面向口腔黏膜癌变过程病理分级的光学相干层析显微成像诊断技术算法研究

注册号:

Registration number:

ChiCTR2600121724 

最近更新日期:

Date of Last Refreshed on:

2026-04-02 08:48:02 

注册时间:

Date of Registration:

2026-04-02 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

面向口腔黏膜癌变过程病理分级的光学相干层析显微成像诊断技术算法研究

Public title:

Study on diagnostic algorithm of optical coherence tomography/microscopy for pathological grading of oral mucosa canceration

注册题目简写:

English Acronym:

研究课题的正式科学名称:

面向口腔黏膜癌变过程病理分级的光学相干层析显微成像诊断技术算法研究

Scientific title:

Study on diagnostic algorithm of optical coherence tomography/microscopy for pathological grading of oral mucosa canceration

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:

黄欣 

研究负责人:

黄欣 

Applicant:

Huang Xin 

Study leader:

Huang Xin 

申请注册联系人电话:

Applicant telephone:

+86 10 57099007

研究负责人电话:

Study leader's
telephone:

+86 10 57099309

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:

huangxin@ccmu.edu.cn

研究负责人电子邮件:

Study leader's E-mail:

huangyue874@sohu.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:

中国北京市丰台区樊家村路9号院

研究负责人通讯地址:

中国北京市丰台区樊家村路9号院

Applicant address:

No. 9 Fanjiacun Road, Fengtai District, Beijing, China

Study leader's address:

No. 9 Fanjiacun Road, Fengtai District, Beijing, 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:

首都医科大学附属北京口腔医院

Applicant's institution:

Beijing Stomatological Hospital, Capital Medical University

研究负责人所在单位:

首都医科大学附属北京口腔医院

Affiliation of the Leader:

Beijing Stomatological Hospital , Capital 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:

CMUSH-IRB-KJ-PJ-2026-07

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:

首都医科大学附属北京口腔医院伦理委员会

Name of the ethic committee:

Ethics Committee of Beijing Stomatological Hospital, Capital Medical University

伦理委员会批准日期:

Date of approved by ethic committee:

2026-02-03 00:00:00

伦理委员会联系人:

夏晓钰

Contact Name of the ethic committee:

Xia Xiaoyu

伦理委员会联系地址:

中国北京市丰台区樊家村路9号院

Contact Address of the ethic committee:

No. 9 Fanjiacun Road, Fengtai District, Beijing, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 10 57099307

伦理委员会联系人邮箱:

Contact email of the ethic committee:

18602615270@163.com

研究实施负责(组长)单位:

首都医科大学附属北京口腔医院

Primary sponsor:

Beijing Stomatological Hospital , Capital Medical University

研究实施负责(组长)单位地址:

中国北京市丰台区樊家村路9号院

Primary sponsor's address:

No. 9 Fanjiacun Road, Fengtai 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(区县):

Country:

China

Province:

Beijing

City:

单位(医院):

首都医科大学附属北京口腔医院

具体地址:

中国北京市丰台区樊家村路9号院

Institution
hospital:

Beijing Stomatological Hospital , Capital Medical University

Address:

No. 9 Fanjiacun Road, Fengtai District, Beijing, China

经费或物资来源:

北京市自然科学基金-海淀原始创新联合基金

Source(s) of funding:

Beijing Natural Science Foundation - Haidian Original Innovation Joint Fund

研究疾病:

口腔癌  

Target disease:

Oral 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:

诊断试验诊断准确性 

Study design:

Diagnostic test for accuracy 

研究目的:

(1) 针对不同病理分级阶段的口腔黏膜癌变在OCT/OCM图像上呈现的特征差异细微的挑战,本项目拟开展高质量医学图像数据库构建,并围绕三个核心临床应用场景,深化对OCT/OCM图像在口腔黏膜癌变分级诊断中的应用。 (2) 基于最新的深度学习和机器学习技术,本研究将探讨构建针对口腔黏膜OCT/OCM图像细粒度特征学习模型的一系列关键科学问题,以满足复杂口腔黏膜癌变过程中精准医疗的需求,并力图推动无创口腔黏膜癌变病理分级自动诊断技术的突破。 (3) 将深入探索在类别差异不显著的情形下,细粒度特征学习及分类技术的系统性研究致力于提出一系列创新方法和模型,旨在促进医学图像细粒度分类技术准确性和扩展性方面的进步,有效解决医工交叉学科中存在的人工智能难题,并落实到临床应用中。  

Objectives of Study:

(1) Addressing the challenge of subtle characteristic differences in OCT/OCM images of oral mucosal carcinogenesis at different pathological grading stages, this project intends to construct a high-quality medical image database and further advance the application of OCT/OCM images in the grading diagnosis of oral mucosal carcinogenesis around three core clinical application scenarios. (2) Based on the latest deep learning and machine learning technologies, this study will explore a series of key scientific issues in constructing fine-grained feature learning models for oral mucosal OCT/OCM images to meet the demands of precision medicine in the complex process of oral mucosal carcinogenesis, and strive to drive a breakthrough in the non-invasive automatic diagnostic technology for pathological grading of oral mucosal carcinogenesis. (3) We will conduct an in-depth exploration of systematic research on fine-grained feature learning and classification technologies under the condition of insignificant category differences, commit to proposing a series of innovative methods and models, aim to promote the progress of medical image fine-grained classification technologies

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.伴有严重基础疾病不能耐受手术者。
2.精神疾病或智力障碍患者。
3.复发肿瘤。
4.女性患者在妊娠期或者哺乳期。
5.术前曾于口腔病变黏膜涂抹外用药物者。

Exclusion criteria:

1.Patients with severe underlying diseases who cannot tolerate surgery.
2.Patients with mental illness or intellectual disability.
3.Patients with recurrent tumors.
4.Female patients who are pregnant or lactating.
5.Patients who have applied topical drugs on the oral lesion mucosa before surgery.

研究实施时间:

Study execute time:

From 2024-09-13 00:00:00 To 2027-09-14 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-04-10 00:00:00 To 2027-09-14 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):

病理诊断

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):

Pathological diagnosis

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):

本研究的主要测量指标为基于OCT/OCM图像的自动分级诊断性能,具体通过诊断准确率、敏感度、特异度、F1分数、阳性预测值、阴性预测值以及受试者工作特征曲线下面积等指标进行综合评估,并计算95%置信区间。结局指标则重点关注所构建模型在无创条件下能否实现与病理金标准高度一致的分级结果。

Index test:

The primary outcome measures of this study are the performance of automatic grading diagnosis based on OCT/OCM images. Specifically, it will be comprehensively evaluated using indicators including diagnostic accuracy, sensitivity, specificity, F1-score, positive predictive value (PPV), negative pred

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)

经病理活检证实为口腔癌,拟行口腔癌扩大切除术者。

例数:

Sample size:

56

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 diagnosed with oral cancer confirmed by pathological biopsy, who are scheduled to undergo extended resection of oral cancer

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):

口腔白斑

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:

Oral leukoplakia

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

北京 

市(区县):

 

Country:

China

Province:

Beijing

City:

单位(医院):

首都医科大学附属北京口腔医院 

单位级别:

三级甲等 

Institution
hospital:

Beijing Stomatological Hospital , Capital Medical University

Level of the institution:

Tertiary A

测量指标:

Outcomes:

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:

病理诊断结束后

测量方法:

经病理诊断边界无癌细胞的病例中,OCT/OCM诊断为阴性所占的比例

Measure time point of outcome:

After the end of pathological diagnosis

Measure method:

SPE = d /(b+d)

指标中文名:

准确率

指标类型:

主要指标

Outcome:

Diagnostic Accuracy

Type:

Primary indicator

测量时间点:

病理诊断结束后

测量方法:

OCT/OCM 诊断的真阳性与真阴性占总例数的比例

Measure time point of outcome:

After the end of pathological diagnosis

Measure method:

ACC =(a+d)/(a+b+c+d)

指标中文名:

阳性预测值

指标类型:

次要指标

Outcome:

Positive Predictive Value (PPV)

Type:

Secondary indicator

测量时间点:

病理诊断结束后

测量方法:

OCT/OCM诊断边界有癌细胞的病例中确实癌变的比例

Measure time point of outcome:

After the end of pathological diagnosis

Measure method:

PV = a /(a+b)

指标中文名:

阴性预测值

指标类型:

次要指标

Outcome:

Negative Predictive Value (NPV)

Type:

Secondary indicator

测量时间点:

病理诊断结束后

测量方法:

OCT/OCM诊断边界无癌细胞的病例中,确实没有癌变的例数所占的比例

Measure time point of outcome:

After the end of pathological diagnosis

Measure method:

PV = d /(c+d)

指标中文名:

敏感度

指标类型:

主要指标

Outcome:

Sensitivity (Sn)

Type:

Primary indicator

测量时间点:

病理诊断结束后

测量方法:

经病理诊断边界有癌组织的病例中,OCT/OCM诊断阳性者所占的比例

Measure time point of outcome:

After the end of pathological diagnosis

Measure method:

SEN = a /( a+c)

采集人体标本:

Collecting sample(s)
from participants:

标本中文名:

组织

组织:

Sample Name:

Tissue

Tissue:

人体标本去向

使用后销毁  

说明

Fate of sample:

Destruction after use  

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):

N/A

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:

本试验设有病例报告表,病例报告表内容与试验方案一致。临床采集数据将及时、真实、准确、完整的记录在病例报告表内。如有电子数据,需对电子数据记录方法及管理进行描述。主要研究者对数据的真实、完整、准确性负责。数据保存时限至本课题结题后。

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

A Case Report Form (CRF) is designed for this study, and its content is consistent with the study protocol. Clinically collected data will be recorded in the CRF in a timely, truthful, accurate, and complete manner. If electronic data are involved, the methods for electronic data recording and management shall be described. The principal investigator (PI) is responsible for the truthfulness, completeness, and accuracy of the data. The data retention period shall last until the completion of the research project.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

无/No

注册人:

Name of Registration:

 2026-04-02 08:47:54