深度学习辅助胶囊内镜对小肠溃疡的识别和病因诊断

注册号:

Registration number:

ChiCTR2500095353 

最近更新日期:

Date of Last Refreshed on:

2025-01-06 16:20:06 

注册时间:

Date of Registration:

2025-01-06 00:00:00 

注册号状态:

补注册

Registration Status:

Retrospective registration

注册题目:

深度学习辅助胶囊内镜对小肠溃疡的识别和病因诊断

Public title:

Deep learning assisted capsule endoscopy in the identification and etiological diagnosis of small intestinal ulcers

注册题目简写:

English Acronym:

研究课题的正式科学名称:

深度学习辅助胶囊内镜对小肠溃疡的识别和病因诊断

Scientific title:

Deep learning assisted capsule endoscopy in the identification and etiological diagnosis of small intestinal ulcers

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:

邱春华 

研究负责人:

邱春华 

Applicant:

Qiu Chunhua 

Study leader:

Qiu Chunhua 

申请注册联系人电话:

Applicant telephone:

+86 189 8183 8277

研究负责人电话:

Study leader's
telephone:

+86 189 8183 8277

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:

zyqch730@163.com

研究负责人电子邮件:

Study leader's E-mail:

zyqch730@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:

四川省成都市青羊区锦翠南路2号锦卉苑

研究负责人通讯地址:

四川省成都市青羊区锦翠南路2号锦卉苑

Applicant address:

Jinhui Yuan, 2 Jincui South Road, Qingyang District, Chengdu City, Sichuan Province

Study leader's address:

Jinhui Yuan, 2 Jincui South Road, Qingyang District, Chengdu City, Sichuan Province

申请注册联系人邮政编码:

Applicant postcode:

610072

研究负责人邮政编码:

Study leader's postcode:

610072

申请人所在单位:

四川省医学科学院·四川省人民医院

Applicant's institution:

Sichuan Academy of Medical Sciences.Sichuan Provincial People's Hospital

研究负责人所在单位:

四川省医学科学院·四川省人民医院

Affiliation of the Leader:

Sichuan Academy of Medical Sciences.Sichuan Provincial 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:

伦审(研)2023年第222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:

四川省医学科学院·四川省人民医院医学伦理委员会

Name of the ethic committee:

Medical Ethics Committee, Sichuan Academy of Medical Sciences.Sichuan Provincial People's Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2023-06-09 00:00:00

伦理委员会联系人:

曹柳

Contact Name of the ethic committee:

Cao Liu

伦理委员会联系地址:

四川省成都市青羊区一环路西二段32号

Contact Address of the ethic committee:

32 West Second Section of First Ring Road, Qingyang District, Chengdu City, Sichuan Province, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 28 8739 3318

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:

四川省医学科学院·四川省人民医院

Primary sponsor:

Sichuan Academy of Medical Sciences.Sichuan Provincial People's Hospital

研究实施负责(组长)单位地址:

四川省成都市青羊区一环路西二段32号

Primary sponsor's address:

32 West Second Section of First Ring Road, Qingyang District, Chengdu City, Sichuan Province, 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):

四川省

市(区县):

成都市

Country:

China

Province:

Sichuan Province

City:

Chengdu City

单位(医院):

四川省医学科学院·四川省人民医院

具体地址:

四川省成都市青羊区一环路西二段32号

Institution
hospital:

Sichuan Academy of Medical Sciences.Sichuan Provincial People's Hospital

Address:

32 West Second Section of First Ring Road, Qingyang District, Chengdu City, Sichuan Province, China

经费或物资来源:

四川省科技厅重点研发项目

Source(s) of funding:

Key research and development project of Sichuan Science and Technology Department

研究疾病:

小肠溃疡  

Target disease:

Small bowel ulcers

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:

本项目的目标是针对小肠溃疡病因诊断的困难入手, 针对最常见的病因克罗恩病和肠结核, 应用 VCE 对小肠溃疡进行诊断的过程中, 使用新开发的卷积神经网络技术自动识别和区分胶囊内镜图像中不同类型的溃疡特点, 帮助鉴别小肠疾病。 同时由于医生阅片工作量大,耗时且易疲劳,有一定的漏诊率, 迫切需要计算机辅助诊断系统帮助医生提高诊断效率, 缩短阅片时间, 降低漏诊率这一实际临床需求问题展开研究。 我们将在深入分析当前基于深度学习理论的 VCE 图像识别和分类算法的基础上,研究适用于小肠 VCE 图像的深度神经网络模型结构,以有效提取图谱中的共性规律;开发具有较高敏感性、 特异性和准确性的 VCE 小肠病变辅助诊断系统原型,用于溃疡病变的检测、 鉴别、 病情评估。推动机器学习方法在胶囊内镜诊断临床上的应用。  

Objectives of Study:

The goal of this project is to address the difficulties in the etiological diagnosis of small intestinal ulcer. In the process of using VCE for the diagnosis of small intestinal ulcer, Crohn's disease and intestinal tuberculosis, the newly developed convolutional neural network technology is used to automatically identify and distinguish the characteristics of different types of ulcers in capsule endoscopy images to help identify small intestinal diseases. At the same time, due to the heavy workload of doctors reading films, time-consuming and easy to fatigue, there is a certain rate of missed diagnosis. Computer-aided diagnosis system is urgently needed to help doctors improve diagnosis efficiency, shorten the reading time, and reduce the rate of missed diagnosis. Based on the in-depth analysis of the current VCE image recognition and classification algorithms based on deep learning theory, a deep neural network model structure suitable for small intestine VCE images was studied to effectively extract the common rules in the atlas. To develop a prototype VCE small intestinal lesion auxiliary diagnosis system with high sensitivity, specificity and accuracy for the detection, identification and disease assessment of ulcer lesions. To promote the application of machine learning methods in clinical diagnosis of capsule endoscopy.

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:

排除标准:1)食管狭窄或吞咽障碍者;2)已知或怀疑胃肠道梗阻、狭窄及瘘管;3)体内安装心脏起搏器或其他电子仪器者;4)无手术条件或拒绝接受任何腹部手术者;5)孕妇。

Exclusion criteria:

Exclusion criteria: 1)Patients with esophageal stenosis or dysphagia; 2) Known or suspected gastrointestinal obstruction, stenosis or fistula; 3) Pacemaker or other electronic equipment installed in the body; 4) Patients without surgical conditions or refusing to accept any abdominal surgery; 5) Pregnant women.

研究实施时间:

Study execute time:

From 2023-06-10 00:00:00 To 2024-12-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2023-07-31 00:00:00 To 2024-12-16 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):

1、克罗恩病的诊断基于临床表现、实验室检查、影像学检查、内镜和病理组织学检查综合诊断,同时排除其他原因引起的肠道炎症或损伤。内镜下表现是阿弗他样溃疡、纵行溃疡。 2、肠结核是结核分枝杆菌引起的肠道慢性特异性感染,内镜下溃疡呈环行、半圆、地图样、边缘呈鼠咬状;病理检查发现干酪性肉芽肿、找到抗酸染色阳性杆菌具有确诊价值。

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):

1.The diagnosis of Crohn's disease is based on a combination of clinical findings, laboratory tests, imaging, endoscopy, and histopathology, while excluding intestinal inflammation or damage from other causes. The endoscopic manifestations were Aphthous ulcer and longitudinal ulcer. 2.Intestinal tuberculosis is a chronic specific intestinal infection caused by Mycobacterium tuberculosis. The ulcers under endoscopy are circular, semicircular, geoglyphic and mouse-bite. The pathological examination showed caseous granuloma and the acid-fast staining positive bacilli had diagnostic value.

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):

新型的基于VCE图像的小肠溃疡诊断深度神经网络模型,主要技术参数,分类精确度不低于95%,灵敏度不低于95%。

Index test:

A novel deep neural network model for the diagnosis of small intestinal ulcer based on VCE images has the main technical parameters, the classification accuracy is not less than 95%, and the sensitivity is not less than 95%.

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)

诊断小肠疾病进行胶囊内镜检查的患者

例数:

Sample size:

30

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 undergoing capsule endoscopy for diagnosis of small bowel disease

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):

白塞病,淋巴瘤

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:

Behcet's disease, Lymphoma

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

四川省 

市(区县):

成都市 

Country:

China

Province:

Sichuan Province

City:

Chengdu City

单位(医院):

四川省医学科学院·四川省人民医院 

单位级别:

三甲 

Institution
hospital:

Sichuan Academy of Medical Sciences.Sichuan Provincial People's Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

精确度

指标类型:

主要指标

Outcome:

Accuracy

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

灵敏度

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:

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:

结束

/Completed

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:

公开/Public

盲法:

Blinding:

None

试验完成后的统计结果(上传文件):

Calculated Results after
the Study Completed(upload file):

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):

ResMan(http://www.medresman.org.cn/login.aspx),论文发表后6个月内。

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

ResMan (http://www.medresman.org.cn/login.aspx), within 6 months of publication.

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:

电子采集和管理系统

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

Electronic Data Capture, EDC

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:

 2025-01-06 16:19:56