ChiCTR2600119037 版本V1.0 版本创建时间2026/02/14 10:16:49 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:

ChiCTR2600119037 

最近更新日期:

Date of Last Refreshed on:

2026-02-14 10:15:42 

注册时间:

Date of Registration:

2026-02-14 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于深度学习的淋巴瘤PET/CT影像处理方法及其临床验证

Public title:

Clinical Validation of a Deep Learning–Based PET/CT Image Processing Approach for Lymphoma

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于淋巴瘤PET/CT影像与Deauville评分的深度学习模型构建与临床验证

Scientific title:

Development and Clinical Validation of a Deep Learning Model Based on Lymphoma PET/CT Imaging and Deauville Scoring

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:

何颖明 

研究负责人:

廖曼甜 

Applicant:

Yingming He 

Study leader:

Mantian Liao 

申请注册联系人电话:

Applicant telephone:

+86 137 8625 0252

研究负责人电话:

Study leader's
telephone:

+86 732 5828 6412

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:

646716865@qq.com

研究负责人电子邮件:

Study leader's E-mail:

410431906@qq.con

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:

湖南省湘潭市和平路120号

研究负责人通讯地址:

湖南省湘潭市和平路120号

Applicant address:

120 Heping Road, Xiangtan, Hunan Province, China

Study leader's address:

120 Heping Road, Xiangtan, Hunan Province, 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:

湘潭市中心医院

Applicant's institution:

The Central Hospital of Xiangtan

研究负责人所在单位:

湘潭市中心医院

Affiliation of the Leader:

The Central Hospital of Xiangtan

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:

KYKS202601010

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:

湘潭市中心医院医学伦理委员会

Name of the ethic committee:

Medical Ethics Committee of Xiangtan Central Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2026-01-29 00:00:00

伦理委员会联系人:

吴红

Contact Name of the ethic committee:

Hong Wu

伦理委员会联系地址:

湖南省湘潭市和平路120号药剂楼(4号楼)3楼

Contact Address of the ethic committee:

3rd Floor, Pharmacy Building (Building No. 4), 120 Heping Road, Xiangtan, Hunan Province, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 731 5821 4854

伦理委员会联系人邮箱:

Contact email of the ethic committee:

xtchllwyh@163.com

研究实施负责(组长)单位:

湘潭市中心医院

Primary sponsor:

The Central Hospital of Xiangtan

研究实施负责(组长)单位地址:

湖南省湘潭市和平路120号

Primary sponsor's address:

120 Heping Road, Xiangtan, Hunan 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):

湖南省

市(区县):

湘潭市

Country:

China

Province:

Hunan

City:

Xiangtan

单位(医院):

湘潭市中心医院

具体地址:

湖南省湘潭市和平路120号

Institution
hospital:

The Central Hospital of Xiangtan

Address:

120 Heping Road, Xiangtan, Hunan Province, China

经费或物资来源:

自筹

Source(s) of funding:

Self-funded

研究疾病:

淋巴瘤  

Target disease:

Lymphoma

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:

本研究旨在评估一种基于深度学习去噪的低剂量CT技术在淋巴瘤[18F]FDG PET/CT成像中的临床可行性与诊断等效性。通过将标准剂量CT、模拟四分之一剂量 CT及深度学习去噪后的四分之一剂量CT融合至PET图像中,研究采用多病例、多阅片者、全交叉的自身对照试验设计,系统比较不同成像条件下在病灶检出、疾病分期及疗效评估中的一致性与诊断表现。研究重点验证在显著降低CT辐射剂量的前提下,深度学习去噪低剂量CT是否能够维持与标准剂量PET/CT相当的临床判读可靠性与可解释性,从而为淋巴瘤患者的低辐射随访成像策略提供循证依据。  

Objectives of Study:

This study aims to evaluate the clinical feasibility and diagnostic equivalence of a deep learning–based denoising low-dose CT technique in [18F]FDG PET/CT imaging for lymphoma. By fusing standard-dose CT, simulated quarter-dose CT, and deep learning–denoised quarter-dose CT with PET images, a multi-case, multi-reader, fully crossed self-controlled study design is employed to systematically compare consistency and diagnostic performance across different imaging conditions in terms of lesion detection, disease staging, and treatment response assessment. The study focuses on determining whether, with a substantial reduction in CT radiation dose, deep learning–denoised low-dose CT can maintain clinical interpretability and reading reliability comparable to those of standard-dose PET/CT, thereby providing evidence to support low-radiation follow-up imaging strategies for patients with lymphoma.

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) 接受全身[18F]FDG PET/CT检查的淋巴瘤患者; 2) 影像数据可从PACS系统完整获取; 3) 同时具备基线PET/CT及至少一次随访PET/CT检查(仅适用于临床评价的患者)。

Inclusion criteria

1. Patients with lymphoma who underwent whole-body [18F]FDG PET/CT examinations; 2. Imaging data that can be fully retrieved from the PACS system; 3. Availability of both baseline PET/CT and at least one follow-up PET/CT examination (applicable only to patients included in the clinical evaluation).

排除标准:

1) PET或CT图像数据缺失、不完整; 2) 图像存在严重伪影或质量明显不足,影响病灶检出、分期或疗效评估者; 3) 临床或影像资料不足,无法确定诊断、分期或疗效评估参考标准者。

Exclusion criteria:

1. Missing or incomplete PET or CT imaging data; 2. Images with severe artifacts or clearly insufficient quality that impair lesion detection, disease staging, or treatment response assessment; 3. Insufficient clinical or imaging information to establish reference standards for diagnosis, staging, or treatment response evaluation.

研究实施时间:

Study execute time:

From 2026-01-01 00:00:00 To 2026-09-30 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-02-20 00:00:00 To 2026-04-30 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):

本研究的参考金标准由两名同时具备放射学与核医学资质、且具有丰富淋巴瘤PET/CT阅片经验的高级医师独立判定。如两位医师在病灶检出、疾病分期或疗效评估结果上存在分歧,则通过协商一致的方式达成最终判定结果。

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):

The reference standard in this study was independently determined by two senior physicians who were dual-certified in radiology and nuclear medicine and had extensive experience in interpreting lymphoma PET/CT. In cases of disagreement regarding lesion detection, disease staging, or treatment response assessment, a consensus was reached through discussion to establish the final reference standard.

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):

本研究的指标试验为基于深度学习去噪的低剂量CT影像处理方法,即将模拟四分之一剂量CT图像经深度学习模型去噪处理后,与 [18F]FDG PET 图像融合形成的PET/CT成像方案。

Index test:

The index test in this study is a deep learning–based denoising low-dose CT image processing method, in which simulated quarter-dose CT images are denoised using a deep learning model and subsequently fused with [18F]FDG PET images to generate a PET/CT imaging approach.

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)

本研究的目标人群为接受全身[18F]FDG PET/CT检查的淋巴瘤患者,涵盖不同病理亚型、疾病分期及治疗阶段。

例数:

Sample size:

140

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):

The target population of this study consists of patients with lymphoma who undergo whole-body [18F]FDG PET/CT examinations, encompassing different pathological subtypes, disease stages, and treatment phases.

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):

不适用

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:

Not applicable

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

湖南省 

市(区县):

湘潭市 

Country:

China

Province:

Hunan

City:

Xiangtan

单位(医院):

湘潭市中心医院 

单位级别:

三甲 

Institution
hospital:

The Central Hospital of Xiangtan

Level of the institution:

Tertiary

测量指标:

Outcomes:

指标中文名:

均方根误差、结构相似性指数、峰值信噪比

指标类型:

主要指标

Outcome:

Root Mean Square Error, Structural Similarity Index, and Peak 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:

高代谢病灶检出的灵敏度

指标类型:

主要指标

Outcome:

Sensitivity for hypermetabolic lesions

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

高代谢病灶检出的特异度

指标类型:

主要指标

Outcome:

Specificity for hypermetabolic lesions

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

高代谢病灶检出的ROC-AUC

指标类型:

主要指标

Outcome:

ROC-AUC for hypermetabolic lesions

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:

尚未开始

Not yet recruiting

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):

在多阅片者多病例研究中,不同成像条件的阅片顺序采用随机化方法进行分配。对每位阅片医生,三种PET/CT成像条件(标准剂量、模拟低剂量及去噪低剂量)的阅片顺序以及各病例在每次阅片中的呈现顺序均通过随机数生成方式确定,以减少顺序效应和潜在偏倚。不同阅片阶段之间设置预定的洗脱期,以降低记忆偏倚对判读结果的影响。

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

In the multi-reader multi-case study, the reading order of different imaging conditions was assigned using a randomization approach. For each reader, the order of the three PET/CT imaging conditions (standard-dose, simulated low-dose, and denoised low-dose) as well as the presentation order of cases within each reading session were determined using a random number generator to minimize order effects and potential bias. A predefined washout period was implemented between reading sessions to reduce memory-related bias in image interpretation.

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:

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

否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):

不适用

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

NA

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:

本研究的数据采集和管理采用原始记录表格进行记录,用于记录入组患者的基本人口学信息、临床资料及影像学相关信息,所有数据均来源于既往临床诊疗过程中形成的原始记录。研究过程中所有数据均进行脱敏处理,仅限授权研究人员访问,以确保数据的完整性、安全性和可追溯性。

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

Data collection and management in this study were conducted using original case record forms to document the basic demographic information, clinical data, and imaging-related information of enrolled patients. All data were derived from original records generated during routine clinical care. Throughout the study, all data were de-identified and access was restricted to authorized research personnel only, in order to ensure data integrity, security, and traceability.

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:

 2026-02-14 10:15:42