ChiCTR2600126480 版本V1.0 版本创建时间2026/06/09 17:41:42 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:

ChiCTR2600126480 

最近更新日期:

Date of Last Refreshed on:

2026-06-09 17:40:55 

注册时间:

Date of Registration:

2026-06-09 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

应用影像组学-Transformer融合模型甄别接受阿替利珠单抗联合贝伐珠单抗治疗的晚期肝癌优势人群

Public title:

A Radiomics-Transformer Fusion Model for Identifying Beneficial Subgroups of Advanced Hepatocellular Carcinoma Treated With Atezolizumab Plus Bevacizumab

注册题目简写:

English Acronym:

研究课题的正式科学名称:

应用影像组学-Transformer融合模型甄别接受阿替利珠单抗联合贝伐珠单抗治疗的晚期肝癌优势人群

Scientific title:

A Radiomics-Transformer Fusion Model for Identifying Beneficial Subgroups of Advanced Hepatocellular Carcinoma Treated With Atezolizumab Plus Bevacizumab

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:

肖芦山 

研究负责人:

肖芦山 

Applicant:

lushan Xiao 

Study leader:

lushan xiao 

申请注册联系人电话:

Applicant telephone:

+86 15622178423

研究负责人电话:

Study leader's
telephone:

+86 20 62787310

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:

15622178423@163.com

研究负责人电子邮件:

Study leader's E-mail:

15622178423@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:

广州大道北1838号南方医院肝脏中心

研究负责人通讯地址:

广州大道北1838号

Applicant address:

Guangdong Provincial Key Laboratory for Prevention and Control of Major Liver Diseases

Study leader's address:

1838 North Guangzhou Avenue

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:

南方医科大学南方医院

Applicant's institution:

Nanfang Hospital, Southern Medical University, Guangzhou 510515, China

研究负责人所在单位:

南方医科大学南方医院

Affiliation of the Leader:

Southern Medical University Southern 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:

NFEC-2026-312

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:

南方医科大学南方医院医学伦理委员会

Name of the ethic committee:

Medical Ethics Committee of Nanfang Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2026-04-29 00:00:00

伦理委员会联系人:

胡兴媛

Contact Name of the ethic committee:

Hu XingYuan

伦理委员会联系地址:

广州大道北1838号

Contact Address of the ethic committee:

1838 North Guangzhou Avenue

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 20 62787238

伦理委员会联系人邮箱:

Contact email of the ethic committee:

nfyyec@163.com

研究实施负责(组长)单位:

南方医科大学南方医院

Primary sponsor:

Southern Medical University Southern Hospital

研究实施负责(组长)单位地址:

广州大道北1838号

Primary sponsor's address:

1838 North Guangzhou Avenue

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

广东省

市(区县):

Country:

China

Province:

Guangdong

City:

单位(医院):

南方医科大学南方医院

具体地址:

广州大道北1838号

Institution
hospital:

Southern Medical University Southern Hospital

Address:

1838 North Guangzhou Avenue

经费或物资来源:

临床研究专项

Source(s) of funding:

Nanfang Hospital, Southern Medical University,

研究疾病:

肝细胞癌  

Target disease:

Hepatocellular Carcinoma

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:

构建并验证可识别免疫分型的影像组学和Transformer深度学习融合模型; 联合CT影像特征与临床特征构建并验证可识别免疫分型的多模态模型; 建立基于免疫分型融合模型的晚期肝癌患者T+A联合治疗疗效评分系统,精确评估患者联合治疗疗效,筛选肝癌T+A联合治疗优势人群,为晚期肝癌精准治疗提供理论依据;  

Objectives of Study:

To construct and validate a fusion model integrating radiomics and Transformer deep learning for immune subtype identification;To develop and validate a multimodal model combining CT imaging features and clinical features to identify immune subtypes;To establish a therapeutic efficacy scoring system for T+A combination therapy in patients with advanced hepatocellular carcinoma based on the immune subtype-based fusion model, so as to accurately evaluate treatment response, screen potential beneficiaries of T+A therapy, and provide a theoretical basis for precision treatment of advanced hepatocellular carcinoma.

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.自愿签署知情同意书;
2.年龄>=18岁;
2019年1月至2025年12月期间南方医科大学南方医院接受治疗;
3.根据我国《原发性肝癌诊疗指南,2024年版》原则通过临床和/或病理确诊为肝细胞癌的患者;
4.至少接受一次阿替利珠单抗联合贝伐珠单抗(Atezolizumab plus Bevacizumab,简称“T+A”方案)治疗;
5.免疫治疗前2周内行平扫、肝动脉期、门静脉期、延迟期CT图像扫描;
6.治疗后随访时间至少1年,所有肿瘤进展患者均行影像学检查或者病理学确认;

Inclusion criteria

1.Voluntarily sign an informed consent form.
2.Aged 18 years or older;
3.Received treatment at Nanfang Hospital, Southern Medical University between January 2019 and December 2025.
4.Diagnosed with hepatocellular carcinoma (HCC) clinically and/or pathologically in accordance with the Guidelines for Diagnosis and Treatment of Primary Liver Cancer in China (2024 Edition).
5.Underwent at least one cycle of Atezolizumab plus Bevacizumab (T+A) combination therapy.
6.Non-contrast, hepatic arterial phase, portal venous phase and delayed phase contrast-enhanced CT scans performed within 2 weeks prior to immunotherapy.
7.Minimum follow-up duration of 1 year after treatment; tumor progression was confirmed by imaging examination or pathological diagnosis in all progressive cases.

排除标准:

1.伴发严重的其他器官疾病;
2.病理确诊为肝脏其他类型恶性肿瘤;
3.肿瘤出现自发性破裂出血并且导致腹腔积血(真性破裂);
4.影像图像质量不合格,存在明显伪影、空白等区域;
5.缺乏可测量的靶病灶;

Exclusion criteria:

1.Complicated with severe diseases of other organs.
2.Pathologically confirmed as other types of malignant hepatic tumors.
3.Spontaneous rupture and hemorrhage of tumor with intra-abdominal hematoma (true rupture).
4.Suboptimal quality of imaging data with obvious artifacts, missing areas or blank regions.
5.Absence of measurable target lesions.

研究实施时间:

Study execute time:

From 2026-01-01 00:00:00 To 2028-12-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-06-09 00:00:00 To 2027-12-31 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):

根据我国《原发性肝癌诊疗指南,2024 年版》原则通过临床和/或病 理确诊为肝细胞癌

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):

Diagnosed with hepatocellular carcinoma (HCC) clinically and/or pathologically per the Chinese Guidelines for the Diagnosis and Treatment of Primary Liver Cancer (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):

影像组学和Transformer深度学习融合模型

Index test:

A hybrid model combining imageomics and Transformer deep learning

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)

根据我国《原发性肝癌诊疗指南,2024 年版》原则通过临床和/或病 理确诊为肝细胞癌的患者

例数:

Sample size:

600

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 hepatocellular carcinoma confirmed clinically and/or pathologically in accordance with the principles specified in the Chinese Guidelines for the Diagnosis and Treatment of Primary Liver Cancer (2024 Edition)

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):

肝内胆管癌、混合型肝细胞-胆管癌、肝转移瘤,以及肝血管瘤、局灶性结节性增生、肝腺瘤、肝硬化再生结节/不典型增生结节、炎性假瘤或肝脓肿等影像学表现易与原发性肝癌混淆的肝脏占位性病变患者。

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:

Patients with hepatic space-occupying lesions, such as intrahepatic cholangiocarcinoma, mixed hepatocellular-cholangiocarcinoma, liver metastases, as well as hepatic haemangiomas, focal nodular hyperplasia, hepatic adenomas, regenerative nodules/atypical hyperplastic nodules in cirrhosis, inflammatory pseudotumours or liver abscesses—whose imaging features may be easily confused with those of primary liver cancer.

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

广东省 

市(区县):

 

Country:

China

Province:

Guangdong

City:

单位(医院):

南方医科大学南方医院 

单位级别:

三级甲等 

Institution
hospital:

Southern Medical University Southern Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

深度特征

指标类型:

主要指标

Outcome:

deep features

Type:

Primary indicator

测量时间点:

首次治疗前1月内

测量方法:

采用基于自监督学习的超级标记注意力算法,在大量未标注的数据中训练RestNet、Transformer等特征提取网络,并选取最优的网络架构用于后续多模态模型构建

Measure time point of outcome:

Within 1 month prior to initial treatment

Measure method:

We adopt a super-label attention algorithm based on self-supervised learning to train feature extraction networks including ResNet and Transformer with a large amount of unlabeled data, and select the optimal network architecture for subsequent multimodal model construction.

指标中文名:

免疫分子表达

指标类型:

主要指标

Outcome:

immune molecule expression

Type:

Primary indicator

测量时间点:

收集患者进行治疗前剩余的肝穿刺病理组织切片

测量方法:

对患者肝癌组织行免疫组化检测,探讨CD8、PD-L1、MHCI等免疫分子表达

Measure time point of outcome:

Residual liver biopsy specimens prior to treatment were collected from enrolled patients.

Measure method:

Immunohistochemistry was conducted to detect the expression of CD8, PD-L1 and MHC class I in HCC tissues.

指标中文名:

肝癌影像特征

指标类型:

主要指标

Outcome:

radiomics features

Type:

Primary indicator

测量时间点:

首次治疗前1月内

测量方法:

对收集到的患者的增强CT影像进行预处理,然后进行半自动+人工分割得到ROI图像,基于Python4.0.0安装影像组学特征提取包,批量提取三维影像组学特征

Measure time point of outcome:

Within 1 month prior to initial treatment

Measure method:

The contrast-enhanced CT images of enrolled patients were preprocessed. Subsequently, regions of interest (ROIs) were delineated via semi-automatic segmentation combined with manual correction. Radiomics feature extraction packages were installed based on Python 4.0.0 for batch extraction of three-dimensional radiomics features.

采集人体标本:

Collecting sample(s)
from participants:

标本中文名:

肝穿刺石蜡包埋组织标本

组织:

Sample Name:

Liver biopsy paraffin-embedded tissue specimens

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:

正在进行

Recruiting

年龄范围:

Participant age:

最小 Min age 18 years
最大 Max age 65 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):

NA

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):

本研究选择不共享原始研究数据。研究数据涉及受试者个人隐私与临床敏感信息,严格遵循伦理委员会审批要求与数据保密管理规定,仅限本研究团队内部用于课题相关科研分析,不对外公开共享。

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

This study chooses not to share the original research data. The research data involves the personal privacy and clinically sensitive information of the subjects. We strictly abide by the approval requirements of the ethics committee and the regulations on data confidentiality management. The data is only used for scientific research analysis related to the project within the research team, and will not be publicly shared externally

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:

本研究的数据采集和管理严格遵循临床研究规范,由两部分核心内容组成:一是标准化病例记录表 (Case Record Form, CRF),根据研究方案设计 CRF 表,统一采集受试者的临床、病理、影像、治疗及随访等研究数据,执行双人录入与交叉核查,保障数据准确完整;二是电子数据采集与管理系统 (Electronic Data Capture, EDC),通过 EDC 系统实现数据的电子化录入、存储、溯源与分级权限管理,建立完善的数据质控流程,所有数据加密备份归档,确保数据安全规范。

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

The data collection and management of this study strictly follow the clinical research specifications, which consist of two core parts. The first is the standardized Case Record Form (CRF), which is designed according to the research protocol to uniformly collect the subjects' clinical, pathological, imaging, treatment and follow-up data. Double entry and cross-verification are implemented to ensure the accuracy and integrity of the data. The second is the Electronic Data Capture (EDC) system, which realizes electronic data entry, storage, traceability and hierarchical authority management. A complete data quality control process is established, and all data are encrypted, backed up and archived to ensure data security and standardization.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

有/Yes

注册人:

Name of Registration:

 2026-06-09 17:40:55