基于多模态影像组学及深度学习构建局灶性肝脏病变精准无创诊断的预测模型研究

注册号:

Registration number:

ChiCTR2500104842 

最近更新日期:

Date of Last Refreshed on:

2025-06-24 16:56:26 

注册时间:

Date of Registration:

2025-06-24 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于多模态影像组学及深度学习构建局灶性肝脏病变精准无创诊断的预测模型研究

Public title:

Research on constructing a predictive model for accurate non-invasive diagnosis of focal liver Lesions based on multimodal radiomics and deep learning

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于多模态影像组学及深度学习构建局灶性肝脏病变精准无创诊断的预测模型研究

Scientific title:

Research on constructing a predictive model for accurate non-invasive diagnosis of focal liver Lesions based on multimodal radiomics and 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:

胡娜 

研究负责人:

雷平贵 

Applicant:

Na Hu 

Study leader:

Pinggui Lei 

申请注册联系人电话:

Applicant telephone:

+86 155 1916 4340

研究负责人电话:

Study leader's
telephone:

+86 187 8611 8165

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:

15519164340@163.com

研究负责人电子邮件:

Study leader's E-mail:

pingguilei@foxmail.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:

贵州省贵阳市贵州医科大学附属医院影像科

研究负责人通讯地址:

贵州省贵阳市贵州医科大学附属医院影像科

Applicant address:

Department of Radiology, The Affiliated Hospital of Guizhou Medical University, Guiyang

Study leader's address:

Department of Radiology, The Affiliated Hospital of Guizhou Medical University, Guiyang

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:

贵州医科大学附属医院

Applicant's institution:

The Affiliated Hospital of Guizhou Medical University

研究负责人所在单位:

贵州医科大学附属医院

Affiliation of the Leader:

The Affiliated Hospital of Guizhou Medical 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:

2025025K

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:

贵州医科大学附属医院研究者发起临床研究伦理委员会

Name of the ethic committee:

Medical Ethics Committee of Affiliated Hospital of Guizhou Medical University

伦理委员会批准日期:

Date of approved by ethic committee:

2025-03-03 00:00:00

伦理委员会联系人:

丁恒

Contact Name of the ethic committee:

Heng Ding

伦理委员会联系地址:

贵阳市云岩区贵医街28号

Contact Address of the ethic committee:

Affiliated Hospital of GuiZhou Medical University Guiyang Guizhou 550004 P.R.China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 851 8675 2685

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:

贵州医科大学附属医院

Primary sponsor:

The Affiliated Hospital of Guizhou Medical University

研究实施负责(组长)单位地址:

贵州省贵阳市云岩区北京路贵医街贵州医科大学附属医院

Primary sponsor's address:

Beijing Road, Guiyi Street, Yunyan District, Guiyang City, Guizhou Province, Affiliated Hospital of Guizhou Medical University, 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):

贵州省

市(区县):

Country:

China

Province:

Guizhou

City:

单位(医院):

贵州医科大学附属医院

具体地址:

贵州省贵阳市云岩区北京路贵医街贵州医科大学附属医院

Institution
hospital:

Affiliated Hospital of Guizhou Medical University

Address:

Beijing Road, Guiyi Street, Yunyan District, Guiyang City, Guizhou Province, Affiliated Hospital of Guizhou Medical University, China

经费或物资来源:

贵州省卫生健康高质量发展医学科研联合基金项目

Source(s) of funding:

Guizhou Provincial Joint Fund for High-Quality Development of Medical Research in Health and Wellness

研究疾病:

局灶性肝脏病变  

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:

回顾性研究 

Study phase:

Retrospective study

研究设计:

病例研究 

Study design:

Case study 

研究目的:

本研究旨在开发一种基于生成对抗网络(GAN)的图像合成模型,利用平扫CT/MR图像合成高质量的腹部三期增强CT/MR图像,用于局灶性肝脏病变(FLLs)的检测,并结合影像组学和深度学习技术构建高精度的无创诊断模型,以实现对FLLs的精准鉴别诊断,降低患者辐射风险和检查成本,同时提高诊断效率和准确性。  

Objectives of Study:

This study aims to develop a GAN-based image synthesis model to generate high-quality triphasic enhanced CT/MR images from non-contrast CT/MR images for the detection of focal liver lesions (FLLs). It will also construct a high-precision non-invasive diagnostic model by integrating radiomics and deep learning techniques to accurately differentiate FLLs, thereby reducing patients' radiation exposure and examination costs while improving diagnostic efficiency and accuracy.

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)图像资料不完整。 (2)肾功能不全和造影剂过敏排除研究。

Exclusion criteria:

(1) Incomplete imaging data. (2) Patients with renal insufficiency and contrast agent allergy are excluded from the study.

研究实施时间:

Study execute time:

From 2025-07-01 00:00:00 To 2028-06-30 00:00:00  

征募观察对象时间:

Recruiting time:

From 2025-07-01 00:00:00 To 2028-06-30 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):

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):

影像组学模型和深度学习模型

Index test:

Radiomics models and deep learning models

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)

影像检查发现局灶性肝脏病变

例数:

Sample size:

800

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):

Imaging examination revealed focal liver lesions

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):

贵州省 

市(区县):

 

Country:

China

Province:

Guizhou

City:

单位(医院):

贵州医科大学附属医院 

单位级别:

三级 

Institution
hospital:

The Affiliated Hospital of Guizhou Medical University

Level of the institution:

Level 3

测量指标:

Outcomes:

指标中文名:

生成图像质量评价

指标类型:

主要指标

Outcome:

Image Quality Assessment

Type:

Primary indicator

测量时间点:

测量方法:

主观评价(采用盲法原则)和客观评价

Measure time point of outcome:

Measure method:

指标中文名:

诊断准确性指标

指标类型:

主要指标

Outcome:

Diagnostic Accuracy Metrics

Type:

Primary indicator

测量时间点:

测量方法:

敏感度,特异度,阳性预测值,阴性预测值,准确性

Measure time point of outcome:

Measure method:

指标中文名:

生成模型性能指标

指标类型:

主要指标

Outcome:

Metrics for Generative Model Performance

Type:

Primary indicator

测量时间点:

测量方法:

生成对抗网络(GAN)的损失函数值,峰值信噪比(PSNR)和结构相似性指数(SSIM),模型的运行时间和计算资源消耗

Measure time point of outcome:

Measure method:

指标中文名:

影像组学及深度学习模型性能评价

指标类型:

次要指标

Outcome:

Performance Evaluation of Radiomics and Deep Learning Models

Type:

Secondary indicator

测量时间点:

测量方法:

准确度、AUC 及其95%CI、灵敏度、特异度、阳性预测值、阴性预测值及F1 分数等

Measure time point of outcome:

Measure method:

指标中文名:

模型开发与验证

指标类型:

次要指标

Outcome:

Model Development and Validation

Type:

Secondary indicator

测量时间点:

测量方法:

训练集和验证集划分,模型验证,模型调优

Measure time point of outcome:

Measure method:

指标中文名:

观察结局

指标类型:

次要指标

Outcome:

Observe the outcome

Type:

Secondary indicator

测量时间点:

测量方法:

图像质量与诊断准确性,患者受益程度,患者受益程度

Measure time point of outcome:

Measure method:

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:

Measure time point of outcome:

Measure method:

指标中文名:

灵敏度

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

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 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:

不公开/Private

盲法:

Blinding:

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:

电子采集和管理系统,PACS系统

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

Electronic acquisition and management system, PACS system

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:

 2025-06-24 16:56:20