ChiCTR2300076271 版本V1.1 版本创建时间2024/03/07 11:32:01 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:

ChiCTR2300076271 

最近更新日期:

Date of Last Refreshed on:

2023-09-28 14:49:21 

注册时间:

Date of Registration:

2023-09-28 00:00:00 

注册号状态:

补注册

Registration Status:

Retrospective registration

注册题目:

AI 能否提高病理医生诊断结直肠肿瘤的准确性和效率研究

Public title:

A study on the ability of AI to enhance the accuracy and efficiency of pathologists' diagnosis of colorectal tumor

注册题目简写:

English Acronym:

研究课题的正式科学名称:

AI 能否提高病理医生诊断结直肠肿瘤的准确性和效率研究

Scientific title:

A study on the ability of AI to enhance the accuracy and efficiency of pathologists' diagnosis of colorectal tumor

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:

袁柳红 

研究负责人:

陶琨 

Applicant:

Yuan Liuhong 

Study leader:

Tao Kun 

申请注册联系人电话:

Applicant telephone:

+86 132 0554 3719

研究负责人电话:

Study leader's telephone:

+86 136 3631 6526

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:

2101734350@qq.com

研究负责人电子邮件:

Study leader's E-mail:

taokun20119@163.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:

上海市长宁区仙霞路1111号

研究负责人通讯地址:

上海市长宁区仙霞路1111号

Applicant address:

1111 Xianxia Road, Changning District, Shanghai.

Study leader's address:

1111 Xianxia Road, Changning District, Shanghai.

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:

上海市同仁医院

Applicant's institution:

Shanghai Tongren Hospital

研究负责人所在单位:

上海市同仁医院

Affiliation of the Leader:

Shanghai Tongren 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:

2022-028-01; 2022-028-02

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:

上海市同仁医院

Name of the ethic committee:

Shanghai Tongren Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2022-02-17 00:00:00

伦理委员会联系人:

沈寅胤

Contact Name of the ethic committee:

Shen Yinyin

伦理委员会联系地址:

上海市长宁区仙霞路1111号

Contact Address of the ethic committee:

1111 Xianxia Road, Changning District, Shanghai

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 181 2122 6901

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:

上海市同仁医院

Primary sponsor:

Shanghai Tongren Hospital

研究实施负责(组长)单位地址:

上海市长宁区仙霞路1111号

Primary sponsor's address:

1111 Xianxia Road, Changning District, Shanghai

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

市(区县):

Country:

China

Province:

Shanghai

City:

单位(医院):

上海市同仁医院

具体地址:

上海市长宁区仙霞路1111号

Institution
hospital:

Shanghai Tongren Hospital

Address:

1111 Xianxia Road, Changning District, Shanghai

经费或物资来源:

结直肠腺瘤和结直肠癌患者术后HE切片及临床病理信息来自上海市同仁医院病理科;切片数字扫描仪由成都微识医疗设备有限公司提供;不涉及经费使用。

Source(s) of funding:

Postoperative HE sections and clinicopathological information of colorectal adenoma and colorectal cancer patients were obtained from the Department of Pathology of Shanghai Tongren Hospital. The digital slice scanner is provided by Chengdu Weishi Medical Equipment Co., LTD. No funds are involved.

Target disease:

Colorectal adenoma and colorectal cancer

Target disease code:

研究类型:

诊断试验

Study type:

Diagnostic test

研究所处阶段:

回顾性研究 

Study phase:

Retrospective study

研究设计:

诊断试验诊断准确性 

Study design:

Diagnostic test for accuracy 

研究目的:

恶性肿瘤的病理诊断是复杂的,尽管人工智能(AI)-病理学家相结合的诊断模式提高了肿瘤的诊断效率,但这种医学人工智能系统所带来的有效性是否显著目前尚不明确,这需要通过客观的实验研究来证明。 PathoCruz (AI)模型是利用TCGA结直肠癌(CRC)组织病理学图像数据库,通过采用由深度学习研究驱动的CNN开发的。PathoCruz可以在500 μm的尺度上识别和定位目标,同时实现过程自动化。本研究根据连续样本定义了纳入和排除标准,符合四级深度学习研究的标准。主要集中在PathoCruz分析,特别是评估预定义的性能指标,如敏感性,特异性,比较病理学家在使用和不使用人工智能辅助时的诊断准确性,以评估人工智能对改善诊断结果的影响。 因此,本研究的实验设计严格遵循了四级深度学习研究的标准,这为人工智能在辅助病理诊断中的意义提供了有价值的见解。  

Objectives of Study:

The pathology diagnosis of malignancy can be complex and expertise-intensive. Although artificial intelligence (AI)-pathologists-interaction improves pathological diagnoses, the medical validity of such AI systems needs to be clarified via unbiased and robust external cohort. The PathoCruz (AI) model was developed, leveraging the TCGA database of histopathological images of colorectal cancer (CRC), by employing a CNN powered by a deep learning study. PathoCruz can identify and localize targets at a scale of 500 μm, while automating the process.The current study was defined the criteria of the inclusion and exclusion based on consecutive samples, in accordance with the standards of a level IV deep learning study. The primary analysis focused on PathoCruz analysis, specifically evaluating pre-defined performance metrics such as sensitivity, specificity. The evaluation aimed to compare the diagnostic accuracy of pathologists when working with and without AI assistance to assess the impact of AI in improving diagnostic outcomes. Hence, the experimental design of the current study was strictly adhere to the standards of a level IV deep learning study, which provides valuable insights into the significance of AI in assistance of pathological diagnosis.

药物成份或治疗方案详述:

 

Description for medicine or protocol of treatment in detail:

 

纳入标准:

性别、年龄不限,经病理确诊为结直肠腺瘤和结直肠癌的患者。

Inclusion criteria

Patients with colorectal adenoma and colorectal cancer were diagnosed pathologically regardless of gender or age.

排除标准:

1. 无法被数字病理扫描仪转化为数字病理切片 2. 切片存在制片问题,如模糊等 3. 切片无 MPP(Micro per Pixel)值

Exclusion criteria:

1. Cannot be converted to digital pathology slides by digital pathology scanners. 2. Problems with photographs, e.g., blurring, etc. 3. Dividing can not be done without MPP (Micro per Pixel) value.

研究实施时间:

Study execute time:

From 2022-06-10 00:00:00 To 2023-02-20 00:00:00  

征募观察对象时间:

Recruiting time:

From 2022-07-01 00:00:00 To 2022-07-31 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):

高级病理医生的诊断结果

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 diagnosis of the senior pathologist

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):

病理学家在使用和不使用人工智能辅助时的诊断的特异性和敏感性

Index test:

The sensitivity and specificity of pathologists when working with and without AI assistance.

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)

结直肠腺瘤患者、结直肠癌的患者

例数:

Sample size:

886

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):

Colorectal adenoma patients, colorectal cancer patients

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:

N/A

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

上海市 

市(区县):

 

Country:

China 

Province:

Shanghai 

City:

 

单位(医院):

上海市同仁医院 

单位级别:

三乙 

Institution
hospital:

Shanghai Tongren Hospital

Level of the institution:

Tertiary B

测量指标:

Outcomes:

指标中文名:

敏感性

指标类型:

主要指标

Outcome:

Sensitivity

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

特异性

指标类型:

主要指标

Outcome:

Specificity

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

病理医生及AI人工智能诊断出结直肠腺瘤或者结直肠癌所需的时间

指标类型:

次要指标

Outcome:

The time required for pathologists and AI artificial intelligence to diagnose colorectal adenomas or colorectal cancer

Type:

Secondary 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:

组织

组织:

结直肠腺瘤

Sample Name:

Tissue

Tissue:

colorectal adenoma

人体标本去向

使用后保存  

说明

Fate of sample:

Preservation after use  

Note:

标本中文名:

组织

组织:

结直肠腺癌

Sample Name:

Tissue

Tissue:

Colorectal adenocarcinoma

人体标本去向

使用后保存  

说明

Fate of sample:

Preservation after use  

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 90 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:

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

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):

临床试验公共管理平台 http://www.medresman.org.cn/login.aspx

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

ResMan http://www.medresman.org.cn/login.aspx

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:

病理科电子病历系统

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

Electronic medical record system in pathology department

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:

 2023-09-28 14:49:17