基于新一代人工智能技术的肺癌智能化诊断产品解决方案及示范应用——一项评价肺结节CT影像辅助诊断软件用于肺结节良恶性判断的回顾性、多中心、多阅片者多病例(MRMC)、配对设计临床试验

注册号:

Registration number:

ChiCTR2400084624 

最近更新日期:

Date of Last Refreshed on:

2025-02-08 17:49:07 

注册时间:

Date of Registration:

2024-05-21 00:00:00 

注册号状态:

补注册

Registration Status:

Retrospective registration

注册题目:

基于新一代人工智能技术的肺癌智能化诊断产品解决方案及示范应用——一项评价肺结节CT影像辅助诊断软件用于肺结节良恶性判断的回顾性、多中心、多阅片者多病例(MRMC)、配对设计临床试验

Public title:

The Intelligent Diagnosis Product Solution and Demonstrative Application for Lung Cancer Based on Next-Generation Artificial Intelligence Technology——A Retrospective, Multicenter, Multi-Reader, Multiple-Case (MRMC), Clinical Trial with a Paired Study Design to Evaluate an Assistive Diagnostic Software for Classification of Benign and Malignant Pulmonary Nodules in CT images

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于新一代人工智能技术的肺癌智能化诊断产品解决方案及示范应用——一项评价肺结节CT影像辅助诊断软件用于肺结节良恶性判断的回顾性、多中心、多阅片者多病例(MRMC)、配对设计临床试验

Scientific title:

The Intelligent Diagnosis Product Solution and Demonstrative Application for Lung Cancer Based on Next-Generation Artificial Intelligence Technology——A Retrospective, Multicenter, Multi-Reader, Multiple-Case (MRMC), Clinical Trial with a Paired Study Design to Evaluate an Assistive Diagnostic Software for Classification of Benign and Malignant Pulmonary Nodules in CT images

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:

胡歌 

研究负责人:

金征宇; 洪楠 

Applicant:

Ge Hu 

Study leader:

Zhengyu Jin; Nan Hong 

申请注册联系人电话:

Applicant telephone:

+86 158 1088 8378

研究负责人电话:

Study leader's
telephone:

+86 10 6915 9553

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:

421840378@qq.com

研究负责人电子邮件:

Study leader's E-mail:

jinzy@pumch.cn

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:

北京市东城区帅府园一号

研究负责人通讯地址:

北京市东城区帅府园一号; 北京市西城区西直门南大街11号

Applicant address:

1 Shuaifuyuan, Dongcheng District, Beijing, China

Study leader's address:

1 Shuaifuyuan, Dongcheng District, Beijing, China; 11 Xizhimen South Street, Xicheng District, Beijing, 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:

中国医学科学院北京协和医院

Applicant's institution:

Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College

研究负责人所在单位:

中国医学科学院北京协和医院; 北京大学人民医院

Affiliation of the Leader:

Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College; Peking University 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:

JS-2805; l-24PJ1037; 2022PHA118-001; 武三医伦QX2023-002; 伦快审(2023)2号

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:

北京协和医院伦理审查委员会;北京大学人民医院伦理审查委员会;武汉市第三医院伦理委员会;黄石市中心医院伦理委员会

Name of the ethic committee:

Institutional Review Board of Peking Union Medical College Hospital; Institutional Review Board of Peking University People's Hospital; Institutional Review Board of Wuhan Third Hospital; Institutional Review Board of Huangshi Central Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2022-12-07 00:00:00

伦理委员会联系人:

丛翠翠

Contact Name of the ethic committee:

Cuicui Cong

伦理委员会联系地址:

北京市西城区西直门南大街11号

Contact Address of the ethic committee:

11 Xizhimen South Street, Xicheng District, Beijing, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 10 8832 4516

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:

中国医学科学院北京协和医院; 北京大学人民医院

Primary sponsor:

Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College; Peking University People's Hospital

研究实施负责(组长)单位地址:

北京市东城区帅府园一号; 北京市西城区西直门南大街11号

Primary sponsor's address:

1 Shuaifuyuan, Dongcheng District, Beijing, China; 11 Xizhimen South Street, Xicheng District, Beijing, 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):

北京

市(区县):

Country:

China

Province:

Beijing

City:

单位(医院):

北京深睿博联科技有限责任公司

具体地址:

西三环北路甲2号院2号楼13层2号

Institution
hospital:

Deepwise & League of PhD Technology Co., Ltd

Address:

Room 02, 13th Floor, Building 2, No. A2, West Third Ring North Road, Haidian District

经费或物资来源:

北京市科技计划项目

Source(s) of funding:

Beijing Municipal Science and Technology Project

研究疾病:

肺结节  

Target disease:

Pulmonary nodule

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:

连续入组 

Study design:

Sequential 

研究目的:

评价肺结节CT影像辅助诊断软件用于肺结节良恶性的判断  

Objectives of Study:

To evaluate the effectiveness of CT imaging-assisted diagnostic software in differentiating between benign and malignant pulmonary nodules

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. 如果一个病理报告上所有结节都无法在CT平扫影像上确定正确的位置,则该病例排除; 2. 胸部CT扫描范围不全;手术或者穿刺后的CT影像;影像拍摄质量不佳、有严重的金属伪影或呼吸伪影,影响研究者阅片判断; 3. 临床诊断为转移性病灶 4. 研究者认为不适合入组的受试者。

Exclusion criteria:

1. If no nodules on a pathological report can be accurately located on the CT scan, the case will be excluded; 2. Incomplete chest CT scan range; CT images taken after surgery or biopsy; poor image quality with severe metal or respiratory artifacts affecting the reading; 3. Clinically diagnosed metastatic lesions; 4. Participants deemed unsuitable by the investigator.

研究实施时间:

Study execute time:

From 2022-11-01 00:00:00 To 2023-09-30 00:00:00  

征募观察对象时间:

Recruiting time:

From 2022-11-01 00:00:00 To 2023-09-30 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):

肺结节的临床病理诊断结果

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):

The clinical pathological diagnosis results of pulmonary nodules

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):

试验组:肺结节CT影像辅助诊断软件+医生联合阅片 对照组:阅片医生单独阅片

Index test:

Test group: CT readings conducted jointly by radiologists using AI-assisted diagnostic software Control group: CT readings conducted independently by radiologists

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)

胸部CT影像检查发现有肺结节,需要进行肺结节良恶性判断的患者

例数:

Sample size:

400

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 pulmonary nodules detected on chest CT imaging who require determination of benign or malignant nature

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):

北京 

市(区县):

 

Country:

China

Province:

Beijing

City:

单位(医院):

北京大学人民医院 

单位级别:

三甲 

Institution
hospital:

Peking University 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):

武汉市第三医院 

单位级别:

三甲 

Institution
hospital:

Wuhan Third 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):

黄石市中心医院 

单位级别:

三甲 

Institution
hospital:

Huangshi Central Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

ROC-AUC (受试者水平)

指标类型:

主要指标

Outcome:

ROC-AUC (paricipants level)

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

ROC-AUC (结节水平)

指标类型:

次要指标

Outcome:

ROC-AUC (nodule level)

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

试验组与对照组肺结节良恶性判断的灵敏度、特异度和准确率(结节水平)

指标类型:

次要指标

Outcome:

The sensitivity, specificity, and accuracy (at the nodule level) of malignancy determination for pulmonary nodules in the test group and the control group

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

试验组与对照组肺结节良恶性判断的灵敏度、特异度和准确率(受试者水平)

指标类型:

次要指标

Outcome:

The sensitivity, specificity, and accuracy (at the participant level) of malignancy determination for pulmonary nodules in the experimental group and the control group

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

软件对受试者肺结节良恶性判断结果的灵敏度与特异度(结节水平)

指标类型:

次要指标

Outcome:

The sensitivity and specificity (at the nodule level) of the software in determining the malignancy of pulmonary nodules in the subjects

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

软件对肺结节位置判断的准确度(结节水平)

指标类型:

次要指标

Outcome:

The accuracy of the software in determining the location of pulmonary nodules (at the nodule level)

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

软件对肺结节密度类型判断的准确度(结节水平)

指标类型:

次要指标

Outcome:

The accuracy of the software in determining the density of pulmonary nodules (nodule level)

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

软件功能主观评价

指标类型:

次要指标

Outcome:

Subjective evaluation of software functionality

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

软件易用性主观评价

指标类型:

次要指标

Outcome:

Subjective evaluation of software usability

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

安全性评价

指标类型:

副作用指标

Outcome:

Security evaluation

Type:

Adverse events

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

采集人体标本:

Collecting sample(s)
from participants:

标本中文名:

组织:

Sample Name:

None

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 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):

对入组影像进行数据清洗与脱敏,去掉患者姓名、中心名称等明确识别患者身份的敏感信息。本研究共需要12名阅片医生,随机分为A、B两组,每组医生以不同的阅片顺序对所有脱敏后的CT影像进行阅片,判断肺结节的良恶性。A组:首先由阅片医生单独阅片(第一阶段),洗脱期(至少28天)后,再由AI+医生联合阅片(第二阶段);B组:首先由AI+医生联合阅片(第一阶段),洗脱期(至少28天)后,再由阅片医生单独阅片(第二阶段)。其中 AI+医生联合阅片为本研究的试验组,阅片医生单独阅片为本研究的对照组,通过比较试验组和对照组的试验结果来评估软件的辅助诊断作用

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

The enrolled imaging data underwent cleaning and desensitization to remove sensitive information, such as participants' names and center identifiers, that could potentially reveal patient identities. A total of 12 radiologists participated in this study, randomly assigned to Group A and Group B. Each group of radiologists reviewed all desensitized CT images in different reading sequences to assess the malignancy of pulmonary nodules. Group A: Radiologists initially reviewed the images independently (Phase 1), followed by a washout period of at least 28 days. After this, the images were reviewed jointly by AI and radiologists (Phase 2). Group B: Images were first reviewed jointly by AI and radiologists (Phase 1), followed by a washout period of at least 28 days, after which the radiologists reviewed the images independently (Phase 2). In this study, the joint reading involving AI and radiologists formed the test group, while the independent reading by radiologists alone served as the control group. The diagnostic performance of the software was evaluated by comparing the results between the experimental and control groups.

是否公开试验完成后的统计结果:

Calculated Results after the Study Completed public access:

公开/Public

盲法:

未说明

Blinding:

Not stated

试验完成后的统计结果(上传文件):

Calculated Results after
the Study Completed(upload file):

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):

在主要研究成果发表1年后,通过向课题负责人及通讯作者发送邮件申请获得,获取数据时需要提供完整的研究计划。

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

One year after the publication of the primary research findings, data can be obtained by sending an email application to the principal investigator and corresponding author. A complete research plan must be provided when requesting the 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:

数据采集:肺结节患者临床及影像数据记录表。数据管理:电子数据采集系统。

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

Data collection: clinical and imaging data record form for patients with pulmonary nodules. Data management: electronic data capture system.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

有/Yes

注册人:

Name of Registration:

 2024-05-21 16:13:43