|
审核状态: Project audit state: |
通过审核 Successful |
|
注册号: Registration number: |
ChiCTR2500101403 |
|
最近更新日期: Date of Last Refreshed on: |
2025-04-24 11:14:51 |
|
注册时间: Date of Registration: |
2025-04-24 00:00:00 |
|
注册号状态: |
预注册 |
|
Registration Status: |
Prospective registration |
|
注册题目: |
基于深度学习的多中心MRI运动伪影校正系统构建及诊断可信性验证研究 |
|
Public title: |
Development of a Deep Learning-Based Multi-Center MRI Motion Artifact Correction System and Validation Study on Diagnostic Credibility |
|
注册题目简写: |
|
|
English Acronym: |
|
|
研究课题的正式科学名称: |
基于深度学习的多中心MRI运动伪影校正系统构建及诊断可信性验证研究 |
|
Scientific title: |
Development of a Deep Learning-Based Multi-Center MRI Motion Artifact Correction System and Validation Study on Diagnostic Credibility |
|
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: |
郑丹群 |
研究负责人: |
边云 |
|
Applicant: |
Danqun Zheng |
Study leader: |
Yun Bian |
|
申请注册联系人电话: Applicant telephone: |
+86 150 8011 9927 |
研究负责人电话: Study leader's telephone: |
+86 138 1635 7024 |
|
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: |
770320180@qq.com |
研究负责人电子邮件: Study leader's E-mail: |
bianyun2012@foxmail.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: |
上海市杨浦区长海路168号 |
研究负责人通讯地址: |
上海市杨浦区长海路168号 |
|
Applicant address: |
No. 168, Changhai Road, Yangpu, ShanghaiNo. 168, Changhai Road, Yangpu, Shanghai |
Study leader's address: |
No. 168, Changhai Road, Yangpu, Shanghai |
|
申请注册联系人邮政编码: Applicant postcode: |
223001 |
研究负责人邮政编码: Study leader's postcode: |
223001 |
|
申请人所在单位: |
海军军医大学长海医院 |
||
|
Applicant's institution: |
Changhai Hospital, The Navy Military Medical University |
||
|
研究负责人所在单位: |
海军军医大学长海医院 |
||
|
Affiliation of the Leader: |
Changhai Hospital, The Navy Military Medical University |
||
|
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: |
CHEC-Y2025-33 |
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: |
上海长海医院伦理委员会 |
||
|
Name of the ethic committee: |
Shanghai Changhai Hospital Ethics Committee |
||
|
伦理委员会批准日期: Date of approved by ethic committee: |
2025-01-10 00:00:00 |
||
|
伦理委员会联系人: |
张优琴 |
||
|
Contact Name of the ethic committee: |
Youqin Zhang |
||
|
伦理委员会联系地址: |
上海市杨浦区长海路168号 |
||
|
Contact Address of the ethic committee: |
No.168, Changhai Road, Yangpu District, Shanghai |
||
|
伦理委员会联系人电话: Contact phone of the ethic committee: |
+86 21 3116 2338 |
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: |
海军军医大学长海医院 |
||||||||||||||||||||||
|
Primary sponsor: |
Changhai Hospital, The Navy Military Medical University |
||||||||||||||||||||||
|
研究实施负责(组长)单位地址: |
上海市杨浦区长海路168号 |
||||||||||||||||||||||
|
Primary sponsor's address: |
No. 168, Changhai Road, Yangpu, Shanghai |
||||||||||||||||||||||
|
试验主办单位(项目批准或申办者): Secondary sponsor: |
|
||||||||||||||||||||||
|
经费或物资来源: |
自筹 |
||||||||||||||||||||||
|
Source(s) of funding: |
Self-raised |
||||||||||||||||||||||
|
Target disease: |
Head tumours/strokes, abdominal organ lesions, knee injuries, ankle trauma |
||||||||||||||||||||||
|
Target disease code: |
|
||||||||||||||||||||||
|
研究类型: |
观察性研究 |
||||||||||||||||||||||
|
Study type: |
Observational study |
||||||||||||||||||||||
|
研究所处阶段: |
其它 | ||||||||||||||||||||||
|
Study phase: |
N/A |
||||||||||||||||||||||
|
研究设计: |
横断面 |
||||||||||||||||||||||
|
Study design: |
Cross-sectional |
||||||||||||||||||||||
|
研究目的: |
1. 验证深度学习运动校正算法的临床诊断非劣效性 2. 评估影像生物标志物稳定性 3. 探索AI校正技术对临床工作流的优化作用 |
||||||||||||||||||||||
|
Objectives of Study: |
1. Validate the clinical diagnostic non-inferiority of the deep learning-based motion correction algorithm 2. Evaluate the robustness of imaging biomarkers across multi-center datasets 3. Investigate the optimization effects of AI-based correction technology on clinical workflows |
||||||||||||||||||||||
|
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)临床指征: 临床开具目标部位MRI检查医嘱(疾病组) 自愿参与研究的健康志愿者(健康组) (2)技术可行性: 可配合完成标准+诱导伪影双序列扫描(采用FDA批准的伪影模拟设备) (3)伦理合规: 签署动态电子知情同意书(通过区块链存证) 未参与其他影像学研究(洗脱期>=3个月) |
||||||||||||||||||||||
|
Inclusion criteria |
(1) Clinical Indications - Patients with clinically indicated MRI requisitions for targeted anatomical regions (disease group) - Healthy volunteers meeting study enrollment criteria with voluntary participation (health group) (2) Technical Feasibility - Capacity to complete dual-protocol MRI acquisitions: ? Standard clinical scanning protocol ? Motion-artifact induced scanning protocol (Use of FDA-approved artefact simulation devices) (3) Ethical Compliance - Signed dynamic electronic informed consent (DEIC) with blockchain-based audit trail(Deposit of evidence via blockchain) - Exclusion of concurrent enrollment in other imaging trials (Elution period >= 3 months) |
||||||||||||||||||||||
|
排除标准: |
(1)安全禁忌(满足任一项即排除): MRI绝对禁忌证(心脏起搏器/磁性植入物等) 妊娠状态(血β-hCG检测阴性准入) (2)技术限制: 体重指数(BMI)>=40导致扫描孔径限制 目标部位金属植入物(Artifact Reduction Score<3级) (3)依从性风险: 幽闭恐惧症(经Claustrophobia Questionnaire评分>=20分) 预期生存期<6个月(姑息治疗患者) |
||||||||||||||||||||||
|
Exclusion criteria: |
(1) Safety Contraindications(excluded if any one of them is satisfied): - Absolute MRI contraindications (e.g., cardiac pacemakers/magnetic implants). - Pregnancy(admission permitted only with negative blood β-hCG test). (2) Technical Limitations: - Body Mass Index (BMI) >=40 (due to scanning bore limitations). - Metallic implants in the target area (Artifact Reduction Score < Grade 3). (3) Compliance Risks: -Claustrophobia (Claustrophobia Questionnaire score >= 20). - Life expectancy < 6 months (for palliative care patients). |
||||||||||||||||||||||
|
研究实施时间: Study execute time: |
从 From 2025-05-07 00:00:00至 To 2026-05-07 00:00:00 |
征募观察对象时间: Recruiting time: |
从From 2025-05-07 00:00:00 至 To 2026-05-07 00:00:00 |
|
干预措施: Interventions: |
|
|
研究实施地点: Countries of recruitment and research settings: |
|
||||||||||||||||||||||||||||
|
测量指标: Outcomes: |
|
|
采集人体标本:
Collecting sample(s)
|
|
|
征募研究对象情况: Recruiting status: |
尚未开始 Not yet recruiting |
年龄范围: Participant age: |
|
||||||
|
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): |
使用Excel生成随机数。 |
||||||||
|
Randomization Procedure (please state who generates the random number sequence and by what method): |
Use Excel to generate random numbers |
||||||||
|
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: |
1、受试者层级盲法核心策略 (1)信息分层披露 :仅告知“两次优化扫描,避免专业术语” (2)行为暗示干预:发布模糊指令(如“根据语音提示调整体位”) 2、技师操作盲法核心策略 (1)协议预编程 :扫描参数封装为单一协议包(Study-ABC (2)自动化触发:视觉引导系统(自动执行运动诱导) 3、影像评估盲法核心策略 (1)数据混淆:混合10%历史正常图像+5%模拟伪影图像 (2)平台限制:隐藏序列参数(TR/TE),禁用窗宽预设,随机化显示顺序 (3)任务干扰:插入模拟病灶标注任务 4、数据分析盲法核心策略 (1) 逻辑隔离:独立统计分析服务器,仅导入编码数据(不包含原始图像) (2)代码锁定:R脚本自动化分析,版本锁定。 |
|
Blinding: |
1. Core strategy for subject-level blinding (1) Hierarchical disclosure of information: only ‘two optimised scans, avoiding jargon’ were given. (2) Behavioural cueing intervention: issue vague instructions (e.g., ‘adjust position according to voice prompts’) 2. Technician-operated blinding core strategy (1) Protocol pre-programming: scanning parameters are encapsulated into a single protocol package (Study-ABC) (2) Automated triggering: visual guidance system (automatic execution of motion induction) 3Image assessment blinding core strategy (1) Data obfuscation: mixing 10% historical normal images + 5% simulated artefact images (2) Platform restriction: hide sequence parameters (TR/TE), disable window width presets, randomise display order (3) Task interference: insert simulated lesion annotation task 4The core strategy of data analysis blinding (1) Logical isolation: independent statistical analysis server, import only coded data (not including the original image) (2) Code locking: R script automated analysis, version locking |
|
试验完成后的统计结果(上传文件): |
|
|
Calculated Results after
|
|
|
是否共享原始数据: IPD sharing |
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): |
发表文章;预测AI模型和推理代码已在GitHub(https://github.com/CHANGHAI-AILab/NET)上公开提供 |
|
The way of sharing IPD”(include metadata and protocol, If use web-based public database, please provide the url): |
Published article;The prediction AI models and inference code were made publicly available on GitHub (https://github.com/CHANGHAI-AILab/NET) |
|
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: |
数据采集:研究者将病例信息记录于excel表格后双人核对; 数据管理:有关受试者身份相关的所有信息资料均予以保密,相关资料在相关法律和/或法规允许的范围之外不对外公开。 |
|
Data collection and Management (A standard data collection and management system include a CRF and an electronic data capture: |
Data collection: The investigator records the case information in excel and then double-checks the data. Data management: All information related to the identity of the subject will be kept confidential, and the relevant information will not be disclosed to the public except as permitted by relevant laws and/or regulations. |
|
数据与安全监察委员会: Data and Safety Monitoring Committee: |
暂未确定/Not yet |