ChiCTR2500112344 版本V1.0 版本创建时间2025/11/12 17:30:08 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:

ChiCTR2500112344 

最近更新日期:

Date of Last Refreshed on:

2025-11-12 17:29:37 

注册时间:

Date of Registration:

2025-11-12 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于深度学习的肝脏局灶性病变恶性筛查

Public title:

Malignant screening of focal liver lesions based on deep learning

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于深度学习的肝脏局灶性病变恶性筛查

Scientific title:

Malignant screening of focal liver lesions based on deep learning

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:

李倩 

研究负责人:

魏毅 

Applicant:

Li Qian 

Study leader:

Wei Yi 

申请注册联系人电话:

Applicant telephone:

+86 158 8113 1639

研究负责人电话:

Study leader's
telephone:

+86 181 0800 8568

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:

1158337590@qq.com

研究负责人电子邮件:

Study leader's E-mail:

drweiyi057@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:

成都市武侯区国学巷37号

研究负责人通讯地址:

成都市武侯区国学巷37号

Applicant address:

No. 37, Guoxue Lane, Wuhou District, Chengdu

Study leader's address:

No. 37, Guoxue Lane, Wuhou District, Chengdu

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:

四川大学华西医院放射科

Applicant's institution:

Department of radiology, West China Hospital, Sichuan University

研究负责人所在单位:

四川大学华西医院放射科

Affiliation of the Leader:

Department of radiology, West China Hospital, Sichuan University

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:

2025年审(1954)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:

四川大学华西医院生物医学伦理审查委员会

Name of the ethic committee:

Biomedical Ethics Review Committee of West China Hospital, Sichuan University

伦理委员会批准日期:

Date of approved by ethic committee:

2025-10-21 00:00:00

伦理委员会联系人:

陈诗琦

Contact Name of the ethic committee:

Chen Shiqi

伦理委员会联系地址:

成都市武侯区国学巷37号

Contact Address of the ethic committee:

No. 37, Guoxue Lane, Wuhou District, Chengdu

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 28 8542 2654

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:

四川大学华西医院

Primary sponsor:

West China Hospital, Sichuan University

研究实施负责(组长)单位地址:

成都市武侯区国学巷37号

Primary sponsor's address:

No. 37, Guoxue Lane, Wuhou District, Chengdu

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

四川省

市(区县):

Country:

China

Province:

Sichuan

City:

单位(医院):

四川大学华西医院

具体地址:

成都市武侯区国学巷37号

Institution
hospital:

Sichuan University, West China Hospital

Address:

No. 37, Guoxue Lane, Wuhou District, Chengdu

经费或物资来源:

国家自然科学基金-青年项目(82202117)

Source(s) of funding:

National Natural Science Foundation of China - Youth Project (82202117)

研究疾病:

肝脏局灶性病变  

Target disease:

focal liver lesions

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:

横断面 

Study design:

Cross-sectional 

研究目的:

1)构建适配国内人群的深度学习模型:基于国内肝癌患者 CT 影像数据,开发并优化深度学习算法,提升对微小病灶(尤其是早期肝癌病灶)的特征提取与识别能力,解决现有模型对本土人群适配性不足的问题。 2)提升 CT 影像筛查效能:通过模型辅助阅片,降低人工阅片的漏诊、误诊率,同时缩短阅片时间,突破传统筛查依赖医师经验、效率低的局限,满足大规模筛查需求。 3)推动基层落地应用:探索模型在基层医疗机构的部署方案,提供轻量化、易操作的辅助筛查工具,弥补基层医疗资源不足的短板,助力肝癌早筛在基层普及。 4)形成可推广的筛查方案:结合模型性能验证结果,构建 “CT 影像 + 深度学习” 的肝癌早筛流程,为临床提供标准化、精准化的筛查参考,推动智能技术与肝癌早筛临床实践深度融合。  

Objectives of Study:

1) Build a deep learning model suitable for the domestic population: Based on the CT image data of domestic liver cancer patients, develop and optimize deep learning algorithms to enhance the feature extraction and recognition capabilities for tiny lesions (especially early-stage liver cancer lesions), and address the issue of insufficient adaptability of existing models to the local population. 2) Enhance the efficiency of CT image screening: By using model-assisted film reading, the rates of missed diagnosis and misdiagnosis caused by manual film reading can be reduced, while also shortening the film reading time. This breaks through the limitations of traditional screening that relies on the experience of physicians and is inefficient, meeting the demands of large-scale screening. 3) Promote the application at the grassroots level: Explore the deployment plan of the model in grassroots medical institutions, provide lightweight and easy-to-operate auxiliary screening tools, make up for the shortage of grassroots medical resources, and facilitate the popularization of early screening for liver cancer at the grassroots level. 4) Develop a scalable screening program: Based on the performance verification results of the model, construct a liver cancer early screening process of "CT images + deep learning" to provide standardized and precise screening references for clinical practice and promote the in-depth integration of intelligent technology with clinical practice of liver cancer early screening.

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.患者年龄>=18 岁; 2.患者在 CT 检查前无肝切除术、经动脉化疗栓塞(TACE)、射频消融(RFA)病史; 3.恶性肿瘤经病理证实; 4.良性病灶需满足以下任一条件:(1)由 3 名放射科医师共同诊断确认;(2)通过两种影像学检查方式随访至少 6 个月证实。

Inclusion criteria

1. Patient age >= 18 years; 2. No history of liver resection, transarterial chemoembolisation (TACE), or radiofrequency ablation (RFA) prior to CT examination; 3. Malignant tumour confirmed by pathology; 4. Benign lesions must meet either of the following criteria: (1) Diagnosis confirmed by three radiologists; (2) Verified through follow-up with at least two imaging modalities over a minimum period of six months.

排除标准:

1.影像质量不佳; 2.曾接受手术治疗; 3.目标检测框与病灶不匹配; 4.缺少 CT 动脉期(AP)/ 门静脉期(PVP)图像。

Exclusion criteria:

1. Substandard image quality; 2. Previous surgical intervention; 3. Mismatch between target detection box and lesion; 4. Absence of CT arterial phase (AP)/portal venous phase (PVP) images.

研究实施时间:

Study execute time:

From 2025-11-17 00:00:00 To 2026-01-15 00:00:00  

征募观察对象时间:

Recruiting time:

From 2025-11-21 00:00:00 To 2025-12-10 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):

肝细胞癌、肝内胆管细胞癌等恶性疾病经病理证实; 良性病灶需满足以下任一条件:(1)由 3 名放射科医师共同诊断确认;(2)通过两种影像学检查方式随访至少 6 个月证实。

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):

Hepatocellular carcinoma, intrahepatic cholangiocarcinoma and other malignant diseases must be pathologically confirmed; Benign lesions must satisfy either of the following conditions: (1) jointly diagnosed and confirmed by three radiologists; (2) verified through follow-up using two imaging modalities for at least six months.

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):

“CT 影像 + 深度学习” 的肝癌早筛流程

Index test:

The early screening process for liver cancer based on "CT imaging + deep learning"

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)

年龄大于18岁怀疑患有肝脏局灶性病变患者。

例数:

Sample size:

5000

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 aged 18 years older and suspected of having focal liver lesions (including but not limited to liver cancer, hepatocellular carcinoma, liver metastasis, liver hemangioma, liver cyst, and liver nodule)

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):

四川 

市(区县):

 

Country:

China

Province:

Sichuan

City:

单位(医院):

四川大学华西医院 

单位级别:

三甲 

Institution
hospital:

Sichuan University, West China Hospital

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

河南 

市(区县):

 

Country:

China

Province:

Henan

City:

单位(医院):

河南省人民医院 

单位级别:

三甲 

Institution
hospital:

Henan Provincial People's Hospital

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

海南 

市(区县):

 

Country:

China

Province:

Hainan

City:

单位(医院):

三亚市人民医院 

单位级别:

三甲 

Institution
hospital:

Sanya People’s Hospital

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

四川 

市(区县):

 

Country:

China

Province:

Sichuan

City:

单位(医院):

成都医学院第一附属医院 

单位级别:

三甲 

Institution
hospital:

Chengdu Medical College First Affiliated 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):

武汉大学人民医院 

单位级别:

三甲 

Institution
hospital:

Wuhan University People's Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

曲线下的面积

指标类型:

主要指标

Outcome:

Area under the curve

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

召回率

指标类型:

主要指标

Outcome:

Recall

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

准确性

指标类型:

主要指标

Outcome:

Precision

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:

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:

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

使用后销毁  

说明

Fate of sample:

Destruction after use  

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 18 years
最大 Max age 80 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

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):

文章结果发表1年后进行数据共享,共享平台采用ResMan, 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):

One year after the publication of the article results, data sharing will be conducted using 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:

病例记录表 (CRF):创建一个标准化的病例记录表,包含所有需要收集的病例信息字段。这可能包括患者的基本信息、临床病史等。确保病例记录表的设计符合研究目的和数据采集要求。字段应清晰明了,便于填写和审核。为每位患者创建一个唯一的标识符,以便在整个数据集中唯一标识每个病例。提供清晰的填写说明,确保研究人员能够正确理解和录入信息。 电子采集和管理系统 (EDC):在EDC系统中设置相应的病例记录表,确保系统能够按照CRF的设计进行数据采集。进行培训,确保研究人员熟悉EDC系统的操作,包括数据录入、修改和审核等功能。实施数据验证规则,以确保数据的完整性和准确性。设置访问权限,保护数据的安全性,确保只有授权人员能够访问和修改数据。 数据采集和管理过程:确保所有参与数据采集和管理的人员都了解研究伦理规范和数据保护法规。定期进行数据监测和质量控制,确保数据的一致性和准确性。保留数据采集过程的详细记录,包括数据修改的原因和日期。遵循相关伦理委员会的规定,确保数据采集和管理的合法性和透明度。

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

Case Record Form (CRF):Create a standardized Case Record Form that includes all the necessary fields for collecting case information. This may include basic patient information, clinical history, laboratory tests, CT image features, etc. Ensure that the design of the CRF aligns with the research objectives and data collection requirements. Fields should be clear and easy to fill in and review. Assign a unique identifier for each patient to uniquely identify each case throughout the dataset. Provide clear instructions for filling out the CRF, ensuring that researchers can correctly understand and enter information. Electronic Data Capture and Management System (EDC): If collecting data electronically, choose a suitable Electronic Data Capture and Management System (EDC). Common EDC systems include OpenClinica, REDCap, Medidata, etc. Set up the corresponding CRF within the EDC system, ensuring that the system can collect data according to the CRF design. Conduct training to ensure that researchers are familiar with the operation of the EDC system, including data entry, modification, and auditing functions. Implement data validation rules to ensure the integrity and accuracy of the data. Set access permissions to protect the security of the data, ensuring that only authorized personnel can access and modify it. Data Collection and Management Process: Ensure that all personnel involved in data collection and management are familiar with research ethical standards and data protection regulations. Conduct regular data monitoring and quality control to ensure the consistency and accuracy of the data. Keep detailed records of the data collection process, including reasons and dates for data modifications. Follow the regulations of the relevant ethics committees to ensure the legality and transparency of data collection and manageme

数据与安全监察委员会:

Data and Safety Monitoring Committee:

有/Yes

注册人:

Name of Registration:

 2025-11-12 17:29:37