ChiCTR2600125858 版本V1.0 版本创建时间2026/06/01 13:57:20 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:

ChiCTR2600125858 

最近更新日期:

Date of Last Refreshed on:

2026-06-01 13:54:45 

注册时间:

Date of Registration:

2026-06-01 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于具身智能系统的甲状腺超声自动化检查与人工智能图像分析的前瞻性多中心随机交叉研究

Public title:

Prospective multicenter randomized crossover study on automated thyroid ultrasound examination and artificial intelligence image analysis based on embodied intelligence system

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于具身智能系统的甲状腺超声自动化检查与人工智能图像分析的前瞻性多中心随机交叉研究

Scientific title:

Prospective multicenter randomized crossover study on automated thyroid ultrasound examination and artificial intelligence image analysis based on embodied intelligence system

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:

李铭德 

研究负责人:

王伟 

Applicant:

Li MingDe 

Study leader:

Wang Wei 

申请注册联系人电话:

Applicant telephone:

+86 159 9495 3457

研究负责人电话:

Study leader's
telephone:

+86 20 8776 5183

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:

limd36@mail.sysu.edu.cn

研究负责人电子邮件:

Study leader's E-mail:

wangw73@mail.sysu.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:

中国广东省广州市越秀区中山二路58号

研究负责人通讯地址:

中国广东省广州市越秀区中山二路58号

Applicant address:

58 Zhongshan Second Road, Yuexiu District, Guangzhou, Guangdong, China

Study leader's address:

58 Zhongshan Second 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:

中山大学附属第一医院

Applicant's institution:

The First Affiliated Hospital of Sun Yat-Sen University

研究负责人所在单位:

中山大学附属第一医院

Affiliation of the Leader:

The First Affiliated Hospital of Sun Yat-Sen University

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:

伦审临[2026]382 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:

中??学附属第?医院临床科研和实验动物伦理委员会

Name of the ethic committee:

IEC for Clinical Research and Animal Trials of the First Affiliated Hospital of Sun Yat-sen University

伦理委员会批准日期:

Date of approved by ethic committee:

2026-05-27 00:00:00

伦理委员会联系人:

颜楚荣

Contact Name of the ethic committee:

Yan Churong

伦理委员会联系地址:

中国?东省?州市越秀区中??路58号

Contact Address of the ethic committee:

58 Zhongshan Second Road, Yuexiu District, Guangzhou City, Guangdong Province, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 20 8733 4871

伦理委员会联系人邮箱:

Contact email of the ethic committee:

研究实施负责(组长)单位:

中山大学附属第一医院

Primary sponsor:

The First Affiliated Hospital of Sun Yat-Sen University

研究实施负责(组长)单位地址:

广东省广州市越秀区中山二路58号

Primary sponsor's address:

58 Zhongshan Second Road, Yuexiu District, Guangzhou, Guangdong

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):

广州市

Country:

China

Province:

Guangdong

City:

Guangzhou

单位(医院):

中山大学附属第一医院

具体地址:

越秀区中山二路58号

Institution
hospital:

The First Affiliated Hospital of Sun Yat-Sen University

Address:

58 Zhongshan Second Road, Yuexiu District

经费或物资来源:

国家自然科学基金(NO: 82371983)

Source(s) of funding:

National Nature Science Foundation of China (No: 82371983)

研究疾病:

甲状腺病变  

Target disease:

Thyroid lesions

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:

随机交叉对照 

Study design:

Cross-over 

研究目的:

1 主要研究目的 比较IS-MAN系统与低年资超声医师对甲状腺结节高风险人群分类敏感性的差异。 2 次要研究目的 (1)比较IS-MAN系统、高年资医师及低年资医师之间的扫查完整性; (2)比较不同扫查方式获得图像的质量差异; (3)比较不同扫查方式、不同读图方式的甲状腺结节检出率; (4)比较不同扫查方式、不同读图方式的甲状腺高低风险的分类性能; (5)评价人工智能自动生成超声报告的自然语言处理性能; (6)受试者主观评分。  

Objectives of Study:

1. Primary Research Objective Compare the differences in sensitivity between the IS-MAN system and junior radiologists in classifying high-risk thyroid nodule populations. 2. Secondary Research Objectives (1) Compare the scanning completeness among the IS-MAN system, senior radiologists, and junior radiologists; (2) Compare the quality differences of images obtained by different scanning methods; (3) Compare the detection rates of thyroid nodules using different scanning methods and different image interpretation methods; (4) Compare the classification performance of thyroid nodules as high-risk or low-risk using different scanning methods and different image interpretation methods; (5) Evaluate the natural language processing performance of AI-generated ultrasound reports; (6) Subjective scoring by participants.

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.年龄18 岁至80岁; 2.自愿参加临床试验研究。

Inclusion criteria

1. Male and female aged between 18 and 80 years; 2. Volunteer to participate in clinical trial research.

排除标准:

排除标准包括存在颈部开放性创伤或感染、无法配合完成标准扫查(如无法保持平卧或无法执行检查指令)、既往全甲状腺切除史或存在出血等高风险情况。

Exclusion criteria:

Exclusion criteria include open trauma or infection in the neck, inability to cooperate with the standard examination (such as inability to remain in a supine position or inability to follow the examination instructions), a history of total thyroidectomy, or any high-risk conditions such as bleeding.

研究实施时间:

Study execute time:

From 2026-06-01 00:00:00 To 2027-06-01 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-06-01 00:00:00 To 2027-06-01 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):

本研究采用独立盲法参考标准。所有获得的超声图像由2名独立、具备医学认证的高年资超声专家进行独立评估(不参与图像采集及后续的读图诊断过程),评估者对操作者类型及扫查方式均保持盲态。当两名评估者意见不一致时,由第3名独立高年资专家进行判定,并通过多数一致原则形成最终参考标准。甲状腺结节使用ACR TI-RADS进行分类,其中1-3类定义为低风险,4-5类定义为中高风险。

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):

This study employed an independent blinded reference standard. All acquired ultrasound images were independently evaluated by two senior, board-certified ultrasound experts who were not involved in image acquisition or subsequent interpretation. The evaluators remained blinded to the operator type and scanning technique. In cases of disagreement between the two evaluators, a third independent senior expert made the determination, and the majority opinion was used to establish the final reference standard. Thyroid nodules were classified using the ACR TI-RADS system, with categories 1–3 defined as low risk and categories 4–5 defined as intermediate to high risk.

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):

每位受试者均接受三种不同甲状腺超声扫查方式: 1.高年资医师甲状腺超声扫查; 2.低年资医师甲状腺超声扫查; 3.具身智能超声机器人IS-MAN扫查系统。

Index test:

Each subject underwent three different thyroid ultrasound scanning methods: 1. Thyroid ultrasound scanning by senior physicians; 2. Thyroid ultrasound scanning for junior doctors; 3. Embodied Intelligence Ultrasound Robot IS-MAN Scanning System.

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)

连续纳入接受甲状腺超声检查的人群,包括健康体检人群以及因疑似或已发现甲状腺结节而就诊的门诊患者。

例数:

Sample size:

786

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):

Consecutive individuals undergoing thyroid ultrasound examination were enrolled, including participants from routine health screening programs and outpatients with suspected or previously identified thyroid nodules.

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):

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:

None

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):

广州 

Country:

China

Province:

Guangdong

City:

Guangzhou

单位(医院):

中山大学附属第一医院 

单位级别:

三甲 

Institution
hospital:

The First Affiliated Hospital of Sun Yat-Sen University

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

广东 

市(区县):

佛山 

Country:

China

Province:

Guangdong

City:

Foshan

单位(医院):

佛山市三水区人民医院 

单位级别:

三甲 

Institution
hospital:

Sanshui District People’s Hospital of Foshan

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

广东 

市(区县):

广州 

Country:

China

Province:

Guangdong

City:

Guangzhou

单位(医院):

广东省人民医院 

单位级别:

三甲 

Institution
hospital:

Guangdong Provincial People's Hospital

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

广东 

市(区县):

广州 

Country:

China

Province:

Guangdong

City:

Guangzhou

单位(医院):

中山大学附属第六医院 

单位级别:

三甲 

Institution
hospital:

The Sixth Affiliated Hospital of Sun Yat-Sen University

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

广东 

市(区县):

深圳 

Country:

China

Province:

Guangdong

City:

Shenzhen

单位(医院):

中山大学附属第七医院 

单位级别:

三甲 

Institution
hospital:

The Seventh Affiliated Hospital of Sun Yat-Sen University

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

敏感性

指标类型:

主要指标

Outcome:

Sensitivity

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

扫查完整性

指标类型:

次要指标

Outcome:

Completeness of thyroid scanning

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

图像质量

指标类型:

次要指标

Outcome:

Image quality assessment

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

结节检出率

指标类型:

次要指标

Outcome:

Detection rate

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

特异性

指标类型:

次要指标

Outcome:

specificity

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

准确性

指标类型:

次要指标

Outcome:

accuracy

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

受试者工作特征曲线下面积

指标类型:

次要指标

Outcome:

area under the receiver operating characteristic curve (AUC)

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

受试者主观评分

指标类型:

次要指标

Outcome:

Subjective score by participants

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

阳性预测值

指标类型:

次要指标

Outcome:

Positive predictive value

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

阴性预测值

指标类型:

次要指标

Outcome:

Negative predictive value

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

自然语言处理评价指标

指标类型:

次要指标

Outcome:

Natural language processing evaluation metrics

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:

组织:

Sample Name:

None

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 years
最大 Max age 80 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):

每位参与者将接受三次超声检查:一次由 IS-MAN 系统进行,一次由资深放射科医生进行,一次由初级放射科医生进行。这三次检查的顺序将在六种可能的检查顺序中随机确定。为确保各检查顺序的均衡性,将采用以 6 为单位的区组随机化方法。分配情况将通过中央随机化系统进行保密处理。 上述所有随机序列均由专业统计师通过计算机算法生成。

Randomization Procedure (please state who generates the random number sequence and by what method):

Each participant will undergo three ultrasound examinations: one performed by the IS-MAN system, one by a senior radiologist, and one by a junior radiologist. The order of the three examinations will be randomized among the six possible examination sequences. To ensure balance across examination sequences, block randomization with a block size of 6 will be used. Allocation will be concealed through a central randomization system. All of the above-mentioned random sequences were generated by professional statisticians using computer algorithms.

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:

1. 图像评估盲法:所有超声图像均进行去标识化处理,阅片者对受试者临床信息、操作者身份、扫查方式及数据顺序均保持盲态。 2. 操作者隔离盲法:各操作者之间实行物理隔离,在某一组进行扫查时,其余组别无法观察检查过程及图像结果,以避免学习效应及信息泄露。 3. 参考标准盲法:参考标准由独立专家组建立,专家不参与图像采集及后续统计分析过程,且独立专家组对扫查来源、扫查顺序保持盲态。 4. 随机分配隐藏:随机序列由独立统计学人员采用计算机生成并单独保管。研究实施人员及操作者在受试者纳入前均无法获知随机分配结果。随机信息仅在检查实施前由指定协调员按顺序告知相关操作者。 通过随机化、交叉对照及盲法设计,本研究旨在最大程度降低选择偏倚、信息偏倚及观察者偏倚,提高研究结果的真实性与可靠性。

Blinding:

1. Image assessment blind method: All ultrasound images are anonymized. The readers remain blinded to the clinical information of the subjects, the identity of the operators, the scanning methods, and the sequence of the data. 2. Operator isolation blind method: Physical isolation is implemented among different operators. When one group is performing scanning, the other groups cannot observe the examination process and image results, in order to avoid learning effects and information leakage. 3. Reference standard blind method: The reference standard is established by an independent expert panel. The experts do not participate in the image collection and subsequent statistical analysis process, and the independent expert panel remains blinded to the source of the scans and the scanning sequence. 4. Random allocation concealment: The random sequence is generated by independent statisticians using a computer and kept separately. The research implementers and operators cannot know the random allocation results before the subjects are included. The random information is only informed to the relevant operators in sequence by the designated coordinator before the examination is implemented. Through randomization, cross-comparison, and blind method design, this study aims to minimize selection bias, information bias, and observer bias, and improve the authenticity and reliability of the research results.

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):

支持本研究结论的数据可由相关作者根据要求提供。个体患者的详细数据和原始临床记录不向公众公开,以保护患者隐私。要获取这些数据需要获得机构数据管理委员会的批准,并需遵守机构和伦理准则。感兴趣的研究人员可以向相关作者提出请求。请求将根据具体情况逐一评估,批准将需要一份正式的数据转移协议,确保数据仅用于学术目的,并严格遵守保密协议。所有共享数据都将进行去识别处理。

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

The data that support the findings of this study are available from the corresponding authors upon request. Individual-level patient data and raw clinical records are not publicly available to protect patient privacy. Access to these data requires approval from the institutional data management committee and is subject to institutional and ethical guidelines. Interested researchers may submit requests to the corresponding author. Requests will be evaluated on a case-by-case basis, and approval will require a formal data transfer agreement ensuring that the data will be used solely for academic purposes, with strict adherence to confidentiality protocols. All shared data will be de-identified.

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:

采用标准病例记录表(CRF)进行数据采集,并录入电子数据管理系统进行统一管理。所有数据均进行去标识化处理,并由专人负责数据核查、清理及质量控制。

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

Data will be collected using standardized Case Report Forms (CRFs) and entered into an electronic database for centralized management. All data will be de-identified and subjected to data verification, cleaning, and quality control procedures.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

暂未确定/Not yet

注册人:

Name of Registration:

 2026-06-01 13:54:45