ChiCTR2600126503 版本V1.0 版本创建时间2026/06/10 09:38:58 中国临床试验注册中心

审核状态:

Project audit state:

通过审核

Successful

注册号:

Registration number:

ChiCTR2600126503 

最近更新日期:

Date of Last Refreshed on:

2026-06-10 09:38:52 

注册时间:

Date of Registration:

2026-06-10 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于喉镜图像的人工智能喉癌辅助诊断系统研究

Public title:

Artificial intelligence-assisted diagnosis of laryngeal cancer using laryngoscopic images

注册题目简写:

M-Larynx-AI

English Acronym:

M-Larynx-AI

研究课题的正式科学名称:

基于多模态喉镜图像深度学习的喉癌辅助诊断系统研究

Scientific title:

Deep Learning-Based System for Auxiliary Diagnosis of Laryngeal Cancer Using Multimodal Laryngoscopic Images

研究课题代号(代码):

Study subject ID:

LC2024A04

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:

倪晓光 

研究负责人:

倪晓光 

Applicant:

Xiaoguang Ni 

Study leader:

Xiaoguang Ni 

申请注册联系人电话:

Applicant telephone:

+86 10 8778 7606

研究负责人电话:

Study leader's
telephone:

+86 10 8778 7606

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:

nixiaoguang@126.com

研究负责人电子邮件:

Study leader's E-mail:

nixiaoguang@126.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:

北京市朝阳区潘家园南里17号,中国医学科学院肿瘤医院内镜科

研究负责人通讯地址:

北京市朝阳区潘家园南里17号,中国医学科学院肿瘤医院内镜科

Applicant address:

Department of Endoscopy, Cancer Hospital, Chinese Academy of Medical Sciences, 17 Panjiayuan Nanli, Chaoyang District, Beijing, China

Study leader's address:

Department of Endoscopy, Cancer Hospital, Chinese Academy of Medical Sciences, 17 Panjiayuan Nanli, Chaoyang District, Beijing, China

申请注册联系人邮政编码:

Applicant postcode:

100021

研究负责人邮政编码:

Study leader's postcode:

100021

申请人所在单位:

中国医学科学院肿瘤医院

Applicant's institution:

Cancer Hospital, Chinese Academy of Medical Sciences

研究负责人所在单位:

中国医学科学院肿瘤医院

Affiliation of the Leader:

Cancer Hospital, Chinese Academy of Medical Sciences

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:

25/576-5522

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:

国家癌症中心/中国医学科学院北京协和医学院肿瘤医院伦理委员会

Name of the ethic committee:

Ethics Committee of National Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College

伦理委员会批准日期:

Date of approved by ethic committee:

2025-10-23 00:00:00

伦理委员会联系人:

薛奇

Contact Name of the ethic committee:

Qi Xue

伦理委员会联系地址:

北京市朝阳区潘家园南里17号,中国医学科学院肿瘤医院伦理委员会

Contact Address of the ethic committee:

The Ethics Committee, Cancer Hospital, Chinese Academy of Medical Sciences, 17 Panjiayuan Nanli, Chaoyang District, Beijing, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 10 8778 8495

伦理委员会联系人邮箱:

Contact email of the ethic committee:

cancergcp@163.com

研究实施负责(组长)单位:

中国医学科学院肿瘤医院

Primary sponsor:

Cancer Hospital, Chinese Academy of Medical Sciences

研究实施负责(组长)单位地址:

北京市朝阳区潘家园南里17号

Primary sponsor's address:

17 Panjiayuan Nanli, Chaoyang District, Beijing, 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):

北京市

市(区县):

Country:

China

Province:

Beijing

City:

单位(医院):

中国医学科学院肿瘤医院

具体地址:

北京市朝阳区潘家园南里17号

Institution
hospital:

Cancer Hospital, Chinese Academy of Medical Sciences

Address:

17 Panjiayuan Nanli, Chaoyang District, Beijing, China

经费或物资来源:

中国医学科学院肿瘤医院院内临床研究课题,课题编号 LC2024A04

Source(s) of funding:

Institutional clinical research project of Cancer Hospital, Chinese Academy of Medical Sciences, project No. LC2024A04.

研究疾病:

喉癌  

Target disease:

Laryngeal cancer

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:

析因分组(即根据危险因素或暴露因素分组) 

Study design:

Factorial 

研究目的:

本研究拟基于白光内镜(WLI)和窄带成像(NBI)喉镜图像,构建并验证多模态深度学习喉癌辅助诊断模型。研究以病理诊断为参考标准,比较多模态模型与单模态模型及不同年资医生在喉癌识别中的诊断性能,评价模型在喉癌早期诊断、良恶性病变鉴别和临床辅助决策中的应用价值。  

Objectives of Study:

This study aims to develop and validate a multimodal deep learning system for the auxiliary diagnosis of laryngeal cancer using white-light imaging and narrow-band imaging laryngoscopic images. Pathological diagnosis will be used as the reference standard. The diagnostic performance of the multimodal model will be compared with unimodal models and with physicians of different experience levels to evaluate its value in early diagnosis, benign-malignant differentiation, and clinical decision support.

药物成份或治疗方案详述:

 

Description for medicine or protocol of treatment in detail:

 

纳入标准:

1. 接受鼻咽喉镜检查,且鼻咽喉镜检查发现喉部异常表现。 2. 喉部异常病变同时具有白光内镜(WLI)和窄带成像(NBI)两种模式下的观察和拍照资料。 3. 采集图像清晰,能够满足图像分析和模型训练/验证需要。 4. 喉部异常病变具有明确病理诊断结果。

Inclusion criteria

1. Patients who underwent nasopharyngolaryngoscopy and had abnormal laryngeal findings. 2. Laryngeal lesions with both white-light imaging and narrow-band imaging photographs. 3. Images of sufficient quality for image analysis and model development or validation. 4. Laryngeal lesions with definite pathological diagnosis.

排除标准:

关键临床资料缺失,无法确定病例分组或参考标准。

Exclusion criteria:

Missing key clinical information required for group assignment or reference standard definition.

研究实施时间:

Study execute time:

From 2024-11-01 00:00:00 To 2027-10-01 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-06-15 00:00:00 To 2027-09-01 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):

病理学检查结果

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):

Pathology 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):

基于多模态喉镜图像深度学习的喉癌辅助诊断系统

Index test:

Deep Learning-Based System for Auxiliary Diagnosis of Laryngeal Cancer Using Multimodal Laryngoscopic Images

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)

喉部病变或可疑喉部病变患者

例数:

Sample size:

500

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 laryngeal lesions or suspected laryngeal lesions

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):

食管癌或甲状腺疾病患者、反流性食管炎患者

例数:

Sample size:

200

Population with condition difficult to distinguish from the target condition, the normal population in a case-control study design should be avoid:

Patients with esophageal cancer, thyroid disease, or reflux esophagitis

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

北京市 

市(区县):

 

Country:

China

Province:

Beijing

City:

单位(医院):

中国医学科学院肿瘤医院 

单位级别:

三甲 

Institution
hospital:

Cancer Hospital, Chinese Academy of Medical Sciences

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

受试者工作特征曲线下面积(AUC)

指标类型:

主要指标

Outcome:

Area under the 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:

灵敏度

指标类型:

主要指标

Outcome:

sensitivity

Type:

Primary 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:

主要指标

Outcome:

specificity

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

准确度

指标类型:

主要指标

Outcome:

Accuracy

Type:

Primary 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:

None

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 90 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:

公开/Public

盲法:

Blinding:

试验完成后的统计结果(上传文件):

Calculated Results after
the Study Completed(upload file):

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):

不共享个体水平原始数据。研究数据包含患者喉镜图像、病理诊断和临床资料,受伦理审批和患者隐私保护要求限制,不适合公开共享。去标识化后的汇总数据、分析代码或模型评估结果可在合理请求并经伦理委员会及研究单位批准后提供。

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

Individual participant-level raw data will not be publicly shared because the dataset contains laryngoscopic images, pathological diagnoses, and clinical information protected by ethics approval and patient privacy requirements. De-identified aggregate data, analysis code, or model performance results may be made available upon reasonable request after approval by the ethics committee and the study institution.

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:

本研究采用病例报告表(CRF,版本号 1.0,版本日期 2025-9-1)进行数据采集,记录患者基本信息、检查日期、临床诊断、病理诊断、内镜所见、WLI 和 NBI 图像数量、AI 识别结果、医生判断结果及医生经验等信息。研究数据由经过授权的研究人员从既往病历系统和内镜图像数据库中提取,进行去标识化和编码管理。电子数据保存在中国医学科学院肿瘤医院受控电脑或服务器中,仅限研究团队成员按权限访问。数据录入后进行一致性核查和质量控制,发现缺失、异常或不一致信息时由研究团队核对原始资料。研究结果以汇总统计形式报告,不包含可识别患者身份的信息。

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

Data will be collected using a case report form (CRF, version 1.0, dated September 1, 2025), including demographic information, examination date, clinical diagnosis, pathological diagnosis, endoscopic findings, numbers of WLI and NBI images, AI outputs, physicians' diagnostic results, and physicians' experience levels. Authorized study personnel will extract data from historical medical records and laryngoscopic image databases. Data will be de-identified and coded. Electronic data will be stored on controlled computers or servers at Cancer Hospital, Chinese Academy of Medical Sciences, with access restricted to authorized research team members. Data consistency and quality checks will be performed after data entry. Missing, abnormal, or inconsistent data will be verified against source records. Study results will be reported only in aggregate form without identifiable patient information.

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:

 2026-06-10 09:38:52