ChiCTR2600120532 版本V1.0 版本创建时间2026/03/16 17:24:24 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:

ChiCTR2600120532 

最近更新日期:

Date of Last Refreshed on:

2026-03-16 17:24:19 

注册时间:

Date of Registration:

2026-03-16 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于DCE-MRI的深度学习在乳腺癌诊断中的应用

Public title:

Application of deep learning based on DCE-MRI in the diagnosis of breast cancer

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于多模态影像特征融合和深度学习的乳腺癌诊断和治疗中的应用

Scientific title:

The application of Multimodal image Feature Fusion and deep Learning in the diagnosis and treatment of breast cancer

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:

林凯歌 

研究负责人:

马韵涵 

Applicant:

Lin Kaige 

Study leader:

Ma Yunhan 

申请注册联系人电话:

Applicant telephone:

+86 166 9703 2836

研究负责人电话:

Study leader's telephone:

+86 131 5301 0619

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:

16697032836@163.com

研究负责人电子邮件:

Study leader's E-mail:

invater@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:

中国山东省济南市槐荫区青岛路6699号

研究负责人通讯地址:

中国山东省济南市天桥区师范路25号

Applicant address:

6699 Qingdao Road, Huaiyin District, Jinan, Shandong, China

Study leader's address:

25 Normal Road, Tianqiao District, Jinan, Shandong, 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:

山东省济南市槐荫区青岛路6699号山东第一医科大学

Applicant's institution:

Shandong First Medical University, 6699 Qingdao Road, Huaiyin District, Jinan City, Shandong Province,China

研究负责人所在单位:

山东省济南市天桥区师范路25号中国人民解放军联勤保障部队第960医院

Affiliation of the Leader:

The 960th Hospital of the PLA Joint Logistics Support Force, 25 Normal Road, Tianqiao District, Jinan City, Shandong Province, China

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:

(2025) 科研伦理审第 (239) 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:

解放军第九六〇医院科研伦理委员会

Name of the ethic committee:

Research Ethics Committee of The 960th Hospital of the PLA Joint Logistic Support Force

伦理委员会批准日期:

Date of approved by ethic committee:

2025-12-16 00:00:00

伦理委员会联系人:

孙志东

Contact Name of the ethic committee:

Sun Zhidong

伦理委员会联系地址:

中国山东省济南市天桥区师范路25号

Contact Address of the ethic committee:

25 Normal Road, Tianqiao District, Jinan, Shandong, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 531 5166 6145

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:

中国人民解放军联勤保障部队第960医院

Primary sponsor:

The 960th Hospital of the PLA Joint Logistics Support Force

研究实施负责(组长)单位地址:

中国山东省济南市天桥区师范路25号

Primary sponsor's address:

25 Normal Road, Tianqiao District, Jinan, Shandong, 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):

山东

市(区县):

济南

Country:

China

Province:

Shandong

City:

Jinan

单位(医院):

中国人民解放军联勤保障部队第960医院

具体地址:

中国山东省济南市天桥区师范路25号

Institution
hospital:

The 960th Hospital of the PLA Joint Logistics Support Force

Address:

25 Normal Road, Tianqiao District, Jinan, Shandong, China

经费或物资来源:

联勤保障部队第960医院课题经费

Source(s) of funding:

Project funds of The 960th Hospital of the PLA Joint Logistics Support Force

Target disease:

Breast cancer

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:

实现多种分类模型的构建,包括鉴别肿块良恶性的模型,不同分子亚型的模型,判定Ki-67等免疫组化指标表达水平的高低的模型,评估淋巴结是否有转移的模型。  

Objectives of Study:

The construction of a variety of classification models was realized, including a model to identify benign and malignant lumps, a model for different molecular subtypes, a model to determine the expression level of immunohistochemical indicators such as Ki-67, and a model to evaluate whether there is metastasis in lymph nodes.

药物成份或治疗方案详述:

 

Description for medicine or protocol of treatment in detail:

 

纳入标准:

1. 术前或穿刺前均接受 1.5T/3.0T MRI 乳腺平扫及增强检查,完成所有序列检查并且图像质量合格。穿刺后接受新辅助化疗的患者还应包括化疗中及化疗结束手术前的 MRI 结果; 2. 经过粗针穿刺活检或手术治疗,有病理穿刺结果或手术病理结果,具有完整的免疫组化结果,获得组织学分类、组织学分级、分子分型、新辅助化疗后 Miller & Payne 分级等结果; 3. 有完整的临床资料,包括月经状态、身高、体质量、既往史、手术史等; 4. 对于接受手术治疗的乳腺癌患者,已行同侧腋窝前哨淋巴结活检或腋窝淋巴结清扫术,得到腋窝淋巴结是否有转移及转移数目信息。

Inclusion criteria

1. 1.5T/3.0T MRI plain scan and enhanced examination of the breast were performed before the operation or before puncture. All sequence examinations were completed and the image quality was qualified. For patients who receive neoadjuvant chemotherapy after puncture, the MRI results during chemotherapy and before the surgery after the end of chemotherapy should also be included. 2. After coarse needle puncture biopsy or surgical treatment, there are pathological puncture results or surgical pathological results, with complete immunohistochemical results, obtaining histological classification, histological grade, molecular typing, Miller & Payne grade after neoadjuvant chemotherapy, etc. 3. There are complete clinical data, including menstrual status, height, body weight, past medical history, surgical history, etc. For breast cancer patients undergoing surgical treatment, ipsilateral axillary sentinel lymph node biopsy or axillary lymph node dissection has been performed to obtain information on whether there is metastasis in the axillary lymph nodes and the number of metastases.

排除标准:

1. MRI 检查禁忌证者; 2. 无法行钆喷酸葡胺(Gd-DTPA)增强检查者; 3. 乳腺癌保乳术后复发的患者; 4. 曾接受过患侧乳房手术的患者; 5. 非肿块型乳腺病变; 6. 同时患有其他恶性肿瘤疾病或血液系统疾病; 7. 图像质量不佳或无法勾画病变 ROI 者。

Exclusion criteria:

1. Those with contraindications for MRI examination; 2. Those who are unable to undergo gadopentine meglumine (Gd-DTPA) enhanced examination; 3. Patients with recurrence after breast-conserving surgery for breast cancer; 4. Patients who have undergone surgery on the affected breast; 5. Non-mass breast lesions; 6. Suffering from other malignant tumor diseases or hematological diseases at the same time; 7. Those with poor image quality or inability to delineate the ROI of the lesion.

研究实施时间:

Study execute time:

From 2026-03-15 00:00:00 To 2026-06-30 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-03-16 00:00:00 To 2026-06-30 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):

手术切除或穿刺的病理结果

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 findings of surgical excision or puncture

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):

使用机器学习及深度学习分类模型对良恶分组、病理指标分组、分子分型分组进行诊断

Index test:

Benign and malignant, molecular subtypes

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)

经病理证实的乳腺病变患者

例数:

Sample size:

300

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 breast lesions confirmed by pathology

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):

 

Country:

China 

Province:

Shandong 

City:

 

单位(医院):

中国人民解放军联勤保障部队第960医院 

单位级别:

三甲 

Institution
hospital:

The 960th Hospital of the PLA Joint Logistics Support Force

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

受试者操作特征曲线下面积

指标类型:

主要指标

Outcome:

Area under the operating characteristic curve of the subject

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

准确度

指标类型:

次要指标

Outcome:

Accuracy

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

敏感度

指标类型:

次要指标

Outcome:

Sensitivity

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

特异度

指标类型:

次要指标

Outcome:

Specificity

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:

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:

尚未开始

Not yet recruiting

年龄范围:

Participant age:

最小 Min age 28 years
最大 Max age 80 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

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:

CRF设计:由研究团队自行设计,内容涵盖患者人口学信息、临床病理特征(TNM分期、ER/PR/HER2/Ki-67状态)、影像采集参数及图像质量评估记录。 数据采集流程:影像数据以DICOM格式从PACS系统导出,经脱敏处理后存储于专用服务器。临床病理数据由两名研究人员独立从电子病历系统提取并填写至纸质CRF,经交叉核对后,由双人独立录入ResMan EDC系统。系统内置逻辑核查功能,对异常值实时提示。 质量控制:每月随机抽取10%的病例进行CRF与EDC数据一致性核查。所有数据录入完毕后,由主要研究者审核并锁定数据库。 隐私保护:所有数据均以研究编号标识,去除患者直接身份信息。ResMan系统实行分级权限管理,确保数据安全

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

CRF: A structured paper CRF will capture demographic, clinical, pathological, and imaging parameters. Data Entry & Verification: Clinical data will be extracted from medical records onto the CRF by trained researchers and verified by a second reviewer. Verified data will be independently double-entered into the ResMan EDC system. Imaging Data: DCE-MRI and ultrasound images will be exported in DICOM format, anonymized, and stored on a secure server. Quality Control: The EDC system has built-in logical verification. A 10% random sample will be audited monthly. The database will be locked after verification. Privacy: All data will be de-identified and stored with unique study IDs. Access to the EDC system is role-based and password-protected. Data are backed up weekly.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

有/Yes

注册人:

Name of Registration:

 2026-03-16 17:24:19