardiovascular disease, such as chest pain, palpitations, dyspnea, fatigue, or other clinical manifestations associated with CVD, while also being suspected of having one of eight cardiovascular diseases based on CCTA or CMR.

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):

使用5折交叉验证策略对模型进行训练和优化。在训练数据中随机抽取80%用于训练,20%用于初步验证。评估指标包括准确率(Accuracy)、灵敏度(Sensitivity)、特异性(Specificity)、精确率(Precision)、F1分数(F1-Score)以及ROC曲线下面积(AUC-ROC)。

Index test:

The model was trained and optimized using a 5-fold cross-validation strategy. From the training data, 80% was randomly selected for training and 20% for preliminary validation. The evaluation metrics included accuracy, sensitivity, specificity, precision, F1-score, and the area under the ROC curve.

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)

既往被临床诊断为心脏肥大,心包积液,冠状动脉疾病,高血压,肥厚型心肌病,扩张型心肌病,心肌炎,以及心包炎等疾病,并行胸部平扫CT检查的患者。

例数:

Sample size:

3200

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 with prior clinical diagnoses of cardiac hypertrophy, pericardial effusion, coronary arterydisease, hypertension, hypertrophic cardiomyopathy, dilated cardiomyopathy, myocarditis, orpericarditis, who underwent non-contrast chest CT scans.

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):

无明确心血管疾病及症状的人群

例数:

Sample size:

1800

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

Individuals without clear cardiovascular disease or symptoms.

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

上海 

市(区县):

 

Country:

China

Province:

Shanghai

City:

单位(医院):

上海市第十人民医院 

单位级别:

三级甲等 

Institution
hospital:

Shanghai Tenth People's Hospital

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

内蒙古自治区 

市(区县):

 

Country:

China

Province:

Inner Mongolia Autonomous Region

City:

单位(医院):

内蒙古自治区人民医院 

单位级别:

三级甲等 

Institution
hospital:

Inner Mongolia People's hospital

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

湖北 

市(区县):

 

Country:

China

Province:

Hubei

City:

单位(医院):

襄阳市第一人民医院 

单位级别:

三级甲等 

Institution
hospital:

Xiangyang No.1 People’s Hospital Hubei University of Medicine

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

贵州 

市(区县):

 

Country:

China

Province:

Guizhou

City:

单位(医院):

铜仁市人民医院 

单位级别:

三级甲等 

Institution
hospital:

Tongren People's Hospital

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

江苏 

市(区县):

 

Country:

China

Province:

Jiangsu

City:

单位(医院):

南京江北医院 

单位级别:

三级乙等 

Institution
hospital:

Nanjing Jiangbei Hospital

Level of the institution:

Tertiary B

国家:

中国

省(直辖市):

江苏 

市(区县):

 

Country:

China

Province:

Jiangsu

City:

单位(医院):

南京鼓楼医院集团仪征医院 

单位级别:

二级甲等 

Institution
hospital:

Yizheng Hospital,Nanjing Drum Tower Hospital Group

Level of the institution:

Secondary A

国家:

中国

省(直辖市):

江苏 

市(区县):

 

Country:

China

Province:

Jiangsu

City:

单位(医院):

南京鼓楼医院 

单位级别:

三级甲等 

Institution
hospital:

Nanjing Drum Tower Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

人工智能模型诊断心脏疾病的准确率

指标类型:

主要指标

Outcome:

Accuracy of AI models in diagnosing heart diseases

Type:

Primary indicator

测量时间点:

模型训练完成后验证阶段

测量方法:

以临床诊断结果为标准,经统计学方法计算智能诊断系统诊断相关心脏疾病的准确率

Measure time point of outcome:

Model validation phase after training completion

Measure method:

Using clinical diagnostic results as the gold standard, the accuracy of the intelligent diagnostic system in diagnosing related heart diseases was calculated through statistical methods.

指标中文名:

人工智能模型诊断心脏疾病的F1分数

指标类型:

次要指标

Outcome:

F1 Score of AI models in diagnosing heart diseases

Type:

Secondary indicator

测量时间点:

模型训练完成后验证阶段

测量方法:

以临床诊断结果为标准,经统计学方法计算智能诊断系统诊断相关心脏疾病的F1分数

Measure time point of outcome:

Model validation phase after training completion

Measure method:

Using clinical diagnostic results as the gold standard, the F1 Score of the intelligent diagnostic system in diagnosing related heart diseases was calculated through statistical methods.

指标中文名:

人工智能模型诊断心脏疾病的灵敏度

指标类型:

次要指标

Outcome:

Sensitivity of AI models in diagnosing heart diseases

Type:

Secondary indicator

测量时间点:

模型训练完成后验证阶段

测量方法:

以临床诊断结果为标准,经统计学方法计算智能诊断系统诊断相关心脏疾病的灵敏度

Measure time point of outcome:

Model validation phase after training completion

Measure method:

Using clinical diagnostic results as the gold standard, the sensitivity of the intelligent diagnostic system in diagnosing related heart diseases was calculated through statistical methods.

指标中文名:

人工智能模型诊断心脏疾病的精确率

指标类型:

主要指标

Outcome:

Precision of AI models in diagnosing heart diseases

Type:

Primary indicator

测量时间点:

模型训练完成后验证阶段

测量方法:

以临床诊断结果为标准,经统计学方法计算智能诊断系统诊断相关心脏疾病的准确率

Measure time point of outcome:

Model validation phase after training completion

Measure method:

Using clinical diagnostic results as the gold standard, the precision of the intelligent diagnostic system in diagnosing related heart diseases was calculated through statistical methods.

指标中文名:

人工智能模型诊断心脏疾病的特异度

指标类型:

次要指标

Outcome:

Specificity of AI models in diagnosing heart diseases

Type:

Secondary indicator

测量时间点:

模型训练完成后验证阶段

测量方法:

以临床诊断结果为标准,经统计学方法计算智能诊断系统诊断相关心脏疾病的特异度

Measure time point of outcome:

Model validation phase after training completion

Measure method:

Using clinical diagnostic results as the gold standard, the specificity of the intelligent diagnostic system in diagnosing related heart diseases was calculated through statistical methods.

指标中文名:

人工智能模型诊断心脏疾病的 AUC 值

指标类型:

主要指标

Outcome:

AUC value of AI models in diagnosing heart diseases

Type:

Primary indicator

测量时间点:

模型训练完成后验证阶段

测量方法:

使用统计学方法绘制人工智能模型诊断各疾病的ROC曲线,并计算曲线下面积AUC值。

Measure time point of outcome:

Model validation phase after training completion

Measure method:

Using statistical methods to plot ROC curves for AI models diagnosing various diseases and calculate the Area Under the Curve (AUC) values.

采集人体标本:

Collecting sample(s)
from participants:

标本中文名:

组织:

Sample Name:

N/A

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:

结束

/Completed

年龄范围:

Participant age:

最小 Min age 18 years
最大 Max age 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

是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):

试验完成后6个月内(最晚不超过试验结束后 6 个月)上传到电子数据收集与管理系统通过临床试验公共管理平台 ResMan(www.medresman.org)。

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

Upload it to the Electronic Data Collection and Management System within 6 months after the completion of the trial (at the latest no more than 6 months after the end of the trial) through the Clinical Trial Public Management Platform ResMan (www.medresman.org).

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:

收集多个医学中心相关影像数据及相关临床数据,由组长单位专门人员进行统一管理,对于数据安全采取分级保护措施;采用RBAC模型及最小权限原则进行访问控制;对所有数据进行加密传输并保留所有数据访问日志(保存5年)。本实验研究数据在进行分析前均需通过脱敏处理,以去除可能的隐私信息并确保所有数据在研究过程中处于匿名状态。

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

Relevant imaging and clinical data collected from multiple medical centers shall be uniformly managed by designated personnel from the lead institution, with tiered protection measures implemented for data security. Access control follows the RBAC (Role-Based Access Control) model and the principle of least privilege. All data shall be encrypted during transmission, and complete access logs shall be retained (for 5 years). Prior to analysis, all research data must undergo anonymization to remove potential privacy identifiers, ensuring anonymity throughout the study.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

无/No

注册人:

Name of Registration:

 2026-05-14 15:13:27