|
审核状态: Project audit state: |
通过审核 Successful |
|
注册号: Registration number: |
ChiCTR2600126031 |
|
最近更新日期: Date of Last Refreshed on: |
2026-06-02 16:44:59 |
|
注册时间: Date of Registration: |
2026-06-02 00:00:00 |
|
注册号状态: |
预注册 |
|
Registration Status: |
Prospective registration |
|
注册题目: |
基于裂隙灯照片的眼部体征智能识别与标准化描述研究 |
|
Public title: |
Automated Detection and Standardized Description of Anterior Eye Signs Using Slit-Lamp Images |
|
注册题目简写: |
|
|
English Acronym: |
|
|
研究课题的正式科学名称: |
基于裂隙灯眼前段照相的眼前段体征结构化识别与标准化描述模型研究 |
|
Scientific title: |
A Study on a Structured Recognition and Standardized Description Model for Anterior Segment Signs Based on Slit-Lamp Anterior Segment Photography |
|
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: |
陈蔚 |
研究负责人: |
陈蔚 |
|
Applicant: |
Wei Chen |
Study leader: |
Wei Chen |
|
申请注册联系人电话: Applicant telephone: |
+86 577 88396800 |
研究负责人电话:
Study leader's |
+86 577 88396800 |
|
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: |
chenweimd@wmu.edu.cn |
研究负责人电子邮件: Study leader's E-mail: |
chenweimd@wmu.edu.cn |
|
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: |
浙江省温州市鹿城区学院西路270号 |
研究负责人通讯地址: |
学院西路270号眼视光医院 |
|
Applicant address: |
270, Xueyuan West Road, Lucheng District, Wenzhou, Zhejiang |
Study leader's address: |
270 West Xueyuan Road, Wenzhou, Zhejiang,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: |
温州医科大学附属眼视光医院 |
||
|
Applicant's institution: |
Eye Hospital, Wenzhou Medical University |
||
|
研究负责人所在单位: |
温州医科大学附属眼视光医院 |
||
|
Affiliation of the Leader: |
Eye Hospital, Wenzhou Medical University |
||
|
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: |
温医大眼视光伦审2026研第143号 |
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: |
温州医科大学附属眼视光医院伦理委员会 |
||
|
Name of the ethic committee: |
Ethics Committee of Eye Hospital of Wenzhou Medical University |
||
|
伦理委员会批准日期: Date of approved by ethic committee: |
2026-05-21 00:00:00 | ||
|
伦理委员会联系人: |
谷佩秋 |
||
|
Contact Name of the ethic committee: |
Gu Peiqiu |
||
|
伦理委员会联系地址: |
学院西路270号眼视光医院 |
||
|
Contact Address of the ethic committee: |
270 West Xueyuan Road, Wenzhou, Zhejiang, China |
||
|
伦理委员会联系人电话: Contact phone of the ethic committee: |
+86 577 88075582 |
伦理委员会联系人邮箱: Contact email of the ethic committee: |
gupeiqiu@126.com |
|
研究实施负责(组长)单位: |
温州医科大学附属眼视光医院 |
||||||||||||||||||||||
|
Primary sponsor: |
Eye Hospital, Wenzhou Medical University |
||||||||||||||||||||||
|
研究实施负责(组长)单位地址: |
浙江省温州市学院西路270号眼视光医院 |
||||||||||||||||||||||
|
Primary sponsor's address: |
270 Xueyuan Road West, Wenzhou, Zhejiang, China |
||||||||||||||||||||||
|
试验主办单位(项目批准或申办者): Secondary sponsor: |
|
||||||||||||||||||||||
|
经费或物资来源: |
自选课题(自筹) |
||||||||||||||||||||||
|
Source(s) of funding: |
Self-selected research (self-funded) |
||||||||||||||||||||||
|
研究疾病: |
眼前段疾病相关影像体征 |
||||||||||||||||||||||
|
Target disease: |
Anterior segment imaging findings and clinical signs in slit-lamp anterior segment photographs |
||||||||||||||||||||||
|
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: |
连续入组 |
||||||||||||||||||||||
|
Study design: |
Sequential |
||||||||||||||||||||||
|
研究目的: |
本研究拟基于既往诊疗过程中形成的裂隙灯眼前段照相图像及相关临床资料,建立眼前段关键体征的结构化标签体系,构建能够识别角膜、结膜、前房等眼前段关键体征概念标签的深度学习模型,并将模型输出转化为标准化、模板化的眼前段照片体征描述。研究将进一步评价模型在不同数据集中的概念识别性能、文本描述质量、关键体征遗漏率、幻觉率、规范性和临床可用性,为眼前段影像辅助解读、临床科研数据治理及后续便携式眼前段照相设备迁移应用提供基础。 |
||||||||||||||||||||||
|
Objectives of Study: |
This study aims to develop and validate a deep learning model for structured recognition and standardized description of anterior segment findings based on retrospective slit-lamp anterior segment photographs and related clinical data. The study will establish a structured label system for key anterior segment signs, train models to identify clinically relevant concept labels, and convert model outputs into standardized template-based descriptions. Model performance will be evaluated in terms of concept recognition, text description quality, consistency with corneal specialists’ annotations, omission rate, hallucination rate, standardization, clinical usability, and generalizability across different time periods, image sources, and imaging devices. |
||||||||||||||||||||||
|
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. 2013年1月1日至2026年5月1日期间,在温州医科大学附属眼视光医院角膜病专科组101或角膜与眼表疾病中心就诊或住院的患者。 2. 既往诊疗过程中至少完成1次裂隙灯眼前段照相或前段照相检查。 3. 可获得与图像对应的基本人口学信息、就诊信息、诊断信息或相关病历文本。 4. 图像中眼前段主要结构可见,具备进行体征识别和标注的基本条件。 |
||||||||||||||||||||||
|
Inclusion criteria |
1.Patients who visited or were hospitalized in the Corneal Disease Specialty Group 101 or the Cornea and Ocular Surface Disease Center of the Eye Hospital of Wenzhou Medical University between January 1, 2013 and May 1, 2026. 2.Patients who underwent at least one slit-lamp anterior segment photography or anterior segment photography examination during previous clinical care. 3.Availability of corresponding demographic information, visit information, diagnostic information, or relevant medical record text. 4.Anterior segment structures are sufficiently visible in the images for sign recognition and annotation. |
||||||||||||||||||||||
|
排除标准: |
1. 图像严重失焦、曝光严重异常,或眼睑、器械等遮挡主要观察区域,无法评价主要眼前段体征。 2. 图像文件损坏、格式无法读取,或无法与患者、眼别、就诊时间等关键信息有效关联。 3. 关键临床记录缺失,导致无法进行必要的数据核验或标签构建。 4. 同一图像重复存储或明显为非研究所需图像。 5. 其他经研究团队质控认为不适合纳入模型训练或评价的数据。 |
||||||||||||||||||||||
|
Exclusion criteria: |
1.Images with severe defocus, markedly abnormal exposure, or major obstruction of the observation area by eyelids, instruments, or other factors, making evaluation of key anterior segment signs impossible. 2.Corrupted or unreadable image files, or images that cannot be effectively linked to key information such as patient identity, laterality, or visit time. 3.Missing key clinical records that prevent necessary data verification or label construction. 4.Duplicate images or images clearly irrelevant to the study purpose. 5.Other data considered unsuitable for model training or evaluation after quality control by the research team. |
||||||||||||||||||||||
|
研究实施时间: Study execute time: |
从 From 2026-05-01 00:00:00至 To 2027-08-01 00:00:00 |
征募观察对象时间: Recruiting time: |
从 From 2026-06-02 00:00:00 至 To 2027-08-01 00:00:00 |
|
干预措施: Interventions: |
|
|
研究实施地点: Countries of recruitment and research settings: |
|
||||||||||||||||||||||||||||
|
测量指标: Outcomes: |
|
|
采集人体标本:
Collecting sample(s)
|
|
|
征募研究对象情况: Recruiting status: |
尚未开始 Not yet recruiting |
年龄范围: Participant age: |
|
||||||
|
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): |
不共享 |
|
The way of sharing IPD”(include metadata and protocol, If use web-based public database, please provide the url): |
Do not share data |
|
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: |
本研究为回顾性观察性研究,不进行前瞻性招募和额外临床干预。伦理审批通过后,由具备数据权限的研究人员按照医院信息管理制度向信息科提出数据提取申请,采集2013年1月1日至2026年5月1日期间符合条件患者的裂隙灯眼前段照相或前段照相图像,以及人口学信息、就诊和诊断信息、门急诊记录、入院记录、出院记录、专科检查和辅助检查等研究所需资料。 数据提取后将进行去标识化处理,去除姓名、身份证号、联系方式、详细住址等直接身份识别信息,并使用研究编号替代个人身份信息。研究数据与患者真实身份信息分库存放。所有数据存储于医院安全服务器或经信息科批准的专用科研服务器,设置访问权限,仅限研究团队授权成员使用。研究过程中将建立数据字典和变量编码规则,规范数据录入、清洗、校验和管理流程;关键变量进行双人核对,并建立数据备份与恢复机制,定期安全备份,防止数据丢失和未经授权访问。 |
|
Data collection and Management (A standard data collection and management system include a CRF and an electronic data capture: |
This is a retrospective observational study without prospective recruitment or additional clinical intervention. After ethics approval, authorized researchers will submit a data extraction request to the hospital information department according to institutional data management regulations. Data to be collected include slit-lamp anterior segment photographs or anterior segment photographs from eligible patients between January 1, 2013 and May 1, 2026, as well as demographic information, visit and diagnostic information, outpatient and emergency records, admission and discharge records, specialist examination records, and ancillary examination results required for this study.All extracted data will be de-identified before analysis. Direct personal identifiers, including name, identification number, contact information, and detailed address, will be removed, and research codes will be used instead of personal identifiers. Research data and identifiable patient information will be stored separately. All study data will be stored on the hospital secure server or a dedicated research server approved by the information department, with access restricted to authorized study personnel only. A data dictionary and variable coding rules will be established to standardize data entry, cleaning, verification, and management. Key variables will be checked by two researchers, and regular data backup and recovery procedures will be implemented to prevent data loss and unauthorized access. |
|
数据与安全监察委员会: Data and Safety Monitoring Committee: |
有/Yes |