ChiCTR2600126451 版本V1.0 版本创建时间2026/06/09 14:41:06 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:

ChiCTR2600126451 

最近更新日期:

Date of Last Refreshed on:

2026-06-09 14:40:46 

注册时间:

Date of Registration:

2026-06-09 00:00:00 

注册号状态:

补注册

Registration Status:

Retrospective registration

注册题目:

基于3.0T MRI的人工智能模型对膝关节软骨损伤程度的评价

Public title:

Evaluation of Knee Cartilage Injury Severity by an Artificial Intelligence Model Based on 3.0T MRI

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于3.0T MRI的人工智能模型对膝关节软骨损伤程度的评价

Scientific title:

Evaluation of Knee Cartilage Injury Severity by an Artificial Intelligence Model Based on 3.0T MRI

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:

李兴华 

研究负责人:

李兴华 

Applicant:

Li Xinghua 

Study leader:

Li Xinghua 

申请注册联系人电话:

Applicant telephone:

+86 29 8767 9617

研究负责人电话:

Study leader's
telephone:

+86 29 8767 9617

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:

lixinghua2020@xjtu.edu.cn

研究负责人电子邮件:

Study leader's E-mail:

lixinghua2020@xjtu.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:

陕西省西安市新城区西五路157号

研究负责人通讯地址:

陕西省西安市新城区西五路157号

Applicant address:

No. 157, Xiwu Road, Xincheng District, Xi'an City, Shaanxi Province

Study leader's address:

No. 157, Xiwu Road, Xincheng District, Xi'an City, Shaanxi Province

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:

西安交通大学第二附属医院

Applicant's institution:

The Second Affiliated Hospital of Xi’an Jiaotong University

研究负责人所在单位:

西安交通大学第二附属医院

Affiliation of the Leader:

The Second Affiliated Hospital of Xi’an Jiaotong 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 伦审 236

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:

西安交通大学第二附属医院医学伦理委员会

Name of the ethic committee:

Medical Ethics Committee of The Second Affiliated Hospital of Xi’an Jiaotong University

伦理委员会批准日期:

Date of approved by ethic committee:

2025-10-25 00:00:00

伦理委员会联系人:

李涵

Contact Name of the ethic committee:

Li Han

伦理委员会联系地址:

陕西省西安市皇城西路30号

Contact Address of the ethic committee:

No. 30, Huangcheng West Road, Xi’An, Shaan’Xi,China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 29 8767 8326

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:

西安交通大学第二附属医院

Primary sponsor:

The Second Affiliated Hospital of Xi’an Jiaotong University

研究实施负责(组长)单位地址:

陕西省西安市新城区西五路157号

Primary sponsor's address:

No. 157, Xiwu Road, Xincheng District, Xi'an City, Shaanxi Province

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

陕西省

市(区县):

Country:

China

Province:

Shaanxi

City:

单位(医院):

西安交通大学第二附属医院

具体地址:

陕西省西安市新城区西五路157号

Institution
hospital:

The Second Affiliated Hospital of Xi’an Jiaotong University

Address:

No. 157, Xiwu Road, Xincheng District, Xi'an City, Shaanxi Province

经费或物资来源:

自筹

Source(s) of funding:

Self-funded

研究疾病:

膝骨关节炎  

Target disease:

Knee Osteoarthritis

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:

诊断试验诊断准确性 

Study design:

Diagnostic test for accuracy 

研究目的:

构建基于深度学习的软骨损伤评估模型并验证模型对早期软骨损伤的诊断效能  

Objectives of Study:

Develop a deep-learning-based model for cartilage injury assessment and validate its diagnostic performance in detecting early-stage cartilage damage.

药物成份或治疗方案详述:

 

Description for medicine or protocol of treatment in detail:

 

纳入标准:

已在我科行3.0T 膝关节MR检查的膝关节疼痛患者及体检人员,年龄20岁到80岁。

Inclusion criteria

Individuals aged 20–80 years who underwent 3.0 T knee MRI in our department, including both patients with knee pain and asymptomatic subjects undergoing health check-ups.

排除标准:

1.膝关节术后; 2.MR数据不全; 3.因外伤行MRI检查; 4.近3个月内有膝关节内注射史; 5.有类风湿性关节炎、创伤性关节炎、结核性关节炎、化脓性关节炎、痛风性关节炎病史。

Exclusion criteria:

1. History of knee surgery 2. Incomplete MRI data 3. MRI performed due to acute trauma 4. Intra-articular knee injection within the past 3 months 5. History of rheumatoid, traumatic, tuberculous, purulent, or gouty arthritis.

研究实施时间:

Study execute time:

From 2025-10-30 00:00:00 To 2027-12-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2025-10-30 00:00:00 To 2026-01-08 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):

由两名有经验的骨关节学组影像诊断医师共同评估膝关节软骨损伤程度分级并达成一致

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):

Two experienced musculoskeletal radiologists jointly assessed and reached consensus on the grading of knee cartilage injury severity.

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):

基于3.0T MRI的人工智能模型

Index test:

Artificial Intelligence Model Based on 3.0T MRI

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)

膝骨关节炎患者

例数:

Sample size:

740

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 knee osteoarthritis

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):

类风湿性关节炎、创伤性关节炎、结核性关节炎、化脓性关节炎、痛风性关节炎等

例数:

Sample size:

10

Population with condition difficult to distinguish from the target condition, the normal population in a case-control study design should be avoid:

Rheumatoid arthritis, post-traumatic arthritis, tuberculous arthritis, septic (purulent) arthritis, and gouty arthritis

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

陕西省 

市(区县):

 

Country:

China

Province:

Shaanxi

City:

单位(医院):

西安交通大学第二附属医院 

单位级别:

三甲 

Institution
hospital:

The Second Affiliated Hospital of Xi’an Jiaotong University

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

ROC曲线下面积

指标类型:

主要指标

Outcome:

Area Under the ROC 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:

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:

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:

加权 F1-score

指标类型:

次要指标

Outcome:

Weighted F1-score

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

Dice 系数

指标类型:

次要指标

Outcome:

Dice coefficient

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

平均表面距离

指标类型:

主要指标

Outcome:

Average Surface Distance

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

特征可解释性

指标类型:

次要指标

Outcome:

feature interpretability

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:

NO

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:

结束

/Completed

年龄范围:

Participant age:

最小 Min age 20 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):

NO

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):

预计共享时间为:试验完成后公开;共享方式为:采用临床试验公共管理平台并向公众开放查询。

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

Expected sharing time: to be made public after the trial is completed. Sharing method: using a public clinical trial management platform that is open to public inquiry.

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:

本研究的数据采集和管理采用Excel表格与电子数据采集系统(Electronic Data Capture, EDC)相结合的方式,确保数据的完整性、准确性与可追溯性。 1. Excel表格: 研究过程中所有原始数据将首先记录在Excel表格中; 内容包括:患者姓名、扫描部位、关节软骨损伤程度分级; Excel表格由经过培训的研究人员填写,并由两人交叉核对以确保数据准确。 2. 电子采集与管理系统(EDC) 本研究采用ResMan临床试验注册与数据管理公共平台作为EDC系统; 所有Excel表格内数据在核对无误后,将由专人录入EDC系统,系统设有自动逻辑检查功能以控制录入质量; 数据管理负责人定期备份数据,并设置访问权限以保障数据安全; 数据锁定前,所有数据将由研究团队进行统一核查与确认,确保其真实性与可用性。

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

Data collection and management will be performed through a hybrid system combining Excel spreadsheets with an Electronic Data Capture (EDC) platform to guarantee completeness, accuracy, and full traceability. Excel spreadsheets ? All source data will first be recorded in standardized Excel case-report forms. ? Each form contains: patient initials, anatomical region scanned, and grade of articular-cartilage damage. ? Forms are completed by trained study staff and cross-checked by a second reviewer to ensure accuracy. Electronic Data Capture system (EDC) ? ResMan, a public clinical-trial registry and data-management platform, serves as the EDC system. ? After verification, data from the Excel files are entered into ResMan by designated personnel; built-in logic checks automatically flag inconsistencies. ? The data manager performs regular backups and assigns role-based access to safeguard security. ? Before database lock, the entire study team will conduct a unified review and confirmation of all records to ensure authenticity and usability.

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:

 2026-06-09 14:40:46