ChiCTR2500104884 版本V1.1 版本创建时间2025/06/26 11:43:39 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:

ChiCTR2500104884 

最近更新日期:

Date of Last Refreshed on:

2025-06-25 10:02:55 

注册时间:

Date of Registration:

2025-06-25 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于超声影像组学鉴别肾肿瘤亚型:一项多中心研究

Public title:

Differentiating subtypes of renal tumors based on ultrasound radiomics: A multicenter study

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于超声影像组学鉴别肾肿瘤亚型:一项多中心研究

Scientific title:

Differentiating subtypes of renal tumors based on ultrasound radiomics: A multicenter study

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:

吴泳倩 

研究负责人:

石宇 

Applicant:

Wu Yongqian 

Study leader:

Shi Yu 

申请注册联系人电话:

Applicant telephone:

+86 18925284366

研究负责人电话:

Study leader's telephone:

+86 13823578405

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:

549302077@qq.com

研究负责人电子邮件:

Study leader's E-mail:

13823578405@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:

广东省深圳市福田区北京大学深圳医院

研究负责人通讯地址:

深圳市福田区莲花路1120号

Applicant address:

Peking University Shenzhen Hospital, Futian District, Shenzhen, Guangdong Province

Study leader's address:

1120 Lianhua Road, Shenzhen 518036, 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:

北京大学深圳医院

Applicant's institution:

Peking University Shenzhen Hospital

研究负责人所在单位:

北京大学深圳医院

Affiliation of the Leader:

Peking University Shenzhen Hospital

是否获伦理委员会批准:

是/Yes

Approved by ethic committee:

Yes

伦理委员会批件文号:

Approved No. of ethic committee:

北大深医伦审(研)[2025]第(129)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:

北京大学深圳医院科研伦理审查委员会

Name of the ethic committee:

Research Ethics Review Committee of Peking University Shenzhen Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2025-06-06 00:00:00

伦理委员会联系人:

陈嘉怡

Contact Name of the ethic committee:

Chen Jiayi

伦理委员会联系地址:

深圳市福田区莲花路1120号

Contact Address of the ethic committee:

1120 Lianhua Road, Shenzhen 518036, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 755 83923333

伦理委员会联系人邮箱:

Contact email of the ethic committee:

jiayichen25@163.com

研究实施负责(组长)单位:

北京大学深圳医院

Primary sponsor:

Peking University Shenzhen Hospital

研究实施负责(组长)单位地址:

深圳市福田区莲花路1120号

Primary sponsor's address:

1120 Lianhua Road, Shenzhen 518036, 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):

广东省

市(区县):

Country:

China

Province:

Guangdong

City:

单位(医院):

北京大学深圳医院

具体地址:

深圳市福田区莲花路1120号

Institution
hospital:

Peking University Shenzhen Hospital

Address:

1120 Lianhua Road, Shenzhen 518036, China

经费或物资来源:

自选课题(自筹)

Source(s) of funding:

Self selected topic (self funded)

Target disease:

clear cell renal cell carcinoma, papillary renal cell carcinoma and chromophobe renal cell carcinoma.

Target disease code:

研究类型:

观察性研究

Study type:

Observational study

研究所处阶段:

探索性研究/预试验 

Study phase:

0

研究设计:

队列研究 

Study design:

Cohort study 

研究目的:

肾细胞癌现已是全球第 14 大最常见的恶性肿瘤。不同肾细胞癌组织学亚型的结局存在显著差异,与不同的预后相关。在治疗前确定肾细胞癌的亚型,有助于制定治疗方案。本研究旨在建立一种新的语义分割模型,准确分割肿瘤区域并鉴别肾肿瘤的亚型,我们引入一种新的解码器架构,该架构集成了频率自适应扩展卷积等技术,显著增强模型识别和提取关键特征能力,从而提高分割与鉴别性能。  

Objectives of Study:

Renal cell carcinoma is now the 14th most common type of malignant tumor worldwide. There are significant differences in the outcomes of different histological subtypes of renal cell carcinoma, which are associated with different prognoses. Determining the subtype of renal cell carcinoma before treatment is helpful for formulating treatment plans. This study aims to establish a new semantic segmentation model to accurately segment the tumor area and distinguish the subtypes of renal tumors. We introduce a new decoder architecture that integrates technologies such as frequency-adaptive expansion convolution, significantly enhancing the model's ability to recognize and extract key features, thereby improving the segmentation and identification performance.

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.年龄在18岁以上;
2.在超声灰度模式下可以得到相同肾肿瘤的横向和纵向平面;
3.有术后病理结果(手术标本或细针穿刺);

Inclusion criteria

1. Age over 18 years old. 2. In the ultrasound grayscale mode, the transverse and longitudinal planes of the same renal tumor can be obtained. 3. There are postoperative pathological results (surgical specimens or fine-needle aspiration).

排除标准:

1.由于超声图像中的测量卡尺或其他标记物影响了肿瘤的识别;
2.因其他原因导致图像质量不合格的;

Exclusion criteria:

1. Because the measuring calipers or other markers in the ultrasound images interfered with the identification of the tumor; 2. Due to other reasons, the image quality was not up to standard.

研究实施时间:

Study execute time:

From 2025-06-30 00:00:00 To 2026-05-01 00:00:00  

征募观察对象时间:

Recruiting time:

From 2025-06-30 00:00:00 To 2026-05-01 00:00:00  

干预措施:

Interventions:

组别:

乳头状肾细胞癌组

样本量:

200

Group:

Papillary renal cell carcinoma group

Sample size:

干预措施:

干预措施代码:

Intervention:

no

Intervention code:

组别:

肾透明细胞癌组

样本量:

600

Group:

Renal clear cell carcinoma group

Sample size:

干预措施:

干预措施代码:

Intervention:

no

Intervention code:

组别:

嫌色肾细胞癌组

样本量:

50

Group:

Chromophobe renal cell carcinoma group

Sample size:

干预措施:

干预措施代码:

Intervention:

no

Intervention code:

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):

北京大学深圳医院 

单位级别:

三级甲等 

Institution
hospital:

Peking University Shenzhen Hospital

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

四川省 

市(区县):

 

Country:

China 

Province:

Sichuan 

City:

 

单位(医院):

首都医科大学附属北京安贞医院南充医院·南充市中心医院 

单位级别:

三级甲等 

Institution
hospital:

Beijing Anzhen Nanchong Hospital of Capital Medical University & Nanchong Central Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

模型准确率

指标类型:

主要指标

Outcome:

accuracy

Type:

Primary indicator

测量时间点:

测量方法:

(TP+TN)/(TP+TN+FP+FN)

Measure time point of outcome:

Measure method:

(TP+TN)/(TP+TN+FP+FN)

指标中文名:

模型加权 F1-score

指标类型:

主要指标

Outcome:

weighted F1-score

Type:

Primary indicator

测量时间点:

测量方法:

2(PrecisionRecall)/(Precision+Recall)

Measure time point of outcome:

Measure method:

2(PrecisionRecall)/(Precision+Recall)

指标中文名:

95% 豪斯多夫距离

指标类型:

次要指标

Outcome:

95% Hausdorff Distance (HD95)

Type:

Secondary indicator

测量时间点:

测量方法:

95th percentile of surface distances

Measure time point of outcome:

Measure method:

95th percentile of surface distances

指标中文名:

模型阳性预测值

指标类型:

主要指标

Outcome:

positive predictive value (PPV)

Type:

Primary indicator

测量时间点:

测量方法:

TP/(TP+FP)

Measure time point of outcome:

Measure method:

TP/(TP+FP)

指标中文名:

模型阴性预测值

指标类型:

主要指标

Outcome:

negative predictive value (NPV)

Type:

Primary indicator

测量时间点:

测量方法:

TN/(TN+FN)

Measure time point of outcome:

Measure method:

TN/(TN+FN)

指标中文名:

模型敏感性/召回率

指标类型:

主要指标

Outcome:

sensitivity/recall

Type:

Primary indicator

测量时间点:

测量方法:

TP/(TP+FN)

Measure time point of outcome:

Measure method:

TP/(TP+FN)

指标中文名:

模型特异性

指标类型:

主要指标

Outcome:

specificity

Type:

Primary indicator

测量时间点:

测量方法:

TN/(TN+FP)

Measure time point of outcome:

Measure method:

TN/(TN+FP)

指标中文名:

平均交并比

指标类型:

次要指标

Outcome:

mean Intersection over Union (mIoU)

Type:

Secondary indicator

测量时间点:

测量方法:

(1/n)Σ(Area of Overlap)/(Area of Union)

Measure time point of outcome:

Measure method:

(1/n)Σ(Area of Overlap)/(Area of Union)

指标中文名:

平均 Dice 系数

指标类型:

次要指标

Outcome:

mean Dice Similarity Coefficient (mDice)

Type:

Secondary indicator

测量时间点:

测量方法:

(2TP)/(2TP+FP+FN)

Measure time point of outcome:

Measure method:

(2TP)/(2TP+FP+FN)

采集人体标本:

Collecting sample(s)
from participants:

标本中文名:

组织:

Sample Name:

NA

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 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):

研究者, python

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

the researcher himself using the random number generation function of python

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:

开放标签,对评估者隐藏分组

Blinding:

Open-label study with blinded-evaluators

是否共享原始数据:

IPD sharing

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):

no

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:

通过医院科室平台收集电子超声图像,并对患者列表分析整理。

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

Collect electronic ultrasound images through the hospital department platform and analyze and organize the patient list.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

有/Yes

注册人:

Name of Registration:

 2025-06-25 10:02:35