基于深度学习的两阶段人工智能系统辅助放射科医生利用对比增强乳房X线摄影图像对乳腺病变进行检测和分类

注册号:

Registration number:

ChiCTR2200065169 

最近更新日期:

Date of Last Refreshed on:

2023-05-28 16:59:31 

注册时间:

Date of Registration:

2022-10-30 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于深度学习的两阶段人工智能系统辅助放射科医生利用对比增强乳房X线摄影图像对乳腺病变进行检测和分类

Public title:

A two-stage artificial intelligence system based on deep learning assists radiologists to detect and classify breast lesions using Contrast Enhanced Mammography

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于深度学习的两阶段人工智能系统辅助放射科医生利用对比增强乳房X线摄影图像对乳腺病变进行检测和分类

Scientific title:

A two-stage artificial intelligence system based on deep learning assists radiologists to detect and classify breast lesions using Contrast Enhanced Mammography

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:

陈玉倩 

研究负责人:

毛宁 

Applicant:

Chen Yuqian 

Study leader:

Mao Ning 

申请注册联系人电话:

Applicant telephone:

+86 178 6112 6238

研究负责人电话:

Study leader's
telephone:

+86 131 0535 1972

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:

yuqianchen2@163.com

研究负责人电子邮件:

Study leader's E-mail:

maoning@pku.edu.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:

山东省烟台市莱山区观海路191号

研究负责人通讯地址:

烟台市芝罘区毓璜顶东路20号

Applicant address:

191, Guanhai Road, Laishan District, Yantai, Shandong

Study leader's address:

20, Yuhuangding East Road, Zhifu District, Yantai, Shandong

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:

山东工商学院

Applicant's institution:

Shandong Technology and Business University

研究负责人所在单位:

烟台毓璜顶医院

Affiliation of the Leader:

Yantai Yuhuangding 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:

2022-176

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:

烟台毓璜顶医院医学伦理委员会

Name of the ethic committee:

Yantai Yuhuangding Hospital Medical Ethics Committee

伦理委员会批准日期:

Date of approved by ethic committee:

2022-09-20 00:00:00

伦理委员会联系人:

宋西城

Contact Name of the ethic committee:

Song Xicheng

伦理委员会联系地址:

山东省烟台市芝罘区毓璜顶东路20号

Contact Address of the ethic committee:

20, Yuhuangding East Road, Zhifu District, Yantai, Shandong

伦理委员会联系人电话:

Contact phone of the ethic committee:

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:

烟台毓璜顶医院

Primary sponsor:

Yantai Yuhuangding Hospital

研究实施负责(组长)单位地址:

烟台市芝罘区毓璜顶东路20号

Primary sponsor's address:

20, Yuhuangding East Road, Zhifu District, Yantai, Shandong

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

山东

市(区县):

烟台

Country:

China

Province:

Shandong

City:

Yantai

单位(医院):

烟台毓璜顶医院

具体地址:

山东省烟台市芝罘区毓璜顶东路20号

Institution
hospital:

Yantai Yuhuangding Hospital

Address:

20, Yuhuangding East Road, Zhifu District, Yantai, Shandong

经费或物资来源:

课题经费

Source(s) of funding:

Project funding

研究疾病:

乳腺癌  

Target disease:

Breast cancer

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:

连续入组 

Study design:

Sequential 

研究目的:

基于深度学习利用治疗前的CESM图像构建了一个两阶段的人工智能模型利用多视图和多模态的图像信息检测乳腺病变并辅助放射科医生更加准确快速地进行良恶性分类,本研究为乳腺癌患者后续方案的制定提供一定的指导作用。  

Objectives of Study:

Aimed to develop and validate a two-stage artificial intelligence model to detect breast lesions using multi-view and multi-modal image information and assist radiologists to classify benign and malignant tumors more accurately and quickly with breast cancer using CESM. The study provides some guidance for the formulation of follow-up plans for breast cancer patients.

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.有先前的放化疗或恶性肿瘤病史。 2.临床或病理信息不完整。 3.图像质量差。 4.有多个、双侧或非质量病变。

Exclusion criteria:

1. Have a previous history of radiotherapy, chemotherapy, or malignant tumors. 2. Incomplete clinical or pathological information. 3. Poor image quality. 4. There are multiple, bilateral, or non mass lesions.

研究实施时间:

Study execute time:

From 2022-11-02 00:00:00 To 2022-12-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2022-11-02 00:00:00 To 2022-12-31 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):

病理结果

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):

pathological result

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):

拟绘ROC曲线评估模型性能

Index test:

Draw ROC curve to evaluate model performance

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)

2022年11月-12月在毓璜顶医院拟行术前乳腺病灶CEM检查的患者

例数:

Sample size:

0

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 who will undergo preoperative CEM examination of breast lesions in Yuhuangding Hospital from September to December 2022

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):

山东 

市(区县):

烟台 

Country:

China

Province:

Shandong

City:

Yantai

单位(医院):

烟台毓璜顶医院 

单位级别:

三甲 

Institution
hospital:

Yantai Yuhuangding Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

受试者工作特征曲线

指标类型:

主要指标

Outcome:

receiver operating characteristic curve

Type:

Primary indicator

测量时间点:

测量方法:

两阶段乳腺癌辅助诊断深度学习模型

Measure time point of outcome:

Measure method:

A two-stage deep learning model for assisted diagnosis of breast cancer

指标中文名:

敏感度

指标类型:

主要指标

Outcome:

sensitivity

Type:

Primary indicator

测量时间点:

测量方法:

两阶段乳腺癌辅助诊断深度学习模型

Measure time point of outcome:

Measure method:

A two-stage deep learning model for assisted diagnosis of breast cancer

指标中文名:

特异度

指标类型:

主要指标

Outcome:

specificity

Type:

Primary indicator

测量时间点:

测量方法:

两阶段乳腺癌辅助诊断深度学习模型

Measure time point of outcome:

Measure method:

A two-stage deep learning model for assisted diagnosis of breast cancer

采集人体标本:

Collecting sample(s)
from participants:

标本中文名:

病理切片

组织:

乳腺

Sample Name:

pathological section

Tissue:

breast

人体标本去向

使用后保存  

说明

保存

Fate of sample:

Preservation after use  

Note:

save

征募研究对象情况:

Recruiting status:

尚未开始

Not yet recruiting

年龄范围:

Participant age:

最小 Min age 25 years
最大 Max age 72 years

性别:

女性

Gender:

Female

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

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):

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

None

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:

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

None

数据与安全监察委员会:

Data and Safety Monitoring Committee:

有/Yes

注册人:

Name of Registration:

 2022-10-30 12:55:34