基于卷积神经网络的深度学习迭代重建算法在能谱CT的基础和临床研究

注册号:

Registration number:

ChiCTR2500104183 

最近更新日期:

Date of Last Refreshed on:

2025-06-12 10:13:39 

注册时间:

Date of Registration:

2025-06-12 00:00:00 

注册号状态:

补注册

Registration Status:

Retrospective registration

注册题目:

基于卷积神经网络的深度学习迭代重建算法在能谱CT的基础和临床研究

Public title:

Basic and clinical research of deep learning iterative reconstruction algorithm based on convolutional neural network in energy spectrum CT

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于卷积神经网络的深度学习迭代重建算法在能谱CT的基础和临床研究

Scientific title:

Basic and clinical research of deep learning iterative reconstruction algorithm based on convolutional neural network in energy spectrum CT

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:

丁玮 

研究负责人:

赵永霞 

Applicant:

Ding Wei 

Study leader:

Zhao Yongxia 

申请注册联系人电话:

Applicant telephone:

+86 182 1108 1636

研究负责人电话:

Study leader's
telephone:

+86 151 3122 1591

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:

dingw616@163.com

研究负责人电子邮件:

Study leader's E-mail:

zyx_zyx999@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:

河北省保定市莲池区联盟街道裕华东路342号

研究负责人通讯地址:

河北省保定市莲池区裕华东路212号

Applicant address:

No. 342, Yuhua East Road, Lianchi District, Baoding, Hebei

Study leader's address:

No. 212 Yuhua East Road, Lianchi District, Baoding, Hebei

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:

河北大学附属医院

Applicant's institution:

Affiliated Hospital of Hebei University

研究负责人所在单位:

河北大学附属医院

Affiliation of the Leader:

Affiliated Hospital of Hebei 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:

HDFYLL-KY-2024-029

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:

河北大学附属医院伦理委员会

Name of the ethic committee:

Ethics Committee of Affiliated Hospital of Hebei University

伦理委员会批准日期:

Date of approved by ethic committee:

2024-02-28 00:00:00

伦理委员会联系人:

靳小石

Contact Name of the ethic committee:

Jin Xiaoshi

伦理委员会联系地址:

河北省保定市莲池区裕华东路212号

Contact Address of the ethic committee:

No. 212 Yuhua East Road, Lianchi District, Baoding, Hebei

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 159 3026 0956

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:

河北大学附属医院

Primary sponsor:

Affiliated Hospital of Hebei University

研究实施负责(组长)单位地址:

河北省保定市莲池区裕华东路212号

Primary sponsor's address:

212 Yuhua East Road, Lianchi District, Baoding, Hebei

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

河北

市(区县):

Country:

China

Province:

Hebei

City:

单位(医院):

河北大学附属医院

具体地址:

河北省保定市莲池区裕华东路212号

Institution
hospital:

Affiliated Hospital of Hebei University

Address:

212 Yuhua East Road, Lianchi District, Baoding, Hebei

经费或物资来源:

1、保定市科技计划项目 (2141ZF307)2、河北省2020年度医学科学研究课题计划项目 (20200572)3、河北省医学适用技术跟踪项目 (GZ2023093)4、河北大学附属医院重点科研基金项目( 2024ZB01)

Source(s) of funding:

1, Baoding Science and Technology Plan Project ( 2141ZF307) 2, Hebei Province 2020 Annual Medical Science Research Project Project (20200572) 3, Hebei Province Medical Technology Tracking project (GZ2023093) 4, Hebei University Affiliated Hospital Key Research Fund project (2024ZB01)

研究疾病:

肺癌  

Target disease:

Lung cancer

研究疾病代码:

Target disease code:

研究类型:

干预性研究

Study type:

Interventional study

研究所处阶段:

其它 

Study phase:

N/A

研究设计:

随机平行对照 

Study design:

Parallel 

研究目的:

本研究的目的是探讨深度学习迭代重建算法以及人工智能迭代重建算法对不同BMI病人进行能谱CT增强检查时的作用,期望优选出适合中国人体质的最佳扫描模式、扫描参数、最佳权重迭代重建算法及最低浓度对比剂。  

Objectives of Study:

The aim of this study is to investigate the performance of deep learning iterative reconstruction algorithm and artificial intelligence iterative reconstruction algorithm in spectral CT examination of patients with different BMI, and to optimize the scanning mode, scanning parameters, the best weight iterative reconstruction algorithm and the lowest concentration of contrast agent suitable for Chinese body mass.

药物成份或治疗方案详述:

探讨自动管电压调制技术联合人工智能迭代重建(AIIR)算法与常规管电压联合卡尔迭代重建(KARL)算法在胸腹盆CT增强中图像质量和辐射剂量比较研究,同时优选出胸腹盆CT增强检查中AIIR的最佳噪声等级。用此优化好的扫描方案对不同胸腹盆患者进行能谱CT增强扫描,将所得能谱CT图像数据在AW4.7工作站进行图像数据分析,通过测量、计算和提取CT值、SNR、CNR。主客观图像质量评价数据等数据。 

Description for medicine or protocol of treatment in detail:

Automatic Tube Voltage Modulation, automatic tube voltage modulation, ATVM) combined with Artificial Intelligence Iterative Reconstruction (AIIR) algorithm and conventional tube voltage combined with KARL 3D Iterative Reduction (KARL 3D Iterative Reduction, ATVM) algorithm To compare the image quality and radiation dose of chest, abdomen and pelvis enhanced CT with Karl-3D IR (KARL-3D IR) algorithm, and to optimize the optimal noise level of AIIR in chest, abdomen and pelvis enhanced CT. Different patients with different chest, abdomen and pelvis underwent enhanced spectral CT scanning with the optimized scanning protocol. The spectral CT image data were analyzed on AW4.7 workstation, and the CT value, SNR and CNR were measured, calculated and extracted. Subjective and objective image quality evaluation data. 

纳入标准:

Inclusion criteria

排除标准:

排除标准:1)碘对比剂过敏病人;2)严重脏器衰竭;3)扫描野有影响图像质量金属植入物;4)心功能不全失代偿期; 5)妊娠。

Exclusion criteria:

Exclusion criteria: 1) Patients with iodine contrast allergy; 2) severe organ failure; 3) The scanning field has metal implants that affect the image quality; 4) decompensation period of cardiac insufficiency; 5) Pregnancy.

研究实施时间:

Study execute time:

From 2024-03-01 00:00:00 To 2026-03-01 00:00:00  

征募观察对象时间:

Recruiting time:

From 2024-03-01 00:00:00 To 2025-08-01 00:00:00

干预措施:

Interventions:

组别:

试验组

样本量:

50

Group:

Experimental group

Sample size:

干预措施:

自动管电压 病人图像采用AIIR算法进行重建

干预措施代码:

Intervention:

Automatic tube voltage The patient image was reconstructed by AIIR algorithm

Intervention code:

组别:

对照组

样本量:

50

Group:

Control group

Sample size:

干预措施:

管电压120kVp 病人图像采用Karl算法重建

干预措施代码:

Intervention:

Tube voltage 120kVp The patient image was reconstructed by Karl algorithm

Intervention code:

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

河北 

市(区县):

 

Country:

China

Province:

Hebei

City:

单位(医院):

河北大学附属医院 

单位级别:

三甲 

Institution
hospital:

Affiliated Hospital of Hebei University

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

信噪比

指标类型:

主要指标

Outcome:

Contrast-to-noise ratio

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

对比信噪比

指标类型:

主要指标

Outcome:

Signal-to-noise ratio

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

容积CT剂量指数

指标类型:

主要指标

Outcome:

Volume CT dose index

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

剂量长度乘积

指标类型:

主要指标

Outcome:

Dose-length product

Type:

Primary 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:

主要指标

Outcome:

Subjective image quality

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:

正在进行

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):

将统一进行胸腹盆检查的患者随机分成两组,并且两组的性别、BMI值分布无差异。

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

The patients who underwent the thoracoabdominal basin examination were randomly divided into two groups, and there was no difference in age, sex and BMI distribution between the two groups.

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:

所有图像均由两名具有10年以上工作经验的放射科医生独立并采用双盲法进行评分。

Blinding:

All images were scored independently and in a double-blind manner by two radiologists with more than 10 years of experience.

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):

试验结束6个月后,邮箱联系zyx_zyx999@163.com获取原始数据。

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

Six months after the conclusion of the experiment, please contact zyx_zyx999@163.com via email to obtain the original data.

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:

采用病历记录表进行数据管理。

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

Case Record Form were used for data management.

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:

 2025-06-12 10:13:33