一种用于小细胞肺癌(SCLC)组织病理学图像分析的人工智能模型研究

注册号:

Registration number:

ChiCTR2600127237 

最近更新日期:

Date of Last Refreshed on:

2026-06-27 16:07:19 

注册时间:

Date of Registration:

2026-06-27 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

一种用于小细胞肺癌(SCLC)组织病理学图像分析的人工智能模型研究

Public title:

An artificial intelligence model for histopathological image analysis of small cell lung cancer (SCLC)

注册题目简写:

English Acronym:

研究课题的正式科学名称:

一种用于小细胞肺癌(SCLC)组织病理学图像分析的人工智能模型研究

Scientific title:

An artificial intelligence model for histopathological image analysis of small cell lung cancer (SCLC)

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:

梁淑梅 

研究负责人:

梁淑梅 

Applicant:

Liang Shumei 

Study leader:

Liang Shumei 

申请注册联系人电话:

Applicant telephone:

+86 20 81045130

研究负责人电话:

Study leader's
telephone:

+86 20 81045130

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:

leungsukmui@163.com

研究负责人电子邮件:

Study leader's E-mail:

leungsukmui@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:

中国广东省广州市越秀区盘福路1号

研究负责人通讯地址:

中国广东省广州市越秀区盘福路1号

Applicant address:

1 Panfu Road, Yuexiu District, Guangzhou, Guangdong,China

Study leader's address:

1 Panfu Road, Yuexiu District, Guangzhou, Guangdong,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:

广州市第一人民医院

Applicant's institution:

Guangzhou First People's Hospital

研究负责人所在单位:

广州市第一人民医院

Affiliation of the Leader:

Guabgzhou First People‘s 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:

K-2026-121-01

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:

广州市第一人民医院伦理委员会

Name of the ethic committee:

Ethics Committee of Guangzhou First People's Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2026-06-10 00:00:00

伦理委员会联系人:

罗裕

Contact Name of the ethic committee:

Luo Yu

伦理委员会联系地址:

中国广东省广州市越秀区盘福路1号

Contact Address of the ethic committee:

1 Panfu Road, Yuexiu District, Guangzhou, Guangdong,China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 10 81045412

伦理委员会联系人邮箱:

Contact email of the ethic committee:

457306297@qq.com

研究实施负责(组长)单位:

广州市第一人民医院

Primary sponsor:

Guabgzhou First People‘s Hospital

研究实施负责(组长)单位地址:

中国广东省广州市越秀区盘福路1号

Primary sponsor's address:

1 Panfu Road, Yuexiu District, Guangzhou, Guangdong,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):

广东

市(区县):

Country:

China

Province:

Guangdong

City:

单位(医院):

广州市第一人民医院

具体地址:

中国广东省广州市越秀区盘福路1号

Institution
hospital:

Guabgzhou First People‘s Hospital

Address:

1 Panfu Road, Yuexiu District, Guangzhou, Guangdong,China

经费或物资来源:

自选课题(自筹)

Source(s) of funding:

Self-selected topic (self-funded)

研究疾病:

小细胞肺癌  

Target disease:

Small cell lung 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:

探索性研究/预试验 

Study phase:

0

研究设计:

诊断性病例对照试验 

Study design:

Diagnostic test: case-control 

研究目的:

本研究旨在开发一个专门分析小细胞肺癌组织病理图像的人工智能模型。核心目标是实现自动化精准辅助病例诊断,包括自动检测肿瘤区域、区分SCLC与其他肺癌类型,并探索预测患者预后及治疗响应的潜力。通过构建可解释的深度学习系统,本研究致力于辅助病理医生提升诊断效率与一致性,挖掘图像中潜在的预后生物标志物,最终为小细胞肺癌的个体化临床诊疗提供智能化工具。  

Objectives of Study:

The aim of this study is to develop an AI model that specifically analyzes the pathological images of small cell lung cancer tissues. The core goal is to achieve automated and accurate auxiliary case diagnosis, including automatic detection of tumor regions, differentiation of SCLC from other lung cancer types, and exploration of the potential to predict patient prognosis and treatment response. By building an interpretable deep learning system, this study aims to assist pathologists in improving the efficiency and consistency of diagnosis, mining the potential prognostic biomarkers in images, and ultimately providing intelligent tools for the individualized clinical diagnosis and treatment of small cell lung cancer.

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.无明确组织学证据的病例;
2.非原发恶性肿瘤病例;
3.其他亚型的肺部恶性肿瘤;
4.诊断为小细胞肺癌但切片病灶部位面积过小(最大病灶部位癌细胞聚集少于4个);

Exclusion criteria:

1.Cases without clear histological evidence;
2.Non-primary malignant tumor cases;
3.Other subtypes of pulmonary malignancy;
4.Small cell lung cancer was diagnosed but the section lesion area was too small (the largest lesion site had less than 4 cancer cells aggregated);

研究实施时间:

Study execute time:

From 2026-02-01 00:00:00 To 2027-02-01 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-07-04 00:00:00 To 2026-07-06 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):

国际规定的小细胞肺癌组织病理学诊断标准。

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):

International histopathological diagnostic criteria for small cell lung cancer.

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):

基于多尺度特征融合与Transformer的医学图像分类方法

Index test:

Medical image classification method based on multi-scale feature fusion and Transformer

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)

通过组织病理学明确诊断为原发小细胞肺癌的病例。

例数:

Sample size:

100

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):

Primary small cell lung cancer was diagnosed by histopathology.

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):

病理诊断为非癌的组织学病理。

例数:

Sample size:

100

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

Histopathological diagnosis was non-cancerous

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

广东 

市(区县):

 

Country:

China

Province:

Guangdong

City:

单位(医院):

广州市第一人民医院 

单位级别:

三甲 

Institution
hospital:

Guabgzhou First People‘s Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

诊断符合率

指标类型:

主要指标

Outcome:

Diagnostic coincidence rate

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

N/A

指标中文名:

模型诊断漏诊率

指标类型:

次要指标

Outcome:

The rate of missed diagnoses in model diagnosis

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:

病理组织切片

组织:

Sample Name:

Pathological sections

Tissue:

人体标本去向

使用后保存  

说明

Fate of sample:

Preservation 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 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:

数据采集:通过数字切片扫描系统,对我院病理科过往诊断为SCLC病例的病理组织切片进行扫描,形成数字切片,以便后续模型验证。 数据管理计划: 数据收集与存储:数据集中需包含经典SCLC亚型及鉴别诊断病例(如类癌、NSCLC)。所有数据采用去标识化编码,存储于加密服务器,建立元数据登记册记录临床病理信息。 数据标准化:统一扫描仪品牌与分辨率,采用H&E染色标准化算法减少批次差异。 数据版本控制:使用Git-LFS或DVC管理不同预处理版本的数据。

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

Data acquisition: Cases previously diagnosed as SCLC in the pathology department of our hospital were scanned by digital slide scanning system to form digital slides for subsequent model validation.Data Management Plan:Data collection and storage: classic SCLC subtypes and differential diagnosis cases (e.g., carcinoid, NSCLC) should be included in the dataset. All data were de-identified and coded, stored in an encrypted server, and a metadata registry was established to record clinicopathological information.Data standardization: scanner brand and resolution were unified, and H&E staining standardization algorithm was used to reduce batch differences.Data versioning: Use Git-LFS or DVC to manage different preprocessed versions of data.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

无/No

注册人:

Name of Registration:

 2026-06-27 08:44:32