辅助结肠镜检查的多模态视觉基础模型的建立和临床应用

注册号:

Registration number:

ChiCTR2600127111 

最近更新日期:

Date of Last Refreshed on:

2026-06-24 17:39:43 

注册时间:

Date of Registration:

2026-06-24 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

辅助结肠镜检查的多模态视觉基础模型的建立和临床应用

Public title:

Establishment and Clinical Application of a Multimodal Visual Foundation Model for Assisted Colonoscopy

注册题目简写:

English Acronym:

研究课题的正式科学名称:

辅助结肠镜检查的多模态视觉基础模型的建立和临床应用

Scientific title:

Establishment and Clinical Application of a Multimodal Visual Foundation Model for Assisted Colonoscopy

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:

杨成 

研究负责人:

杨成 

Applicant:

Yang Cheng 

Study leader:

Cheng Yang 

申请注册联系人电话:

Applicant telephone:

+86 18861878129

研究负责人电话:

Study leader's
telephone:

+86 510 85351121

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:

yangchengds@163.com

研究负责人电子邮件:

Study leader's E-mail:

yangchengds@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:

江苏省无锡市梁溪区清扬路299号

研究负责人通讯地址:

江苏省无锡市梁溪区清扬路299号

Applicant address:

299 Qingyang Road, Liangxi District, Wuxi City, Jiangsu Province

Study leader's address:

299 Qingyang Road, Liangxi District, Wuxi City, Jiangsu 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:

南京医科大学附属无锡人民医院, 南京医科大学无锡医学中心

Applicant's institution:

The Affiliated Wuxi People's Hospital of Nanjing Medical University, Wuxi Medical Center

研究负责人所在单位:

无锡市人民医院

Affiliation of the Leader:

Wuxi people’s 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:

KY26056

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:

无锡市人民医院科研伦理委员会

Name of the ethic committee:

Research Ethics Committee of Wuxi People's Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2026-03-16 00:00:00

伦理委员会联系人:

彭雁

Contact Name of the ethic committee:

Peng Yan

伦理委员会联系地址:

江苏省无锡市梁溪区清扬路299号

Contact Address of the ethic committee:

299 Qingyang Road, Liangxi District, Wuxi City, Jiangsu Province

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 510 85350835

伦理委员会联系人邮箱:

Contact email of the ethic committee:

76489926@qq.com

研究实施负责(组长)单位:

无锡市人民医院

Primary sponsor:

Wuxi people’s Hospital

研究实施负责(组长)单位地址:

江苏省无锡市梁溪区清扬路299号

Primary sponsor's address:

299 Qingyang Road, Liangxi District, Wuxi City, Jiangsu 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):

江苏省

市(区县):

Country:

China

Province:

Jiangsu

City:

单位(医院):

无锡市人民医院

具体地址:

江苏省无锡市梁溪区清扬路299号

Institution
hospital:

Wuxi people’s Hospital

Address:

299 Qingyang Road, Liangxi District, Wuxi City, Jiangsu Province

经费或物资来源:

校级/院级(2024“雁阵人才”后备学科带头人-2024(杨成))

Source(s) of funding:

2024“Yan Zhen Talent”Backup subject leader-2024(Yang Cheng)

研究疾病:

结直肠腺瘤  

Target disease:

Colorectal adenoma

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:

本研究旨在构建一个集成肠道准备质量实时评估、多类别病变检测与分割、消化道出血风险评估及结构化报告生成等四大核心任务的多模态视觉基础模型并进行临床验证,最终推动结肠镜检查向智能化、标准化、系统化方向迈进,为降低结直肠癌发病率与死亡率提供可靠技术支撑。  

Objectives of Study:

This study aims to develop and clinically validate a multimodal visual foundation model that integrates four core tasks: real-time assessment of bowel preparation quality, multi-class lesion detection and segmentation, gastrointestinal bleeding risk evaluation, and structured report generation. The ultimate goal is to advance colonoscopy toward a more intelligent, standardized, and systematic approach, providing reliable technological support for reducing the incidence and mortality of colorectal cancer.

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.结肠镜检查禁忌证的患者;
2.家族息肉病综合征或炎症性肠病患者;
3.结直肠癌或结直肠癌手术史的患者;
4.已知或疑似肠梗阻或穿孔的患者;
5.妊娠或哺乳期患者;
6.无法实现盲肠插管的患者;

Exclusion criteria:

1.Patients with contraindications to colonoscopy;
2.Patients with familial polyposis syndromes or inflammatory bowel disease;
3.Patients with a history of colorectal cancer or colorectal surgery;
4.Patients with known or suspected intestinal obstruction or perforation;
5.Pregnant or lactating patients;
6.Patients in whom cecal intubation cannot be achieved;

研究实施时间:

Study execute time:

From 2026-04-01 00:00:00 To 2027-04-01 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-09-01 00:00:00 To 2026-12-31 00:00:00

干预措施:

Interventions:

组别:

常规检查组

样本量:

222

Group:

Control group

Sample size:

干预措施:

干预措施代码:

Intervention:

None

Intervention code:

组别:

AI辅助组

样本量:

222

Group:

AI-assisted group

Sample size:

干预措施:

干预措施代码:

Intervention:

None

Intervention code:

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

江苏省 

市(区县):

 

Country:

China

Province:

Jiangsu

City:

单位(医院):

无锡市人民医院 

单位级别:

三级甲等 

Institution
hospital:

Wuxi people’s Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

腺瘤检出率

指标类型:

主要指标

Outcome:

Adenoma detection rate,ADR

Type:

Primary indicator

测量时间点:

结肠镜检查全过程

测量方法:

在接受筛查、监测或诊断性结肠镜检查的患者中,经病理学验证发现≥1个常规腺瘤的患者百分比

Measure time point of outcome:

During the complete colonoscopy procedure

Measure method:

The proportion of patients undergoing screening, surveillance, or diagnostic colonoscopy in whom ≥1 conventional adenoma is detected and confirmed by histopathology

指标中文名:

肠道准备质量

指标类型:

主要指标

Outcome:

Boston bowel preparation scale,BBPS

Type:

Primary indicator

测量时间点:

退镜过程中

测量方法:

按照Lai 等编制的BBPS量表进行评估

Measure time point of outcome:

During the withdrawal process

Measure method:

Evaluation was performed according to the BBPS (Boston Bowel Preparation Scale) developed by Lai et al

指标中文名:

退镜时间

指标类型:

主要指标

Outcome:

Withdrawal time,WT

Type:

Primary indicator

测量时间点:

在结肠镜检查过程中,从回盲部开始退至肛门口的实际时间,不包括吸出残余粪水、清理肠腔、对病灶取活检等的时间

测量方法:

秒表计时

Measure time point of outcome:

The actual time from the start of withdrawal from the cecum to reaching the anal verge

Measure method:

Measured by a stopwatch

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 75 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):

试验结束后,预计2027年12月份进行相关论文的投稿,原始数据会上传ResMan(http://www.medresman.org.cn/)或国家生物信息中心 (https://ngdc.cncb.ac.cn/gsub/)等网站

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

Planned manuscript submission is scheduled for December 2027 following trial completion. All raw data will be uploaded to public repositories like ResMan (http://www.medresman.org.cn/) or China's National Genomics Data Center (NGDC, https://ngdc.cncb.ac.cn/gsub/).

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:

患者一般资料由科研人员建立档案进行记录,该档案对外保密,只有研究小组成员有权进行查阅,内镜特征及病理结果通过美迪康内镜临床研究数据管理与报告系统采集,研究过程中由计算机与助手协助记录进镜时间等相关结局指标,后交由研究小组中数据分析者进行统计分析。所有数据均采用去标识化处理,研究团队无法识别个体患者信息,隐私泄露风险极低。研究者将立即为每位受试者生成一个唯一的研究识别码(Study ID),所有包含个人身份标识的信息(如姓名、身份证号、电话号码、住院号等)将被完全删除或替换为该Study ID。

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

General Patient Data: Research personnel created confidential records for general patient data, accessible only to study team members.Endoscopic Characteristics and Pathological Results: These were collected via the Medicon Endoscopic Clinical Research Data Management and Reporting System.Outcome Indicator Recording: Outcome indicators such as insertion time during the study were recorded with the assistance of computer systems and research assistants, and were subsequently handed over to the data analyst within the research team for statistical analysis.Privacy Protection: All data were de-identified. The research team immediately generated a unique Study ID for each participant. All personally identifiable information (such as name, ID number, phone number, hospital admission number, etc.) was completely removed or replaced with this Study ID. Consequently, the research team could not identify individual patient information, resulting in a very low risk of privacy breach.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

有/Yes

注册人:

Name of Registration:

 2026-06-24 17:39:15