基于计算机视觉的术中基底节晕染征识别对机械取栓术后出血转化的预测:多中心真实世界研究

注册号:

Registration number:

ChiCTR2600118594 

最近更新日期:

Date of Last Refreshed on:

2026-02-09 10:27:53 

注册时间:

Date of Registration:

2026-02-09 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于计算机视觉的术中基底节晕染征识别对机械取栓术后出血转化的预测:多中心真实世界研究

Public title:

Computer Vision–Based Intraoperative Identification of the Basal Ganglia Blush Sign for Predicting Hemorrhagic Transformation After Mechanical Thrombectomy: A Multicenter Real-World Study

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于计算机视觉的术中基底节晕染征识别对机械取栓术后出血转化的预测:多中心真实世界研究

Scientific title:

Computer Vision–Based Intraoperative Identification of the Basal Ganglia Blush Sign for Predicting Hemorrhagic Transformation After Mechanical Thrombectomy: A Multicenter Real-World Study

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:

莽靖 

研究负责人:

莽靖 

Applicant:

Jing Mang 

Study leader:

Jing Mang 

申请注册联系人电话:

Applicant telephone:

+86 431 84995916

研究负责人电话:

Study leader's
telephone:

+86 431 8499 5916

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:

mangjing@jlu.edu.cn

研究负责人电子邮件:

Study leader's E-mail:

mangjing@jlu.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:

吉林省长春市南关区仙台大街126号

研究负责人通讯地址:

吉林省长春市仙台大街126号

Applicant address:

No.126 Xiantai Road, Nanguan District, Changchun, China

Study leader's address:

126 Sendai Dajie, Changchun City, Jilin 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:

吉林大学中日联谊医院

Applicant's institution:

China-Japan Union Hospital of Jilin University

研究负责人所在单位:

吉林大学中日联谊医院

Affiliation of the Leader:

China-Japan Union Hospital of Jilin 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)临研审第(2025121103)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:

吉林大学中日联谊医院伦理委员会

Name of the ethic committee:

China-Japan Union Hospital of Jilin University Institutional Review Board

伦理委员会批准日期:

Date of approved by ethic committee:

2025-12-12 00:00:00

伦理委员会联系人:

俞亭伊

Contact Name of the ethic committee:

Yu TingYi

伦理委员会联系地址:

吉林省长春市仙台大街126号

Contact Address of the ethic committee:

126 Sendai Dajie, Changchun City, Jilin Province

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 431 84995047

伦理委员会联系人邮箱:

Contact email of the ethic committee:

jdsyky2021@163.com

研究实施负责(组长)单位:

吉林大学中日联谊医院

Primary sponsor:

China-Japan Union Hospital of Jilin University

研究实施负责(组长)单位地址:

吉林省长春市仙台大街126号

Primary sponsor's address:

126 Sendai Dajie, Changchun City, Jilin 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):

吉林省

市(区县):

Country:

China

Province:

Jilin

City:

单位(医院):

吉林大学中日联谊医院

具体地址:

吉林省长春市仙台大街126号

Institution
hospital:

China-Japan Union Hospital of Jilin University

Address:

126 Sendai Dajie, Changchun City, Jilin Province

经费或物资来源:

吉林省卫生科研人才专项

Source(s) of funding:

Jilin Province Department of Finance

研究疾病:

前循环大血管闭塞引起的急性缺血性脑卒中  

Target disease:

Acute ischemic stroke due to anterior circulation large vessel occlusion

研究疾病代码:

Target disease code:

研究类型:

观察性研究

Study type:

Observational study

研究所处阶段:

其它 

Study phase:

N/A

研究设计:

队列研究 

Study design:

Cohort study 

研究目的:

本研究旨在通过多中心真实世界数据,系统性构建一种能够客观、稳定识别基底节“晕染征”(Basal Ganglia Blush, BGB)的影像组学模型,以克服传统肉眼判读的主观性和一致性不足。通过对再通后 DSA 图像进行高维纹理、强度及空间特征的自动提取与量化,本研究计划将 BGB 从传统的主观影像征象转变为可重复、可比较的影像组学表型。基于此表型,本研究进一步探讨 radiomics-BGB 与术后颅内出血之间的关联性,评估其作为再灌注损伤风险标志物的独立预测价值。同时,本研究将综合临床特征、操作信息及再灌注质量,构建预测术后出血和 90 天功能预后的多因素模型,以明确 radiomics-BGB 在预后评估中的增益效应。此外,通过独立验证队列对模型的外部泛化能力进行评估,确保其在真实临床环境中的可推广性与实用价值。最终,本研究的目标不仅在于建立 BGB 的客观识别方法,还希望为卒中取栓术中提供一种能够实时预警再灌注损伤风险的量化工具,为优化术后管理、降低出血转化风险及改善长期功能预后奠定方法学基础,从而推进影像智能化在卒中介入治疗中的临床转化与应用。  

Objectives of Study:

This study aims to develop a radiomics-based, objective, and robust model for identifying the basal ganglia blush (BGB) sign using multicenter real-world data, thereby overcoming the subjectivity and limited reproducibility of traditional visual assessment. By automatically extracting and quantifying high-dimensional texture, intensity, and spatial features from post-reperfusion DSA images, the study seeks to transform BGB from a subjective angiographic finding into a reproducible and comparable radiomic phenotype. Based on this phenotype, we will further investigate the association between radiomics-defined BGB and postprocedural intracranial hemorrhage, assessing its independent predictive value as a marker of reperfusion-related microvascular injury. In addition, clinical characteristics, procedural variables, and reperfusion metrics will be integrated to construct multivariable models for predicting hemorrhagic complications and 90-day functional outcomes, thereby determining the incremental prognostic value of radiomics-BGB. External validation using an independent cohort will be performed to evaluate the model’s generalizability and real-world applicability. Ultimately, this study seeks not only to establish an objective approach for BGB identification but also to provide a quantitative tool capable of offering real-time intraoperative warnings of reperfusion injury, supporting postoperative management, reducing hemorrhagic risk, and improving long-term outcomes, thus p

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.未能实现成功再通(eTICI <2b)。
2.既往存在明显功能障碍(mRS ≥3 分)。
3.术中 DSA 图像质量不符合分析要求。
4.缺乏术后 CT/MRI 影像无法评估出血结局。
5.缺少 90 天 mRS 随访信息、无法用于功能预后分析。

Exclusion criteria:

1.Patients without successful reperfusion(TICI <2b). 2.Premorbid disability defined as a modified Rankin Scale (mRS) score>=3. 3.Unanalyzable or poor-quality DSA imaging. 4.Absence of postoperative neuroimaging, resulting in unavailable hemorrhagic outcome assessment. 5.Missing 90-day functional outcome data (mRS).

研究实施时间:

Study execute time:

From 2025-12-01 00:00:00 To 2027-05-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-03-01 00:00:00 To 2026-11-30 00:00:00

干预措施:

Interventions:

组别:

基底节晕染征阳性组

样本量:

300

Group:

Basal Ganglia Blush–positive group

Sample size:

干预措施:

干预措施代码:

Intervention:

N/A

Intervention code:

组别:

基底节晕染征阴性组

样本量:

500

Group:

Basal Ganglia Blush–negative group

Sample size:

干预措施:

干预措施代码:

Intervention:

N/A

Intervention code:

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

吉林省 

市(区县):

 

Country:

China

Province:

Jilin

City:

单位(医院):

吉林大学中日联谊医院 

单位级别:

三级甲等 

Institution
hospital:

China-Japan Union Hospital of Jilin 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 Province

City:

单位(医院):

昆明医科大学第二附属医院 

单位级别:

三级甲等 

Institution
hospital:

The Second Affiliated Hospital of Kunming Medical University

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

海南省 

市(区县):

 

Country:

China

Province:

Hainan Province

City:

单位(医院):

琼海市人民医院 

单位级别:

三级甲等 

Institution
hospital:

Qionghai People's Hospital

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

浙江省 

市(区县):

 

Country:

China

Province:

Zhejiang Province

City:

单位(医院):

浙江省人民医院 

单位级别:

三级甲等 

Institution
hospital:

Zhejiang Provincial People's Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

90 天功能预后

指标类型:

次要指标

Outcome:

90-day modified Rankin Scale score

Type:

Secondary indicator

测量时间点:

发病后 90 天

测量方法:

通过门诊随访或电话随访方式评估改良 Rankin 量表(mRS)评分,评分范围为 0–6 分。

Measure time point of outcome:

90 days after stroke onset

Measure method:

Functional outcome is assessed using the modified Rankin Scale (mRS) at 90 days after stroke onset, obtained through outpatient follow-up or standardized telephone interview.

指标中文名:

术后颅内出血

指标类型:

主要指标

Outcome:

Postprocedural intracranial hemorrhage

Type:

Primary indicator

测量时间点:

术后 24–48 小时

测量方法:

基于术后 24–48 小时头颅 CT 或 MRI 进行评估,按照 ECASS 分型标准将颅内出血分为 HI1、HI2、PH1、PH2,并记录是否合并蛛网膜下腔出血或脑室内出血。

Measure time point of outcome:

24–48 hours after endovascular thrombectomy

Measure method:

Intracranial hemorrhage is assessed on non-contrast CT or MRI performed 24–48 hours after EVT and classified according to the ECASS criteria (HI1, HI2, PH1, PH2), with additional documentation of subarachnoid or intraventricular hemorrhage when present.

指标中文名:

症状性颅内出血

指标类型:

次要指标

Outcome:

Symptomatic intracranial hemorrhage

Type:

Secondary indicator

测量时间点:

术后 24–48 小时

测量方法:

按 ECASS II 标准定义,即影像学证实的颅内出血伴随 NIHSS 评分较基线增加 ≥4 分。

Measure time point of outcome:

24–48 hours after endovascular thrombectomy

Measure method:

Symptomatic intracranial hemorrhage is defined according to the ECASS II criteria as intracranial hemorrhage associated with an increase of ≥4 points in the NIHSS score compared with baseline.

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 18 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

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:

本研究所用数据均来源于参与中心既往常规临床诊疗过程中形成的病历和影像资料。各中心按照统一的数据采集表提取患者的人口学特征、临床信息、手术相关变量及结局指标,影像资料以原始 DICOM 格式收集。所有数据在汇总前均进行去标识化处理,并由授权研究人员进行整理和核查。研究数据仅用于本研究相关分析,在安全环境中存储和管理,研究结束后按伦理要求妥善保存或处理。

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

All data used in this study are derived from routine clinical care previously performed at the participating centers. Relevant clinical variables and imaging data are collected using a standardized case report form, with imaging obtained in the original DICOM format. All data are de-identified prior to aggregation and managed by authorized study personnel. Study data are securely stored and used solely for research purposes in accordance with ethical requirements.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

无/No

注册人:

Name of Registration:

 2026-02-09 10:27:45