通过临床适用的深度学习算法对多视角X线图像进行骨肿瘤风险的前瞻性评估

注册号:

Registration number:

ChiCTR2500102778 

最近更新日期:

Date of Last Refreshed on:

2025-05-20 09:23:58 

注册时间:

Date of Registration:

2025-05-20 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

通过临床适用的深度学习算法对多视角X线图像进行骨肿瘤风险的前瞻性评估

Public title:

Prospective Assessment of Bone Tumor Risk from Multimodal Multiview Radiography Images via Clinically Applicable Deep Learning

注册题目简写:

English Acronym:

研究课题的正式科学名称:

通过临床适用的深度学习算法对多视角X线图像进行骨肿瘤风险的前瞻性评估

Scientific title:

Prospective Assessment of Bone Tumor Risk from Multimodal Multiview Radiography Images via Clinically Applicable 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:

宋春霖 

研究负责人:

郝大鹏 

Applicant:

Chunlin Song 

Study leader:

Dapeng Hao 

申请注册联系人电话:

Applicant telephone:

+86 156 2186 1256

研究负责人电话:

Study leader's
telephone:

+86 186 6180 2582

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:

15621861256@163.com

研究负责人电子邮件:

Study leader's E-mail:

haodp2021@qdu.edu.cn

申请单位网址(自愿提供):

Applicant website(voluntary supply):

The Affiliated Hospital of Qingdao University

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:

山东省青岛市市南区江苏路16号

研究负责人通讯地址:

山东省青岛市市南区江苏路16号

Applicant address:

16 Jiangsu Road, Shinan District, Qingdao, Shandong Province, China

Study leader's address:

16 Jiangsu Road, Shinan District, Qingdao, Shandong Province, China

申请注册联系人邮政编码:

Applicant postcode:

266003

研究负责人邮政编码:

Study leader's postcode:

266003

申请人所在单位:

青岛大学附属医院放射科

Applicant's institution:

Department of Radiology, The Affiliated Hospital of Qingdao University

研究负责人所在单位:

青岛大学附属医院放射科

Affiliation of the Leader:

Department of Radiology, The Affiliated Hospital of Qingdao 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:

QYFYWZLL28985

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:

青岛大学附属医院伦理委员会

Name of the ethic committee:

Ethics Committee of The Affiliated Hospital of Qingdao University

伦理委员会批准日期:

Date of approved by ethic committee:

2025-05-05 00:00:00

伦理委员会联系人:

刘奕辰

Contact Name of the ethic committee:

Yichen Liu

伦理委员会联系地址:

山东省青岛市市南区江苏路16号

Contact Address of the ethic committee:

16 Jiangsu Road, Shinan District, Qingdao, Shandong Province, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 186 6180 2841

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:

青岛大学附属医院放射科

Primary sponsor:

Department of Radiology, The Affiliated Hospital of Qingdao University

研究实施负责(组长)单位地址:

山东省青岛市市南区江苏路16号

Primary sponsor's address:

16 Jiangsu Road, Shinan District, Qingdao, Shandong 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):

山东

市(区县):

青岛

Country:

China

Province:

Shandong

City:

Qingdao

单位(医院):

青岛大学附属医院

具体地址:

山东省青岛市市南区江苏路16号

Institution
hospital:

The Affiliated Hospital of Qingdao University

Address:

16 Jiangsu Road, Shinan District, Qingdao, Shandong Province, China

经费或物资来源:

国家自然科学基金No. 82172035 和 No. 82472067.

Source(s) of funding:

The National Natural Science Foundation of China under Grant No. 82172035 and Grant No. 82472067.

研究疾病:

骨肿瘤  

Target disease:

Bone Tumor

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:

连续入组 

Study design:

Sequential 

研究目的:

通过构建融合临床数据、X线影像深度学习特征与Bone-RADS评分的多模态模型,显著提高骨肿瘤良恶性鉴别的准确率与敏感度,减少误诊与漏诊。开发具有高可解释性的AI辅助诊断工具,帮助医生快速定位病灶、生成诊断报告,提升临床工作效率。利用联邦学习技术,打破数据孤岛,推动多中心数据共享与模型联合优化,为基层医院提供标准化诊断支持。  

Objectives of Study:

By constructing a multimodal model that integrates clinical data, deep learning features from X-ray imaging, and Bone-RADS scores, the accuracy and sensitivity in differentiating benign and malignant bone tumors can be significantly improved, reducing misdiagnosis and missed diagnoses. A highly interpretable AI-assisted diagnostic tool will be developed to help physicians quickly locate lesions and generate diagnostic reports, thereby enhancing clinical efficiency. Utilizing federated learning technology, the model overcomes data silos, promotes multi-center data sharing and joint model optimization, and provides standardized diagnostic support for primary healthcare institutions.

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:

排除标准: (1)影像图像(X线)质量差,影响分析; (2)仅有X线图像,缺乏临床及病理资料; (3)发生在非四肢骨(如脊柱骨、骨盆骨等)的病变或非溶骨性病变。

Exclusion criteria:

Exclusion Criteria: (1) Poor-quality X-ray images that hinder analysis; (2) X-ray images available but lacking corresponding clinical and pathological data; (3) Lesions located in non-limb bones (e.g., spine, pelvis) or non-osteolytic lesions.

研究实施时间:

Study execute time:

From 2024-04-01 00:00:00 To 2026-06-01 00:00:00  

征募观察对象时间:

Recruiting time:

From 2025-06-01 00:00:00 To 2026-06-01 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):

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):

深度学习模型辅助诊断系统

Index test:

AI-Assisted Diagnostic System Based on 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)

经穿刺活检或手术证实为骨肿瘤的患者。(回顾性研究2000例,前瞻性研究200例)

例数:

Sample size:

2200

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 diagnosed with bone tumors confirmed by needle biopsy or surgical resection pathology. The study includes 2,000 retrospective cases and 200 prospective cases.

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):

青岛 

Country:

China

Province:

Shandong

City:

Qingdao

单位(医院):

青岛大学附属医院 

单位级别:

三级甲等 

Institution
hospital:

The Affiliated Hospital of Qingdao University

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 receiver operating characteristic 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:

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:

指标中文名:

准确性

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:

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 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:

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:

EDC

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

EDC

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:

 2025-05-20 09:23:41