基于人工智能神经网络对于胸部CT肺结节探测的诊断效能评估

注册号:

Registration number:

ChiCTR1800016226 

最近更新日期:

Date of Last Refreshed on:

2018-05-21 19:27:52 

注册时间:

Date of Registration:

2018-05-21 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于人工智能神经网络对于胸部CT肺结节探测的诊断效能评估

Public title:

Diagnostic Performance of Neural Network-Based Artificial Intelligent in Detecting Pulmonary Nodule on Chest CT

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于人工智能神经网络对于胸部CT肺结节探测的诊断效能评估

Scientific title:

Diagnostic Performance of Neural Network-Based Artificial Intelligent in Detecting Pulmonary Nodule on Chest CT

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:

明帅 

研究负责人:

龚向阳 

Applicant:

Shuai MING 

Study leader:

Xiangyang GONG 

申请注册联系人电话:

Applicant telephone:

+86 15955219030

研究负责人电话:

Study leader's
telephone:

+86 13958159183

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:

ming.ys@foxmail.com

研究负责人电子邮件:

Study leader's E-mail:

cjr.gxy@hotmail.com

申请单位网址(自愿提供):

Applicant website(voluntary supply):

http://www.hospitalstar.com

研究负责人网址(自愿提供):

Study leader's website(voluntary supply):

http://www.hospitalstar.com

申请注册联系人通讯地址:

浙江省杭州市下城区朝晖四区32栋204室

研究负责人通讯地址:

浙江省杭州市上塘路158号

Applicant address:

Room 204, 32th Building, Chaohui 4th Area, Xicheng District, Hangzhou, Zhejiang, China

Study leader's address:

158 Shangtang Road, Hangzhou, Zhejiang, China

申请注册联系人邮政编码:

Applicant postcode:

310014

研究负责人邮政编码:

Study leader's postcode:

310014

申请人所在单位:

浙江省人民医院

Applicant's institution:

Zhejiang Provincial People's Hospital

研究负责人所在单位:

浙江省人民医院

Affiliation of the Leader:

Zhejiang Provincial 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:

2018KY003

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:

浙江省人民医院伦理委员会

Name of the ethic committee:

Ethics committee of zhejiang provincial people's hospital.

伦理委员会批准日期:

Date of approved by ethic committee:

2018-03-15 00:00:00

伦理委员会联系人:

李青青

Contact Name of the ethic committee:

Qingqing Li

伦理委员会联系地址:

浙江省杭州市上塘路158号7号楼2楼药物临床试验机构办公室

Contact Address of the ethic committee:

Office of drug clinical trial office, 2nd Floor, 7th Building, 158 Shangtang Road, Hangzhou, Zhejiang, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 0571-85893646

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:

浙江省人民医院

Primary sponsor:

Zhejiang Provincial People's Hospital

研究实施负责(组长)单位地址:

浙江省杭州市上塘路158号

Primary sponsor's address:

158 Shangtang Road, Hangzhou, Zhejiang, 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):

浙江省

市(区县):

杭州市

Country:

China

Province:

Zhejiang

City:

Hangzhou

单位(医院):

浙江省人民医院

具体地址:

浙江省杭州市上塘路158号

Institution
hospital:

Zhejiang Provincial People's Hospital

Address:

158 Shangtang Road, Hangzhou, Zhejiang, China

经费或物资来源:

自筹

Source(s) of funding:

self-finance

研究疾病:

肺结节  

Target disease:

pulmonary nodules

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:

诊断试验新技术临床试验 

Study phase:

Diagnostic New Technique Clincal Study

研究设计:

诊断性病例对照试验 

Study design:

Diagnostic test: case-control 

研究目的:

在多中心临床试验中随机抽取LDCT肺部结节筛查体检者影像资料作为研究的样本,评估监督学习状态下人工智能神经网络在肺结节探测的效能, 并与初级放射科医师进行同组数据比较。这一研究成果不仅帮助放射科医生提高诊断精度和诊断效率,且提升医疗检验水平同质化。  

Objectives of Study:

This multicenter clinical trial randomly collect LDCT images as medical sample for lung nodules screening. The aim of this research is to assess detection performance of artificial neural network with supervision learning in lung nodules , and compared with the primary radiologists group.The results of this study not only help radiologists to improve diagnostic accuracy and diagnostic efficiency, but also promote diagnostic homogenization within medical institutes with different level and region.

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.体检者图像合并有基础肺疾病:如胸部手术后患者,大面积肺部感染,大量胸水,弥漫性间质性肺炎等; 2.图像采集质量差; 3.肺内实质性病灶直径大于3cm; 4.两肺结节数大于20枚。

Exclusion criteria:

1. Patients with basic lung diseases: after chest surgery, large area of lung infection, large amount of chest water, diffuse interstitial pneumonia, etc.;
2. Poor quality of image collection;
3. The diameter of the substantial lesion in the lung is greater than 3cm;
4. The number of pulmonary nodules is greater than 20.

研究实施时间:

Study execute time:

From 2018-01-16 00:00:00 To 2019-08-01 00:00:00  

征募观察对象时间:

Recruiting time:

From 2018-08-01 00:00:00 To 2018-10-01 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):

3位具有15-20年诊断经验的胸部亚临床专业影像医师在无时间限制下对肺结节进行诊断,一致性≧2.

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):

Three sub-division radiologists with 15-20 years of diagnostic experience separately rated all CT images without time limitation.Pulmonary nodules confirmed by at least 2 radiologist were rated as the true 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):

初级放射科医生诊断及人工智能诊断分析

Index test:

Diagnostic analysis of primary radiologists and artificial intelligence.

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)

肺部CT体检人群

例数:

Sample size:

600

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):

Lung CT health examination population

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):

肺部CT体检人群

例数:

Sample size:

600

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

Lung CT health examination population

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

浙江省 

市(区县):

杭州 

Country:

China

Province:

Zhejiang

City:

Hangzhou

单位(医院):

浙江省人民医院 

单位级别:

三甲 

Institution
hospital:

Zhejiang Provincial People's Hospital

Level of the institution:

Tertiary A Hospital

测量指标:

Outcomes:

指标中文名:

肺结节

指标类型:

主要指标

Outcome:

Pulmonary nodules

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

SEN, SPE, ACC, AUC of ROC

指标类型:

主要指标

Outcome:

SEN, SPE, ACC, AUC of ROC

Type:

Primary indicator

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:

CT图像

组织:

Sample Name:

CT images

Tissue:

none

人体标本去向

其它  

说明

无标本

Fate of sample:

0thers  

Note:

no samples

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 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):

采用同源配对设计:采集结节分别由三位高年资医生及九位初级医师采用盲法进行阅片并得出结论,同一影像资料同时进行人工智能评估。

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

Adopt homologous pairs design: nodules collected respectively by the three high qualification doctor and nine primary physician using blinded to read and draw a conclusion, the same image data to evaluate artificial intelligence at the same time.

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:

Blinding:

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):

2019年6月30日前,http://www.zjradiology.com/

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

before Jun 30, 2019 on http://www.zjradiology.com/

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:

采用电子记录

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

electronic data capture

数据与安全监察委员会:

Data and Safety Monitoring Committee:

暂未确定/Not yet

注册人:

Name of Registration:

 2018-05-21 19:27:52