基于深度学习的儿童迁延性细菌性支气管炎CT影像无创识别模型构建与多中心验证

注册号:

Registration number:

ChiCTR2500111741 

最近更新日期:

Date of Last Refreshed on:

2025-11-05 11:20:09 

注册时间:

Date of Registration:

2025-11-05 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于深度学习的儿童迁延性细菌性支气管炎CT影像无创识别模型构建与多中心验证

Public title:

Deep Learning–Based Noninvasive CT Imaging Model for Pediatric Protracted Bacterial Bronchitis: Development and Multicenter Validation

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于深度学习的儿童迁延性细菌性支气管炎CT影像无创识别模型构建与多中心验证

Scientific title:

Deep Learning–Based Noninvasive CT Imaging Model for Pediatric Protracted Bacterial Bronchitis: Development and Multicenter Validation

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:

代继宏 

研究负责人:

代继宏 

Applicant:

Dai jihong 

Study leader:

Dai Jihong 

申请注册联系人电话:

Applicant telephone:

+86 137 0837 2373

研究负责人电话:

Study leader's
telephone:

+86 23 6362 4074

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:

danieljh@163.com

研究负责人电子邮件:

Study leader's E-mail:

daniejh@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:

重庆市渝中区中山二路136号

研究负责人通讯地址:

重庆市渝中区中山二路136号

Applicant address:

Children’s Hospital of Chongqing Medical University, No. 136 Zhongshan Second Road, Yuzhong District

Study leader's address:

No. 136, Zhongshan 2nd Road, Yuzhong District, Chongqing

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:

重庆医科大学附属儿童医院

Applicant's institution:

Children's Hospital of Chongqing Medical University

研究负责人所在单位:

重庆医科大学附属儿童医院

Affiliation of the Leader:

Children's Hospital of Chongqing 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:

(2025)年伦审(临研)第(390)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:

重庆医科大学附属儿童医院医学研究伦理委员会

Name of the ethic committee:

Institutional Review Board Children's Hospital of Chongqing Medical University

伦理委员会批准日期:

Date of approved by ethic committee:

2025-09-17 00:00:00

伦理委员会联系人:

蔡诗容

Contact Name of the ethic committee:

caishirong

伦理委员会联系地址:

重庆市渝中区中山二路136号

Contact Address of the ethic committee:

No. 136, Zhongshan 2nd Road, Yuzhong District, Chongqing

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 23 6837 0035

伦理委员会联系人邮箱:

Contact email of the ethic committee:

741223671@qq.com

研究实施负责(组长)单位:

重庆医科大学附属儿童医院

Primary sponsor:

Children's Hospital of Chongqing Medical University

研究实施负责(组长)单位地址:

重庆市渝中区中山二路136号

Primary sponsor's address:

No. 136, Zhongshan 2nd Road, Yuzhong District, Chongqing

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

重庆市

市(区县):

Country:

China

Province:

Chongqing

City:

单位(医院):

重庆医科大学附属儿童医院

具体地址:

重庆市渝中区中山二路136号

Institution
hospital:

Children's Hospital of Chongqing Medical University

Address:

No. 136, Zhongshan 2nd Road, Yuzhong District, Chongqing

经费或物资来源:

自选课题(自筹)

Source(s) of funding:

Self-raised

研究疾病:

迁延性细菌性支气管炎  

Target disease:

Protracted bacterial bronchitis (PBB)

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:

诊断性病例对照试验 

Study design:

Diagnostic test: case-control 

研究目的:

开发并验证一种可解释的深度学习方法,利用高分辨率胸部 CT 自动识别儿童迁延性细菌性支气管炎(PBB)的影像特征,建立与“支气管镜下脓性分泌物 + BALF 病原学阳性”金标准高度一致的预测模型,实现无创、快速、跨中心可推广的 PBB 辅助诊断工具。  

Objectives of Study:

To develop and externally validate an interpretable deep-learning model that automatically detects imaging signatures of pediatric protracted bacterial bronchitis (PBB) on high-resolution chest CT, achieving high agreement with the reference standard of “endoscopic purulent secretion plus positive BALF culture” and providing a non-invasive, rapid and generalizable diagnostic aid for PBB across different clinical settings.

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.PBB排除标准:①入院后行胸部影像学见肺部絮状、斑片状、条索状或点状阴影者;②合并支原体、百日咳、结核感染者;③以及合并严重心肺或全身性疾病者。
2.非PBB组排除标准:①肺部CT检查提示有明显絮状、斑片状、条索状或点状阴影者;②近期有呼吸道症状。
3.外部验证数据:排除标准同上;

Exclusion criteria:

1.PBB Exclusion Criteria: Patients will be excluded from the PBB group if they meet any of the following conditions: (1) Chest imaging upon admission shows flocculent, patchy, linear, or punctate shadows in the lungs; (2) Co-infection with Mycoplasma, Bordetella pertussis, or tuberculosis; or (3) Co-existing severe cardiopulmonary or systemic diseases.
2.Non-PBB Group Exclusion Criteria:Patients will be excluded from the Non-PBB group if they meet either of the following conditions: (1) Chest CT examination shows **obvious flocculent, patchy, linear, or punctate shadows** in the lungs; or (2) **Recent history of respiratory symptoms.
3.External Validation Data: Exclusion criteria are the same as above.

研究实施时间:

Study execute time:

From 2025-10-01 00:00:00 To 2027-06-30 00:00:00  

征募观察对象时间:

Recruiting time:

From 2025-11-15 00:00:00 To 2025-12-31 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):

支气管镜下脓性分泌物 + BALF 病原学阳性

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):

Endoscopic purulent secretion plus positive BALF culture

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):

一种可解释的深度学习方法,利用高分辨率胸部 CT 自动识别儿童迁延性细菌性支气管炎(PBB)的影像特征,建立与“支气管镜下脓性分泌物 + BALF 病原学阳性”金标准高度一致的预测模型

Index test:

An interpretable deep-learning model that automatically detects imaging signatures of pediatric protracted bacterial bronchitis (PBB) on high-resolution chest CT, achieving high agreement with the reference standard of "endoscopic purulent secretion plus positive BALF culture"

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)

迁延性细菌性支气管炎患者

例数:

Sample size:

400

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 protracted bacterial bronchitis (PBB)

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):

重庆市 

市(区县):

 

Country:

China

Province:

Chongqing

City:

单位(医院):

重庆医科大学附属儿童医院 

单位级别:

三级甲等 

Institution
hospital:

Children's Hospital of Chongqing Medical University

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

云南省 

市(区县):

 

Country:

China

Province:

Yunnan

City:

单位(医院):

开远市人民医院 

单位级别:

三级乙等 

Institution
hospital:

Kaiyuan People's Hospital

Level of the institution:

Tertiary B

国家:

中国

省(直辖市):

四川省 

市(区县):

 

Country:

China

Province:

Sichuan

City:

单位(医院):

成都市妇女儿童中心医院 

单位级别:

三级甲等 

Institution
hospital:

Chengdu Women's and Children's Central Hospital, School of Medicine, University of Electronic Science and Technology of China

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

甘肃省 

市(区县):

 

Country:

China

Province:

Gansu

City:

单位(医院):

甘肃省妇幼保健院 

单位级别:

三级甲等 

Institution
hospital:

Gansu Provincial Maternity and Child-care Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

影像模型诊断 PBB 的准确性

指标类型:

主要指标

Outcome:

Accuracy of imaging model for diagnosing PBB

Type:

Primary indicator

测量时间点:

入院后、支气管镜检查前7天内

测量方法:

全身麻醉下于入院后7天内行支气管镜检查,记录脓性分泌物并定量培养BALF;单一细菌≥10? CFU/mL为微生物学阳性,作为影像模型的参考标准。

Measure time point of outcome:

Within 7 days before bronchoscopy, during the post-admission baseline period.

Measure method:

Bronchoscopy under general anesthesia was performed within 7 days after admission; the presence of purulent secretions was recorded and BALF was cultured quantitatively. A single bacterial species ≥10? CFU/mL defined microbiological positivity, constituting the reference standard for the imaging model.

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 1 years
最大 Max age 18 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

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):

文章在线发表后,即刻作为期刊Supplementary Material的原始数据附件公开,含去身份化DICOM影像、NRRD标注文件、变量表及研究方案,读者可在期刊官网免费下载。

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

Upon online publication, the de-identified DICOM images, NRRD annotation files, data dictionary and study protocol will be released immediately as the journal’s Supplementary Material; all readers can download them free of charge from the journal’s website.

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:

临床数据由Excel病例记录表(CRF)收集并双人核对锁库;DICOM影像从各中心PACS导出后脱敏,加密存储于本地专用服务器,与Excel CRF通过唯一研究编号链接,定期异盘备份,确保数据完整、可追溯。

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

Clinical data were collected in Excel case report forms (CRFs) and double-checked before being locked. DICOM images were de-identified, exported from each centre’s PACS, encrypted and stored on a dedicated local server. CRFs and images were linked by a unique study ID, with regular off-disk backups to ensure completeness and full traceability.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

有/Yes

注册人:

Name of Registration:

 2025-11-05 11:20:03