ChiCTR2600116028 版本V1.0 版本创建时间2026/01/04 17:58:58 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:

ChiCTR2600116028 

最近更新日期:

Date of Last Refreshed on:

2026-01-04 17:58:53 

注册时间:

Date of Registration:

2026-01-04 00:00:00 

注册号状态:

补注册

Registration Status:

Retrospective registration

注册题目:

人工智能辅助多时序多模态影像与病理图像评估乳腺肿块

Public title:

Artificial intelligence-assisted multi-temporal multimodal imaging and pathology images for the evaluation of breast masses

注册题目简写:

人工智能辅助多时序多模态影像与病理图像评估乳腺肿块

English Acronym:

Artificial intelligence-assisted multi-temporal multimodal imaging and pathology images for the evaluation of breast masses

研究课题的正式科学名称:

人工智能辅助多时序多模态影像与病理图像评估乳腺肿块

Scientific title:

Artificial intelligence-assisted multi-temporal multimodal imaging and pathology images for the evaluation of breast masses

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:

石佳瑶 

研究负责人:

石佳瑶 

Applicant:

Shi Jiayao 

Study leader:

Shi Jiayao 

申请注册联系人电话:

Applicant telephone:

+86 132 6501 1638

研究负责人电话:

Study leader's
telephone:

+86 132 6501 1638

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:

295423432@qq.com

研究负责人电子邮件:

Study leader's E-mail:

295423432@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:

广东省广州市越秀区大德路111号

研究负责人通讯地址:

广东省广州市越秀区大德路111号

Applicant address:

111 Dade Road, Yuexiu District, Guangzhou City, Guangdong Province

Study leader's address:

111 Dade Road, Yuexiu District, Guangzhou City, Guangdong Province

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:

广东省中医院

Applicant's institution:

Guangdong Provincial Hospital of Traditional Chinese Medicine

研究负责人所在单位:

广东省中医院

Affiliation of the Leader:

Guangdong Provincial Hospital of Traditional Chinese Medicine

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:

广东省中医院伦理委员会ZE2023-350-01

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:

广东省中医院伦理委员会

Name of the ethic committee:

Ethics Committee of Guangdong Hospital of Traditional Chinese Medicine

伦理委员会批准日期:

Date of approved by ethic committee:

2023-10-07 00:00:00

伦理委员会联系人:

李晓彦

Contact Name of the ethic committee:

Li Xiaoyan

伦理委员会联系地址:

广东省广州市越秀区大德路111号广东省中医院伦理委员会办公室

Contact Address of the ethic committee:

Ethics Committee Office, Guangdong Hospital of Traditional Chinese Medicine, 111 Dade 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 8188 7233

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:

广东省中医院

Primary sponsor:

Guangdong Provincial Hospital of Traditional Chinese Medicine

研究实施负责(组长)单位地址:

广东省广州市越秀区大德路111号

Primary sponsor's address:

111 Dade Road, Yuexiu District, Guangzhou City, Guangdong Province

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

Country:

China

Province:

Guangdong

City:

Guangzhou

单位(医院):

广东省中医院

具体地址:

广东省广州市越秀区大德路111号

Institution
hospital:

Guangdong Provincial Hospital of Traditional Chinese Medicine

Address:

11 Dade Road, Yuexiu District, Guangzhou City, Guangdong Province

经费或物资来源:

自筹

Source(s) of funding:

self-finance

研究疾病:

乳腺肿瘤  

Target disease:

Breast tumor

研究疾病代码:

N63

Target disease code:

N63

研究类型:

观察性研究

Study type:

Observational study

研究所处阶段:

回顾性研究 

Study phase:

Retrospective study

研究设计:

队列研究 

Study design:

Cohort study 

研究目的:

本研究拟利用人工智能辅助影像及病理多时序多模态图像构建乳腺癌早期诊断及良恶性肿块鉴别、乳腺癌手术前新辅助化疗疗效预测和手术后预后评估的三个模型。 模型一旨在有效鉴别乳腺肿块的性质,提高乳腺肿块的诊断水平,减少误诊率和漏诊率,为患者及时接受治疗提供有效的依据。 模型二旨在新辅助化疗早期或术前预测新辅助化疗疗效的病理完全反应(pCR),1、在早期精准预测pCR,为临床获得药敏信息提供参考依据,从而有助于及时调整治疗方案,实现个性化治疗;2、在手术前准确、安全地识别pCR患者可以调整最佳手术策略,尤其是对腋窝的管理。 模型三旨在准确地预测乳腺癌患者的生存期,对于指导临床医生制定合适的治疗方案及患者的心理康复都有重要意义。 我们将人工智能技术应用到乳腺肿块,研发出乳腺癌早期诊断及良恶性肿块鉴别、乳腺癌新辅助化疗疗效预测和预后评估的智能决策系统,不断进行验证和优化,从而为患者提供个体化的最佳治疗选择,指导治疗决策,从而改善患者结局。  

Objectives of Study:

This study proposes to use artificial intelligence-assisted imaging and pathology multi-temporal multimodal images to construct three models for early diagnosis of breast cancer and identification of benign and malignant masses, prediction of the efficacy of neoadjuvant chemotherapy before breast cancer surgery and prognostic assessment after surgery. Model 1 aims to effectively identify the nature of breast masses, improve the diagnosis of breast masses, reduce the rate of misdiagnosis and underdiagnosis, and provide a valid basis for patients to receive timely treatment. Model II aims to predict the pathological complete response (pCR) to neoadjuvant chemotherapy early or preoperatively. 1. Accurately predicting pCR at an early stage provides a reference basis for clinical access to drug sensitivity information, thus helping to adjust treatment regimens in a timely manner and personalise treatment; 2. Accurately and safely identifying patients with pCR before surgery allows adjustment of the optimal surgical strategy, especially for axillary management. Model 3 aims to accurately predict the survival of breast cancer patients, which is important for guiding clinicians to develop appropriate treatment plans and for patients' psychological recovery. We have applied artificial intelligence technology to breast masses to develop an intelligent decision system for early diagnosis of breast cancer and identification of benign and malignant masses, prediction of neoadjuvant chemotherapy efficacy and prognostic assessment of breast cancer, which is continuously validated and optimised so as to provide patients with individualised and optimal treatment options and guide treatment decisions, thereby improving patient outcomes.

药物成份或治疗方案详述:

 

Description for medicine or protocol of treatment in detail:

 

纳入标准:

模型一:乳腺癌早期诊断及乳腺良恶性肿块鉴别: 纳入标准如下: 1、我院门诊或外院发现乳腺肿块而入院行穿刺或手术切除患者,术前常规行乳腺超声检查 2、超声图像质量好 3、通过穿刺或手术病理活检证实 4、患者年龄18-80岁 模型二:乳腺癌手术前新辅助化疗NAC疗效预测: 纳入标准如下: 1、在NAC治疗前经穿刺活检病理证实单侧原发性乳腺癌,有或无同侧淋巴结转移,且无远处转移; 2、患者接受了完整疗程的NAC,之前无其它癌症或全身化疗史 3、NAC前后行超声检查 4、在NAC完成后一个月内进行手术,有完整的手术后病理结果以评估pCR 5、临床相关资料完整者 6、患者年龄18-80岁 模型三:乳腺癌术后预后评估: 纳入标准如下: 1、手术前NAC乳腺癌患者 2、未行术前新辅助化疗而直接手术患者 3、临床相关资料完整 4、患者年龄大于18岁,小于80岁

Inclusion criteria

Model 1: Early diagnosis of breast cancer and differentiation of benign and malignant breast masses: Inclusion criteria were as follows: 1. Patients admitted for puncture or surgical excision of breast masses found in our outpatient clinic or outside hospital, with routine preoperative breast ultrasound examination 2. Good quality of ultrasound images 3. confirmed by puncture or surgical pathological biopsy 4. age > 18 years, and< 80 years Model 2: Prediction of the efficacy of neoadjuvant chemotherapy NAC before breast cancer surgery: Inclusion criteria were as follows: 1. unilateral primary breast cancer with or without ipsilateral lymph node metastases and no distant metastases confirmed by puncture biopsy pathology prior to NAC treatment; 2. Patients received a full course of NAC with no previous history of other cancers or systemic chemotherapy 3. Ultrasound was performed before and after NAC 4. Surgery performed within one month of NAC completion, with complete post-surgical pathology results to assess pCR 5. Complete clinically relevant information 6. age > 18 years, and< 80 years Model III: Prognostic assessment after breast cancer surgery: Inclusion criteria were as follows: 1. Patients with pre-surgical NAC breast cancer 2. Patients operated directly without preoperative neoadjuvant chemotherapy 3. Complete clinically relevant data 3. age > 18 years, and< 80 years

排除标准:

模型一:乳腺癌早期诊断及乳腺良恶性肿块鉴别纳排标准: 排除标准如下: 1、图像质量差,无法提取特征 3、未取得穿刺活检或手术病理组织学结果 模型二:乳腺癌新辅助化疗NAC疗效预测 排除标准如下: 1、未完成NAC方案或接受非标准治疗的患者(主要指未接受曲妥珠单抗的HER-2阳性患者) 2、图像质量差,无法提取特征 3、缺乏某期超声图像或某期多模态超声图像不完整 4、患者多中心或多灶性癌,在超声图像上的病变与术后病理分析之间的相关性不确定 5、远处转移 模型三:乳腺癌术后预后评估 排除标准: 1、NAC患者未完成NAC方案或接受非标准治疗的患者(主要指未接受曲妥珠单抗的HER-2阳性患者) 2、图像质量差,无法提取特征 3、缺乏某期超声图像或某期多模态超声图像不完整 4、术前远处转移 5、临床相关资料不完整

Exclusion criteria:

Model 1: Early diagnosis of breast cancer and differentiation of benign and malignant breast masses Nullification criteria: The exclusion criteria are as follows: 1. Poor image quality, unable to extract features 3. No puncture biopsy or surgical histology results were obtained Model 2: Prediction of the efficacy of neoadjuvant chemotherapy NAC for breast cancer Exclusion criteria are as follows 1. Patients who did not complete the NAC regimen or received non-standard treatment (mainly HER-2 positive patients who did not receive trastuzumab) 2. Poor image quality and inability to extract features 3, lack of ultrasound images of a particular phase or incomplete multimodality ultrasound images of a particular phase 4Patients with multicentric or multifocal cancer with uncertain correlation between the lesion on the ultrasound image and postoperative pathological analysis 5. distant metastases Model III: Prognostic assessment after breast cancer surgery Exclusion criteria: 1. NAC patients who have not completed the NAC protocol or who are receiving non-standard treatment (mainly HER-2 positive patients who are not receiving trastuzumab) 2. Poor image quality and inability to extract features 3. Lack of ultrasound images of a particular stage or incomplete multimodality ultrasound images of a particular stage 4. Preoperative distant metastases 5. Incomplete clinically relevant information

研究实施时间:

Study execute time:

From 2023-10-07 00:00:00 To 2025-10-07 00:00:00  

征募观察对象时间:

Recruiting time:

From 2023-10-11 00:00:00 To 2025-10-07 00:00:00

干预措施:

Interventions:

组别:

病例组

样本量:

1026

Group:

Case group

Sample size:

干预措施:

干预措施代码:

Intervention:

None

Intervention code:

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):

广东省中医院 

单位级别:

三甲 

Institution
hospital:

Guangdong Provincial Hospital of Traditional Chinese Medicine

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):

南方医科大学珠江医院 

单位级别:

三甲 

Institution
hospital:

Zhujiang Hospital of Southern Medical University

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

多时序多模态超声检查图像

指标类型:

主要指标

Outcome:

Multi-temporal multimodal ultrasound images

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

术前穿刺病理图像

指标类型:

主要指标

Outcome:

Pre-operative puncture pathology images

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

整合超声及病理图像多模态

指标类型:

主要指标

Outcome:

Integration of ultrasound and pathology image multimodality

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

穿刺或手术病理肿块类型

指标类型:

主要指标

Outcome:

Type of puncture or surgical pathology mass

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

新辅助化疗病理完全缓解

指标类型:

主要指标

Outcome:

Complete remission of neoadjuvant chemotherapy pathology

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

无病生存期

指标类型:

主要指标

Outcome:

Disease-free survival

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

原发灶大小

指标类型:

次要指标

Outcome:

Size of primary focus

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

初诊年龄

指标类型:

次要指标

Outcome:

Age at first diagnosis

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

绝经状态

指标类型:

次要指标

Outcome:

Menopausal state

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

激素受体

指标类型:

次要指标

Outcome:

Hormone receptor

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

人表皮生长因子受体-2

指标类型:

次要指标

Outcome:

Human epidermal growth factor receptor-2

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

Ki-67

指标类型:

次要指标

Outcome:

Ki-67

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

分子亚型

指标类型:

次要指标

Outcome:

Molecular subtype

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

组织学分型

指标类型:

次要指标

Outcome:

Histologic typing

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

乳腺癌类型

指标类型:

次要指标

Outcome:

Types of breast cancer

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

新辅助化疗治疗方案

指标类型:

次要指标

Outcome:

Neoadjuvant chemotherapy treatment protocols

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

肿瘤分期

指标类型:

次要指标

Outcome:

Tumor staging

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:

肿块活检病理HE切片

组织:

乳腺

Sample Name:

Pathological HE section of the mass biopsy

Tissue:

Brest

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:

结束

/Completed

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):

采用连续入组的方式选取乳腺肿块或新辅助化疗患者。

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

Patients who underwent ultrasound of breast lumps or neoadjuvant chemotherapy at our hospital were admitted using a consecutive entry group.

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

是Yes

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):

文章公开发表后向ResMan (www.medresman.org.cn)平台共享

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

Article shared with ResMan (www.medresman.org.cn) platform after public release

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:

广东省中医院的数据采集和管理系统

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

Data Collection and Management System for Guangdong Chinese Hospital

数据与安全监察委员会:

Data and Safety Monitoring Committee:

有/Yes

注册人:

Name of Registration:

 2026-01-04 17:58:53