中国临床试验注册中心 - 世界卫生组织国际临床试验注册平台一级注册机构

注册号： Registration number：	ChiCTR2600130974
最近更新日期： Date of Last Refreshed on：	2026-08-27 09:34:51
注册时间： Date of Registration：	2026-08-27 00:00:00
注册号状态：	预注册
Registration Status：	Prospective registration
注册题目：	基于特征增强与判别学习的口腔黏膜疾病分割与识别模型研究及应用
Public title：	Research and Application of a Segmentation and Recognition Model for Oral Mucosal Diseases Based on Feature Enhancement and Discriminative Learning
注册题目简写：
English Acronym：
研究课题的正式科学名称：	基于特征增强与判别学习的口腔黏膜疾病分割与识别模型研究及应用
Scientific title：	Research and Application of a Segmentation and Recognition Model for Oral Mucosal Diseases Based on Feature Enhancement and Discriminative Learning
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：	沈雪敏	研究负责人：	沈雪敏
Applicant：	Shen Xuemin	Study leader：	Shen Xuemin
申请注册联系人电话： Applicant telephone：	+86 21 23271699	研究负责人电话： Study leader's telephone：	+86 21 23271699
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：	kiyoshen@163.com	研究负责人电子邮件： Study leader's E-mail：	kiyoshen@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：	中国上海市黄浦区瞿溪路500号	研究负责人通讯地址：	中国上海市黄浦区制造局路639号
Applicant address：	500 Quxi Road, Huangpu District, Shanghai,China	Study leader's address：	639 Zhizaoju Road, Huangpu District, Shanghai,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：	上海交通大学医学院附属第九人民医院
Applicant's institution：	Shanghai Ninth Peoples Hospital,Shanghai JiaoTong University School of Medicine
研究负责人所在单位：	上海交通大学医学院附属第九人民医院
Affiliation of the Leader：	Shanghai Ninth Peoples Hospital,Shanghai JiaoTong University School of Medicine

是否获伦理委员会批准：	是
Approved by ethic committee：	Yes
伦理委员会批件文号： Approved No. of ethic committee：	SH9H-2026-T478-2	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：	上海交通大学医学院附属第九人民医院研究者发起的临床研究伦理审查专委会
Name of the ethic committee：	Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine Ethics Committee
伦理委员会批准日期： Date of approved by ethic committee：	2026-08-15 00:00:00
伦理委员会联系人：	甄红
Contact Name of the ethic committee：	Zhen Hong
伦理委员会联系地址：	中国上海市黄浦区制造局路639号
Contact Address of the ethic committee：	639 Zhizaoju Road, Huangpu District, Shanghai,China
伦理委员会联系人电话： Contact phone of the ethic committee：	+86 21 23271699	伦理委员会联系人邮箱： Contact email of the ethic committee：	shjyiec@126.com

研究实施负责（组长）单位：

上海交通大学医学院附属第九人民医院

Primary sponsor：

Shanghai Ninth Peoples Hospital,Shanghai JiaoTong University School of Medicine

研究实施负责（组长）单位地址：

中国上海市黄浦区制造局路639号

Primary sponsor's address：

639 Zhizaoju Road, Huangpu District, Shanghai,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)：	上海	市(区县)：
Country：	China	Province：	Shanghai	City：
单位(医院)：	上海交通大学医学院附属第九人民医院	具体地址：	中国上海市黄浦区制造局路639号
Institution hospital：	Shanghai Ninth Peoples Hospital,Shanghai JiaoTong University School of Medicine	Address：	639 Zhizaoju Road, Huangpu District, Shanghai,China

经费或物资来源：

AI交叉研究专项

Source(s) of funding：

Interdisciplinary AI Research Special Program

研究疾病：

口腔溃疡；口腔扁平苔藓 (OLP)；口腔白斑病 (OLK)。

Target disease：

Oral ulcer; Oral lichen planus (OLP); Oral leukoplakia (OLK)

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：

诊断性病例对照试验

Study design：

Diagnostic test: case-control

研究目的：

本项目旨在攻克口腔黏膜疾病临床诊断中“非显著性目标”精准分割与“高相似性病种”准确识别的双重难题，研发一套兼具高精度、高效率与临床实用性的分割-识别一体化智能解决方案。

Objectives of Study：

This project aims to address the dual challenges of precise segmentation of non-salient targets and accurate identification of highly similar disease categories in the clinical diagnosis of oral mucosal diseases, thereby developing an integrated, intelligent segmentation-and-recognition framework that combines high accuracy, computational efficiency, and clinical utility.

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

Inclusion criteria for patients:
1.Clear pathological or clinical gold-standard diagnoses were established: for oral leukoplakia (OLK), oral lichen planus (OLP), and early-stage malignant transformations, definitive histopathological reports were mandatory; for recurrent aphthous stomatitis (RAS), diagnoses were jointly confirmed by two senior specialists in oral mucosal diseases based on recurrent clinical history and the classic diagnostic hallmarks (i.e., 'yellow pseudomembrane, erythematous border, central depression, and intense pain').
2.Clinical diagnoses fell within the target disease spectrum of this study, specifically including oral ulcers (predominantly recurrent aphthous stomatitis), oral lichen planus (encompassing reticular, plaque-like, and atrophic subtypes, among others), and early oral malignancies or oral leukoplakia (comprising homogeneous, non-homogeneous, and verrucous subtypes, among others). Additionally, a limited number of other definitively diagnosed oral mucosal disorders were included as appropriate to serve as control cohorts or for extended generalization validation.
3.Lesion characteristics were required to align with the core focus of this study, encompassing:  non-salient lesions (early-stage, minuscule, or subtly differentiated from surrounding normal mucosa);  lesions with indistinct/blurred boundaries (where clinical visual inspection challenges clear margin delineation); and typical lesions (exhibiting canonical clinical features and sharp demarcation, serving as benchmarks for model performance evaluation).
4.Patients were required to be aged between 18 and 80 years and capable of cooperating with the oral mucosal imaging procedure.
5.All participants voluntarily enrolled in this study and provided written informed consent prior to data collection.

Criteria for inclusion in the normal control group: 
1.No symptoms or signs of oral mucosal diseases, normal color and shape of the oral mucosa; age, gender, and site of sampling matched those of the case group; and consent to participate was obtained.

排除标准：

1.既往接受过可能改变病灶形态的治疗。
2.因患者不配合、唾液或血迹遮挡、成像模块故障等原因导致采集图像无法满足算法标注或分析的最低要求。
3.因精神障碍、严重张口受限、剧烈疼痛等原因无法完成口腔内图像采集。

Exclusion criteria：

1.Prior treatment history that could potentially alter lesion morphology.
2.Substandard image quality failing to meet the minimum requirements for algorithmic annotation or analysis due to uncooperative patient behavior, visual occlusion by saliva or bloodstains, or hardware/imaging module malfunctions.
3.Inability to undergo or complete intraoral image acquisition due to psychiatric disorders, severe trismus (restricted mouth opening), excruciating pain, or other limiting conditions.

研究实施时间：

Study execute time：

从 From 2025-11-01 00:00:00至 To 2027-10-01 00:00:00

征募观察对象时间：

Recruiting time：

从 From 2026-09-01 00:00:00 至 To 2027-10-01 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）：	对于口腔白斑病、口腔扁平苔藓、早期癌变等疾病，需有组织病理学确诊报告；对于复发性阿弗他溃疡，需由两名口腔黏膜病主任医师根据典型临床表现（“黄、红、凹、痛”）及复发性病史共同诊断。
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):	For conditions such as oral leukoplakia, oral lichen planus, and early-stage cancerous changes, a histopathological diagnosis report is required; for recurrent aphthous ulcers, the diagnosis must be made by two specialists in oral mucosal diseases, based on the typical clinical symptoms (yellowing, redness, depression, and pain) as well as the history of recurrence.
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）：	集“精准病灶分割”与“疾病智能识别”于一体的口腔黏膜病智能诊断系统
Index test:	An intelligent diagnosis system for oral mucosal diseases that combines \"precise lesion segmentation\" with \"intelligent disease recognition\".
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）	患有特定类型口腔黏膜疾病（特别是口腔溃疡、口腔扁平苔藓、口腔白斑病）的患者	例数: Sample size: 160
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 suffering from specific types of oral mucosal diseases (particularly oral ulcers, oral lichen planus, and oral leukoplakia)
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）：	正常对照志愿者	例数: Sample size: 40
Population with condition difficult to distinguish from the target condition, the normal population in a case-control study design should be avoid:	Normal control volunteers

研究实施地点：

Countries of recruitment and research settings：

国家：	中国	省(直辖市)：	上海	市(区县)：
Country：	China	Province：	Shanghai	City：
单位(医院)：	上海交通大学医学院附属第九人民医院	单位级别：	三级甲等
Institution hospital：	Shanghai Ninth Peoples Hospital,Shanghai JiaoTong University School of Medicine	Level of the institution：	Tertiary A

测量指标：

Outcomes：

指标中文名：	Dice系数	指标类型：	主要指标
Outcome：	Dice Similarity Coefficient (DSC)	Type：	Primary indicator
测量时间点：	此研究为诊断性研究，将计算机诊断结果与常规组织病理学结果和临床医生诊断结果比较	测量方法：	组织病理学结果&临床医生诊断结果 vs 计算机诊断结果
Measure time point of outcome：	In this diagnostic study, the computational predictions were benchmarked against both conventional histopathological results and clinical diagnoses.	Measure method：	In this diagnostic study, the computational predictions were benchmarked against both conventional histopathological results and clinical diagnoses.

指标中文名：	平均交并比（mIoU）	指标类型：	主要指标
Outcome：	Mean Intersection over Union (mIoU)	Type：	Primary indicator
测量时间点：	此研究为诊断性研究，将计算机诊断结果与常规组织病理学结果和临床医生诊断结果比较	测量方法：	组织病理学结果&临床医生诊断结果 vs 计算机诊断结果
Measure time point of outcome：	In this diagnostic study, the computational predictions were benchmarked against both conventional histopathological results and clinical diagnoses.	Measure method：	In this diagnostic study, the computational predictions were benchmarked against both conventional histopathological results and clinical diagnoses.

指标中文名：	像素准确率	指标类型：	主要指标
Outcome：	Pixel Accuracy (PA)	Type：	Primary indicator
测量时间点：	此研究为诊断性研究，将计算机诊断结果与常规组织病理学结果和临床医生诊断结果比较，完成全部图像标注后	测量方法：	组织病理学结果&临床医生诊断结果 vs 计算机诊断结果
Measure time point of outcome：	In this diagnostic study, the computational predictions were benchmarked against both conventional histopathological results and clinical diagnoses.	Measure method：	In this diagnostic study, the computational predictions were benchmarked against both conventional histopathological results and clinical diagnoses.

指标中文名：	召回率/敏感度	指标类型：	主要指标
Outcome：	Recall / Sensitivity (REC / SEN)	Type：	Primary indicator
测量时间点：	此研究为诊断性研究，将计算机诊断结果与常规组织病理学结果和临床医生诊断结果比较	测量方法：	组织病理学结果&临床医生诊断结果 vs 计算机诊断结果
Measure time point of outcome：	In this diagnostic study, the computational predictions were benchmarked against both conventional histopathological results and clinical diagnoses.	Measure method：	In this diagnostic study, the computational predictions were benchmarked against both conventional histopathological results and clinical diagnoses.

指标中文名：	精确率	指标类型：	主要指标
Outcome：	Precision	Type：	Primary indicator
测量时间点：		测量方法：
Measure time point of outcome：		Measure method：

指标中文名：	对比优势指标	指标类型：	次要指标
Outcome：	Comparative advantage indicator	Type：	Secondary indicator
测量时间点：		测量方法：
Measure time point of outcome：		Measure method：

指标中文名：	模型轻量化指标	指标类型：	次要指标
Outcome：	Model lightweighting metrics	Type：	Secondary indicator
测量时间点：		测量方法：
Measure time point of outcome：		Measure method：

指标中文名：	临床认可度指标	指标类型：	次要指标
Outcome：	Clinical acceptance metrics	Type：	Secondary indicator
测量时间点：		测量方法：
Measure time point of outcome：		Measure method：

指标中文名：	项目产出指标	指标类型：	次要指标
Outcome：	Project output indicators	Type：	Secondary 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：	无	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	岁 years
最大 Max age	80	岁 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）：

无

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：	无
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）：	不适用
The way of sharing IPD”(include metadata and protocol, If use web-based public database, please provide the url)：	Not applicable
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：	病例记录表
Data collection and Management (A standard data collection and management system include a CRF and an electronic data capture：	Case Record Form
数据与安全监察委员会： Data and Safety Monitoring Committee：	有/Yes
注册人： Name of Registration：	2026-08-27 09:34:41