ChiCTR2600126937 版本V1.0 版本创建时间2026/06/19 08:03:41 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:

ChiCTR2600126937 

最近更新日期:

Date of Last Refreshed on:

2026-06-19 08:02:17 

注册时间:

Date of Registration:

2026-06-19 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

面向远程医疗的白癜风AI辅助系统:基于临床照片生成伍德灯图像的诊断与随访模型

Public title:

An AI-assisted system for vitiligo in telemedicine: A diagnostic and follow-up model based on generating Wood's lamp images from clinical photos

注册题目简写:

English Acronym:

研究课题的正式科学名称:

面向远程医疗的白癜风AI辅助系统:基于临床照片生成伍德灯图像的诊断与随访模型

Scientific title:

An AI-assisted system for vitiligo in telemedicine: A diagnostic and follow-up model based on generating Wood's lamp images from clinical photos

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:

卞芳 

研究负责人:

卞芳 

Applicant:

Bian Fang 

Study leader:

Bian Fang 

申请注册联系人电话:

Applicant telephone:

+86 18827557314

研究负责人电话:

Study leader's
telephone:

+86 18827557314

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:

379836243@qq.com

研究负责人电子邮件:

Study leader's E-mail:

379836243@qq.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:

湖北省襄阳市襄城区荆州街136号

研究负责人通讯地址:

湖北省襄阳市东津新区楚山路19号

Applicant address:

136 Jingzhou Street, Xiangcheng District, Xiangyang, Hubei

Study leader's address:

19 Chushan Road, Dongjin New District, Xiangzhou District, Xiangyang, Hubei

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:

襄阳市中心医院

Applicant's institution:

Xiangyang Central Hospital

研究负责人所在单位:

襄阳市中心医院

Affiliation of the Leader:

Xiangyang Central 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:

2026-IIT-021

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:

襄阳市中心医院医学伦理委员会

Name of the ethic committee:

Medical Ethics Committee of Xiangyang Central Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2026-03-13 00:00:00

伦理委员会联系人:

王晨玥

Contact Name of the ethic committee:

Wang ChenYue

伦理委员会联系地址:

东津新区楚山路19号

Contact Address of the ethic committee:

19 Chushan Road, Dongjin New District, Xiangzhou District, Xiangyang City, Hubei Province

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 710 3511354

伦理委员会联系人邮箱:

Contact email of the ethic committee:

Lynd0820@outlook.com

研究实施负责(组长)单位:

襄阳市中心医院

Primary sponsor:

Xiangyang Central Hospital

研究实施负责(组长)单位地址:

湖北省襄阳市东津新区楚山路19号

Primary sponsor's address:

19 Chushan Road, Dongjin New District, Xiangzhou District, Xiangyang, Hubei

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

湖北省

市(区县):

Country:

China

Province:

Hubei

City:

单位(医院):

襄阳市中心医院

具体地址:

东津新区楚山路19号

Institution
hospital:

Xiangyang Central Hospital

Address:

19 Chushan Road, Dongjin New District, Xiangzhou District, Xiangyang, Hubei

经费或物资来源:

湖北省中医药管理局;襄阳市市委组织部;襄阳市中心医院

Source(s) of funding:

Hubei Provincial Administration of Traditional Chinese Medicine; The Organization Department of the CPC Xiangyang Municipal Committee; Xiangyang Central Hosiptal

研究疾病:

白癜风  

Target disease:

vitiligo

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:

连续入组 

Study design:

Sequential 

研究目的:

白癜风的病期主要分为进展期和稳定期,而伍德灯检查是确定白癜风临床分级分期的重要方式之一。本项目旨在开发一种基于深度学习的人工智能模型,能够将标准肤色照明下的白癜风皮损照片,转换为模拟伍德灯照射下的对应图像,确保生成图像在皮损边界、荧光强度及分布模式等关键特征上具有高度的医学可靠性与一致性。  

Objectives of Study:

The disease stage of vitiligo is mainly divided into the progressive stage and the stable stage, and Wood’s lamp examination is one of the important methods for determining the clinical grading and staging of vitiligo. This project aims to develop a deep learning?based artificial intelligence model capable of converting vitiligo lesion images taken under standard skin?color illumination into corresponding simulated Wood’s lamp images, ensuring that the generated images have high medical reliability and consistency in key features such as lesion boundaries, fluorescence intensity, and distribution patterns.

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.性别不限,年龄不限; 2.诊断为白癜风; 3.经我院伦理委员会同意;

Inclusion criteria

1. No restrictions on gender or age; 2. Diagnosed with vitiligo; 3. Approved by our hospital's ethics committee.

排除标准:

1.皮损部位有破溃及感染者; 2.色素减退斑、白色糠疹、贫血痣等与白癜风临床表现相似的皮肤病; 3.其他因各种原因中途停止治疗者。

Exclusion criteria:

1. Lesion areas with ulceration or infection; 2. Skin conditions such as hypopigmented patches, pityriasis alba, and nevus anemicis that have similar clinical manifestations to vitiligo; 3. Those who have discontinued treatment prematurely for various reasons.

研究实施时间:

Study execute time:

From 2026-06-26 00:00:00 To 2026-11-01 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-06-26 00:00:00 To 2026-07-03 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):

参照《中国临床皮肤病学》和《白癜风诊疗共识( 2024版) 》

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):

The diagnosis was made based on "Chinese Clinical Dermatology" and "Consensus on the Diagnosis and Treatment of Vitiligo (2024 Edition)"

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):

基于临床照片生成伍德灯图像的诊断与随访模型

Index test:

The diagnostic and follow-up model based on generating Wood's lamp images from clinical photos.

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)

进展期及稳定期白癜风患者

例数:

Sample size:

150

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 advanced-stage and stable-stage vitiligo

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):

色素减退斑、白色糠疹、贫血痣等

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:

Hypopigmented macules, pityriasis alba, nevus anemicus, etc.

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

湖北省 

市(区县):

 

Country:

China

Province:

Hubei

City:

单位(医院):

襄阳市中心医院 

单位级别:

三级甲等 

Institution
hospital:

Xiangyang Central Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

学习感知图像块相似度

指标类型:

主要指标

Outcome:

Learned Perceptual Image Patch Similarity

Type:

Primary indicator

测量时间点:

模型评估阶段

测量方法:

通过计算两者在深层特征空间中的感知距离来量化相似度。

Measure time point of outcome:

Model evaluation stage

Measure method:

Similarity is quantified by computing the perceptual distance between the two in a deep feature space.

指标中文名:

评分系统

指标类型:

次要指标

Outcome:

scoring system

Type:

Secondary indicator

测量时间点:

临床验证阶段

测量方法:

专家将从图像清晰度、荧光特征准确性、伪影情况和临床辅助价值等维度,对生成的图像进行打分

Measure time point of outcome:

Clinical validation stage

Measure method:

Experts will rate the generated images based on dimensions such as image clarity, accuracy of fluorescence features, presence of artifacts, and clinical utility value.

指标中文名:

图灵测试

指标类型:

次要指标

Outcome:

Turing test

Type:

Secondary indicator

测量时间点:

临床验证阶段

测量方法:

将模型生成的虚拟伍德灯照片与真实伍德灯照片随机混合,由专家判断其真伪,以评估生成图像的逼真度。

Measure time point of outcome:

Clinical validation stage

Measure method:

The virtual Wood’s lamp images generated by the model and the real Wood’s lamp images are randomly mixed, and experts are asked to distinguish between them (i.e., judge authenticity) to evaluate the fidelity of the generated images.

指标中文名:

结构相似性指数

指标类型:

主要指标

Outcome:

Structural Similarity Index

Type:

Primary indicator

测量时间点:

模型评估阶段

测量方法:

从亮度、对比度和结构三个维度,综合对比生成的虚拟伍德灯图像与对应的真实伍德灯图像。计算两图之间的均值、方差及协方差的相关性。

Measure time point of outcome:

Model evaluation stage

Measure method:

A comprehensive comparison is made between the generated virtual Wood’s lamp images and the corresponding real Wood’s lamp images in terms of three dimensions: luminance, contrast, and structure. The correlations of the mean, variance, and covariance between the two images are calculated.

指标中文名:

峰值信噪比

指标类型:

主要指标

Outcome:

Peak Signal-to-Noise Ratio

Type:

Primary indicator

测量时间点:

模型评估阶段

测量方法:

利用数学算法计算模型生成的“虚拟伍德灯图像”与对应的“真实伍德灯图像”之间的像素级差异。

Measure time point of outcome:

Model evaluation stage

Measure method:

Mathematical algorithms are used to calculate the pixel?level differences between the virtual Wood’s lamp images generated by the model and the corresponding real Wood’s lamp images.

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 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:

3-5 名不参与模型开发的皮肤科主治及以上医师盲法评估。

Blinding:

The images were blindly evaluated by 3–5 dermatologists at the attending level or above, who were not involved in model development.

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

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

not shared

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:

 2026-06-19 08:02:17