ChiCTR2600127035 版本V1.0 版本创建时间2026/06/23 11:45:27 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:

ChiCTR2600127035 

最近更新日期:

Date of Last Refreshed on:

2026-06-23 11:44:29 

注册时间:

Date of Registration:

2026-06-23 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于人工智能深度学习端到端多任务学习的髋关节盂唇“分割-诊断”一体化模型构建

Public title:

Construction of an Integrated Model for Hip Acetabular Labrum Segmentation and Diagnosis Based on Artificial Intelligence Deep Learning End-to-End Multi-Task Learning

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于人工智能深度学习端到端多任务学习的髋关节盂唇“分割-诊断”一体化模型构建

Scientific title:

Construction of an Integrated Model for Hip Acetabular Labrum Segmentation and Diagnosis Based on Artificial Intelligence Deep Learning End-to-End Multi-Task 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:

何克 

研究负责人:

何克 

Applicant:

HeKe 

Study leader:

HeKe 

申请注册联系人电话:

Applicant telephone:

+86 153 9032 8188

研究负责人电话:

Study leader's telephone:

+86 825 226 7622

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:

heke12@163.com

研究负责人电子邮件:

Study leader's E-mail:

heke12@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:

四川省遂宁市船山区河东新区东平北路27号

研究负责人通讯地址:

德胜西路127号

Applicant address:

No. 27, Dongping North Road, Hedong New District, Chuanshan District, Suining City, Sichuan Province

Study leader's address:

No.127, West Desheng Rd., Chuanshan District, Suining, Sichuan Province, 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:

遂宁市中心医院

Applicant's institution:

Suining Central Hospital

研究负责人所在单位:

遂宁市中心医院

Affiliation of the Leader:

Suining Central Hospital

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:

KYLLKS20260140

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:

遂宁市中心医院医学科研伦理委员会

Name of the ethic committee:

Medical Researsh Ethics Committee of Suining Central Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2026-05-28 00:00:00

伦理委员会联系人:

王曼

Contact Name of the ethic committee:

Man Wang

伦理委员会联系地址:

德胜西路127号

Contact Address of the ethic committee:

No.127, West Desheng Rd., Chuanshan District, Suining, Sichuan Province, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 825 229 2068

伦理委员会联系人邮箱:

Contact email of the ethic committee:

1063209851@qq.com

研究实施负责(组长)单位:

遂宁市中心医院

Primary sponsor:

Suining Central Hospital

研究实施负责(组长)单位地址:

德胜西路127号

Primary sponsor's address:

No.127, West Desheng Rd., Chuanshan District, Suining, Sichuan Province, 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):

四川省

市(区县):

Country:

China

Province:

Sichuan

City:

单位(医院):

遂宁市中心医院

具体地址:

德胜西路127号

Institution
hospital:

Suining Central Hospital

Address:

No.127, West Desheng Rd., Chuanshan District, Suining, Sichuan Province, China

经费或物资来源:

自选课题(自筹)

Source(s) of funding:

Self-funded project

Target disease:

Hip acetabular labral injury

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:

髋关节盂唇损伤是运动人群髋痛的常见病因,常规MRI漏诊率高、阅片一致性差,基层诊断能力尤为薄弱。本项目旨在构建“自动分割—智能诊断”端到端一体化深度学习模型,实现从MRI影像输入到盂唇精确定位与损伤四分类的整合输出,以技术创新突破现有诊断瓶颈,进而提高基层医院诊断水平高质量发展  

Objectives of Study:

Hip acetabular labral injury is a common cause of hip pain in the athletic population. Conventional MRI suffers from a high missed diagnosis rate and poor inter-reader consistency, with diagnostic capability being particularly weak in primary healthcare settings. This project aims to construct an end-to-end integrated deep learning model for automatic segmentation and intelligent diagnosis, achieving integrated output from MRI image input to precise labral localization and four-category injury classification. Through technological innovation, we aim to break through existing diagnostic bottlenecks and thereby promote high-quality development of diagnostic capabilities in primary hospitals.

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.有完整斜冠状位、斜矢状位脂肪抑制质子密度加权(FS-PD)序列, 层厚≤3mm;
2.有关节镜手术记录或至少2名高年资影像科医师的共识诊断可作为参考 标准;
3.影像资料完整,DICOM信息完备;
4.收集的病例资料为2019年-2026年我院单侧髋关节检查的患者;

Inclusion criteria

1.Complete oblique coronal and oblique sagittal fat?suppressed proton density?weighted (FS?PD) sequences are available, with a slice thickness ≤3?mm;
2.Arthroscopic surgical records or a consensus diagnosis by at least two senior radiologists can serve as the reference standard;
3.Imaging data are complete with full DICOM information;
4.The collected case data are from patients who underwent unilateral hip examinations at our hospital between 2019 and 2026;

排除标准:

1.严重骨性关节炎(T?nnis3级及以上)或已行全髋关节置换者;
2.既往髋关节镜手术或盂唇修复手术史者;
3.影像存在明显金属伪影(如内固定物遮挡盂唇区域)或运动伪影致关键 层面不可评估者;
4.合并髋关节骨折、骨肿瘤、化脓性关节炎等其他严重病变者;
5.年龄<14岁(骨骺未闭合,盂唇形态与成人差异显著);

Exclusion criteria:

1.Patients with severe osteoarthritis (T?nnis grade ≥3) or those who have undergone total hip arthroplasty;
2.Prior history of hip arthroscopic surgery or labral repair surgery;
3.Presence of significant metal artifacts (e.g., internal fixation devices obscuring the labral region) or motion artifacts rendering key planes unevaluable;
4.Concurrent severe hip pathologies including femoral fractures, bone tumors, or septic arthritis;
5.Age <14 years (epiphyseal plate not yet closed, with labral morphology significantly different from that of adults);

研究实施时间:

Study execute time:

From 2026-06-30 00:00:00 To 2028-09-30 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-06-30 00:00:00 To 2027-05-01 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):

关节镜

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):

Arthroscopy

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):

核磁共振

Index test:

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)

髋部疼痛病人

例数:

Sample size:

500

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 hip pain

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):

股骨头缺血性坏死

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:

Avascular necrosis of femoral head

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

四川省 

市(区县):

 

Country:

China 

Province:

Sichuan 

City:

 

单位(医院):

遂宁市中心医院 

单位级别:

三级甲等 

Institution
hospital:

Suining Central Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

髋关节盂唇

指标类型:

主要指标

Outcome:

Labrum of the hip joint

Type:

Primary indicator

测量时间点:

核磁共振检查后

测量方法:

由2名高年资放射科医师(副主任医师以上,髋关节影像诊断经验≥5年)在 3D Slicer 软件中对盂唇进行逐层轮廓勾画

Measure time point of outcome:

After the magnetic resonance imaging (MRI) examination

Measure method:

Two senior radiologists (with senior resident physician qualifications or above, and having ≥ 5 years of experience in hip joint imaging diagnosis) performed the layer-by-layer contour delineation of the labrum using the 3D Slicer software.

指标中文名:

准确度

指标类型:

主要指标

Outcome:

Accuracy

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:

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:

NA

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 14 years
最大 Max age 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:

None

是否共享原始数据:

IPD sharing

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):

联系负责人

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

Contact the responsible person

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:

数据采集:回顾性收集本院放射科2019年-2026年因髋部疼痛行3.0T MRI检查的病例。纳入标准:①有完整斜冠状位、斜矢状位FS-PD序列(层厚≤3mm);②有关节镜手术记录或2名高年资医师共识诊断作为参考标准;③影像资料完整。排除标准:①严重骨性关节炎(T?nnis 3级及以上)或关节置换术后;②既往髋关节镜手术史;③图像存在明显伪影。预计样本量300-500例。 数据管理:采用CRF表记录临床与影像参数,通过电子采集系统(如3D Slicer)进行脱敏标注。由2名高年资放射科医师独立勾画盂唇轮廓及损伤分级(改良Czerny分级),Fleiss‘ Kappa评估一致性。数据存储于医院加密服务器,仅课题组可访问,符合隐私保护规定。

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

Data collection: Retrospectively collect cases of patients in the radiology department of our hospital who underwent 3.0T MRI examinations due to hip pain from 2019 to 2026. Inclusion criteria: 1. Complete sagittal and coronal FS-PD sequences (slice thickness <= 3 mm); 2. Joint arthroscopy surgery records or consensus diagnosis by two senior physicians as reference standards; 3. Complete imaging data. Exclusion criteria: 1. Severe osteoarthritis (Toennis grade 3 or above) or after joint replacement surgery; 2. Previous hip arthroscopy surgery history; 3. Images with obvious artifacts. The estimated sample size is 300-500 cases. Data Management: Clinical and imaging parameters are recorded using CRF forms, and de-sensitized annotations are made through electronic collection systems (such as 3D Slicer). Two senior radiologists independently delineate the labial contour and grade the injury (modified Czerny grading). Fleiss' Kappa is used to assess consistency. The data are stored on the hospital's encrypted server and are accessible only to the research team, in compliance with privacy protection regulations.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

有/Yes

注册人:

Name of Registration:

 2026-06-23 11:44:29