基于深度学习与拓扑约束的血管内超声视频序列运动校正模型研究

注册号:

Registration number:

ChiCTR2500115210 

最近更新日期:

Date of Last Refreshed on:

2026-01-12 14:40:56 

注册时间:

Date of Registration:

2025-12-23 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于深度学习与拓扑约束的血管内超声视频序列运动校正模型研究

Public title:

Motion Correction in Intravascular Ultrasound Sequences Based on Deep Learning and Topological Constraints

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于深度学习与拓扑约束的血管内超声视频序列运动校正模型研究

Scientific title:

Motion Correction in Intravascular Ultrasound Sequences Based on Deep Learning and Topological Constraints

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:

杨圆 

研究负责人:

杨圆 

Applicant:

Yuan Yang 

Study leader:

Yuan Yang 

申请注册联系人电话:

Applicant telephone:

+86 571 56006035

研究负责人电话:

Study leader's
telephone:

+86 571 56006035

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:

yuanyang9608@163.com

研究负责人电子邮件:

Study leader's E-mail:

yuanyang9608@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:

浙江省杭州市上城区严官巷34号

研究负责人通讯地址:

浙江省杭州市上城区严官巷34号

Applicant address:

34 Yanguan Lane, Shangcheng District, Hangzhou, Zhejiang, China

Study leader's address:

34 Yanguan Lane, Shangcheng District, Hangzhou, Zhejiang, 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:

杭州市肿瘤医院

Applicant's institution:

Hangzhou Cancer Hospital

研究负责人所在单位:

杭州市肿瘤医院

Affiliation of the Leader:

Hangzhou Cancer Hospital

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:

(HZCH-2025)意见第(103)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:

杭州市肿瘤医院医学伦理委员会

Name of the ethic committee:

Clinical Trial Ethics Committee of Hangzhou Cancer Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2025-08-19 00:00:00

伦理委员会联系人:

周利三

Contact Name of the ethic committee:

Zhou Lisan

伦理委员会联系地址:

浙江省杭州市上城区严官巷34号

Contact Address of the ethic committee:

34 Yanguan Lane, Shangcheng District, Hangzhou, Zhejiang, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 571 56006035

伦理委员会联系人邮箱:

Contact email of the ethic committee:

hzchiec2020@163.com

研究实施负责(组长)单位:

杭州市肿瘤医院

Primary sponsor:

Hangzhou Cancer Hospital

研究实施负责(组长)单位地址:

浙江省杭州市上城区严官巷34号

Primary sponsor's address:

34 Yanguan Lane, Shangcheng District, Hangzhou, Zhejiang, 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):

浙江省

市(区县):

Country:

China

Province:

Zhejiang

City:

单位(医院):

杭州市肿瘤医院

具体地址:

浙江省杭州市上城区严官巷34号

Institution
hospital:

Hangzhou Cancer Hospital

Address:

34 Yanguan Lane, Shangcheng District, Hangzhou, Zhejiang, China

经费或物资来源:

浙江省卫生健康行业科技计划

Source(s) of funding:

Zhejiang Provincial Medical and Healthy Science and Technology Projects

研究疾病:

冠心病;动脉粥样硬化  

Target disease:

Coronary Heart Disease; Atherosclerosis

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:

连续入组 

Study design:

Sequential 

研究目的:

设计基于CNN的轻量级架构,直接处理完整IVUS回撤序列,通过时空注意力机制建模血管运动规律,避免传统逐帧校正导致的时间分辨率损失与误差累积;在此基础上,在损失函数的部分显式引入血管解剖先验或结构一致性约束,确保校正后血管壁的拓扑结构完整,解决现有方法导致的形变错位问题;在公开数据集上验证算法对不同探头频率的适应性,验证模型鲁棒性,为后续临床转化提供理论基础。  

Objectives of Study:

Design a lightweight CNN-based architecture to directly process complete IVUS pullback sequences. The model employs spatiotemporal attention mechanisms to capture vascular motion patterns, thereby avoiding the temporal resolution loss and error accumulation caused by traditional frame-by-frame correction methods. On this basis, anatomical priors or structural consistency constraints of vascular topology are explicitly incorporated into the loss function to ensure the integrity of vessel wall topology after correction and to address deformation and misalignment issues in existing methods. The proposed algorithm will be validated on public datasets to assess its adaptability to different probe frequencies and to verify its robustness, providing a theoretical foundation for future clinical translation.

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.图像受损(如存在断帧);
2.数据标注缺失(如无血管结构参考标准);

Exclusion criteria:

1. Image damage (e.g., missing frames); 2. Missing data annotations (e.g., absence of vascular structure reference standards).

研究实施时间:

Study execute time:

From 2026-01-01 00:00:00 To 2028-12-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-01-01 00:00:00 To 2028-12-31 00:00:00

干预措施:

Interventions:

组别:

数据集A

样本量:

22

Group:

Dataset A

Sample size:

干预措施:

干预措施代码:

Intervention:

No intervention.

Intervention code:

组别:

数据集B

样本量:

10

Group:

Dataset B

Sample size:

干预措施:

干预措施代码:

Intervention:

No intervention.

Intervention code:

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

浙江省 

市(区县):

 

Country:

China

Province:

Zhejiang

City:

单位(医院):

杭州市肿瘤医院 

单位级别:

无  

Institution
hospital:

Hangzhou Cancer Hospital

Level of the institution:

N/A

国家:

中国

省(直辖市):

浙江省 

市(区县):

 

Country:

China

Province:

Zhejiang

City:

单位(医院):

杭州市第一人民医院 

单位级别:

三级甲等 

Institution
hospital:

Affiliated Hangzhou First People's Hospital, Zhejiang University School of Medicine

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

频谱泄露

指标类型:

主要指标

Outcome:

Spectral leakage

Type:

Primary indicator

测量时间点:

数据采集时间点

测量方法:

将图像序列对应运动信号转换到频率域,通过计算几个次要的频率幅值与第一主频率的比值得到信噪比值。

Measure time point of outcome:

Data acquisition time.

Measure method:

The motion signals corresponding to the image sequence were transformed into the frequency domain, and the signal-to-noise ratio was calculated by computing the ratios of several minor frequency amplitudes to the primary frequency.

指标中文名:

信噪比

指标类型:

主要指标

Outcome:

Signal-to-noise ratio

Type:

Primary indicator

测量时间点:

数据采集时间点

测量方法:

将图像序列对应运动信号转换到频率域,通过计算几个主要的频率幅值的比值得到频谱泄露值。

Measure time point of outcome:

Data acquisition time.

Measure method:

The motion signals corresponding to the image sequence were transformed into the frequency domain, and the spectral leakage is calculated by computing the ratios of several major frequency amplitudes.

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 0 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

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):

2029年12月于Github网站的个人主页https://github.com/yytangxiaoyuan上公开

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

Publicly released on the personal GitHub page (https://github.com/yytangxiaoyuan) in December 2029.

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:

本研究使用MICCAI 2011 Computing and Visualization for (Intra)Vascular Imaging (CVII) workshop公开的影像数据集。该数据集由主办方在获得原始伦理批准后公开发布,仅用于科研和算法开发用途。数据集已由公开平台进行统一管理和质量控制。研究者下载后在本地服务器进行分析,所有数据仅用于本研究目的,不会对外泄露。

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

This study uses the publicly available imaging dataset from the MICCAI 2011 Computing and Visualization for (Intra)Vascular Imaging (CVII) Workshop. The dataset was released by the organizers after obtaining the necessary ethical approval and is intended solely for research and algorithm development purposes. The dataset has been uniformly managed and quality-controlled by the public platform. Researchers downloaded the data for analysis on a local server, and all data are used exclusively for the purposes of this study without any external disclosure.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

无/No

注册人:

Name of Registration:

 2025-12-23 18:20:32