ChiCTR2600126172 版本V1.0 版本创建时间2026/06/04 16:22:49 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：

 ChiCTR2600126172 

最近更新日期：

Date of Last Refreshed on：

 2026-06-04 16:22:35 

注册时间：

Date of Registration：

 2026-06-04 00:00:00 

注册号状态：

预注册

Registration Status：

Prospective registration

注册题目：

基于瘤体和瘤周区域 CT 特征的人工智能融合模型预测结直肠癌肿瘤沉积与预后的临床研究

Public title：

Clinical Study on Predicting Tumor Deposition and Prognosis of Colorectal Cancer by Artificial Intelligence Fusion Model Based on CT Features of Tumor and Peritumoral Regions

注册题目简写：

English Acronym：

研究课题的正式科学名称：

基于瘤体和瘤周区域 CT 特征的人工智能融合模型预测结直肠癌肿瘤沉积与预后的临床研究

Scientific title：

Clinical Study on Predicting Tumor Deposition and Prognosis of Colorectal Cancer by Artificial Intelligence Fusion Model Based on CT Features of Tumor and Peritumoral Regions

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：

汤梓祺 

研究负责人：

李永海 

Applicant：

Ziqi Tang 

Study leader：

Yonghai Li 

申请注册联系人电话：

Applicant telephone：

 +86 18616296548

研究负责人电话：

Study leader's
telephone：

+86 551 62183010

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：

 2320186540@qq.com

研究负责人电子邮件：

Study leader's E-mail：

 liyonghai20@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：

中国安徽省合肥市庐阳区淮河路390号

研究负责人通讯地址：

中国安徽省合肥市庐阳区淮河路390号

Applicant address：

390 Huaihe Road, Luyang District, Hefei, Anhui, China

Study leader's address：

390 Huaihe Road, Luyang District, Hefei, Anhui, 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：

合肥市第一人民医院

Applicant's institution：

Hefei First People's Hospital

研究负责人所在单位：

合肥市第一人民医院

Affiliation of the Leader：

Hefei First People's Hospital

是否获伦理委员会批准：

是

Approved by ethic committee：

Yes

伦理委员会批件文号：

Approved No. of ethic committee：

 伦研批第2026-133-01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：

合肥市第一人民医院伦理委员会

Name of the ethic committee：

Ethics Committee of Hefei First People's hospital

伦理委员会批准日期：

Date of approved by ethic committee：

 2026-05-25 00:00:00

伦理委员会联系人：

叶芝

Contact Name of the ethic committee：

Ye Zhi

伦理委员会联系地址：

中国安徽省合肥市庐阳区淮河路390号

Contact Address of the ethic committee：

390 Huaihe Road, Luyang District, Hefei, Anhui, China

伦理委员会联系人电话：

Contact phone of the ethic committee：

 +86 551 62183685

伦理委员会联系人邮箱：

Contact email of the ethic committee：

 hfyykyc@163.com

研究实施负责（组长）单位：

合肥市第一人民医院

Primary sponsor：

Hefei First People's Hospital

研究实施负责（组长）单位地址：

中国安徽省合肥市庐阳区淮河路390号

Primary sponsor's address：

390 Huaihe Road, Luyang District, Hefei, Anhui, 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)：

安徽

市(区县)：

Country：

China

Province：

Anhui

City：

单位(医院)：

合肥市第一人民医院

具体地址：

中国安徽省合肥市庐阳区淮河路390号

Institution
hospital：

Hefei First People's Hospital

Address：

390 Huaihe Road, Luyang District, Hefei, Anhui, China

经费或物资来源：

合肥市卫生健康科技项目

Source(s) of funding：

Hefei Health Science and Technology Project

研究疾病：

结直肠癌肿瘤沉积  

Target disease：

Colorectal cancer; tumor deposits (TD)

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：

肿瘤沉积是结直肠癌重要的不良病理因素，与复发、远处转移和生存不良密切相关。现行临床实践中，TD主要依赖术后病理切除标本进行确认，术前缺乏稳定、可重复、无创的风险识别工具。已有研究提示，TD在结直肠癌分期和预后评估中具有独立价值，但其在现有TNM体系中的处理仍存在局限，尤其是在合并淋巴结转移时，TD的额外预后信息容易被低估。因此，构建基于术前增强CT的AI-TD风险预测模型，有助于在手术前识别TD高风险患者，为手术范围评估、淋巴结清扫策略、围手术期治疗决策、术后辅助治疗强度及随访方案制定提供参考。本研究模型的临床定位不是替代术后病理诊断，而是作为术前风险分层和个体化管理的辅助工具。  

Objectives of Study：

Tumor deposition (TD) is an important adverse pathological factor in colorectal cancer (CRC), which is closely associated with recurrence, distant metastasis and poor survival. In current clinical practice, TD is mainly confirmed based on postoperative pathological resection specimens, and there is a lack of stable, reproducible and non-invasive tools for preoperative risk identification. Accumulating evidence indicates that TD has independent value in the staging and prognostic evaluation of CRC, but its handling in the current TNM staging system still has limitations. Particularly when concomitant lymph node metastasis is present, the additional prognostic information provided by TD is prone to be underestimated. Therefore, the construction of an AI-based TD risk prediction model based on preoperative contrast-enhanced CT can help identify patients at high risk of TD before surgery, and provide references for the assessment of surgical extent, lymph node dissection strategy, perioperative treatment decision-making, intensity of postoperative adjuvant therapy and formulation of follow-up plans. The clinical positioning of the model developed in this study is not to replace postoperative pathological diagnosis, but to serve as an adjunctive tool for preoperative risk stratification and individualized management.

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. 经手术切除并经术后病理证实为结直肠癌的患者；
2. 术前接受增强CT检查，且CT图像质量满足影像组学/深度学习分析要求；
3. 术后病理资料完整，可明确肿瘤沉积状态；
4. 临床资料、影像资料及病理资料完整；

Inclusion criteria

1. Patients with colorectal cancer confirmed by postoperative pathology after surgical resection;
2. Patients who underwent preoperative contrast-enhanced CT examination with adequate image quality for radiomics/deep learning analysis;
3. Complete pathological information was available to determine the status of tumor deposits (TD);
4. Complete clinical, imaging and pathological data were available;

排除标准：

1. 术前已接受放疗、化疗、靶向治疗、免疫治疗等抗肿瘤治疗者；
2. CT图像质量差、存在明显伪影或病灶显示不清，无法进行图像分割及特征提取者；
3. 临床资料、影像资料或病理资料缺失者；
4. 合并其他恶性肿瘤或既往有其他恶性肿瘤病史者；
5. 非原发性结直肠癌、术后复发病例或病理诊断不明确者；

Exclusion criteria：

1. Patients who received preoperative radiotherapy, chemotherapy, targeted therapy, immunotherapy or other anti-tumor treatments;
2. Patients with poor CT image quality, obvious artifacts or unclear tumor visualization, making image segmentation and feature extraction impossible;
3. Patients with incomplete clinical, imaging or pathological data;
4. Patients with concurrent or previous history of other malignancies;
5. Patients with non-primary colorectal cancer, postoperative recurrent disease or unclear pathological diagnosis;

研究实施时间：

Study execute time：

从 From 2026-01-01 00:00:00至 To 2027-12-31 00:00:00  

征募观察对象时间：

Recruiting time：

从 From 2026-06-10 00:00:00 至 To 2026-12-31 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）：

以手术切除标本的术后病理检查结果作为参考标准，由病理报告明确结直肠癌患者是否存在肿瘤沉积

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 postoperative pathological examination of surgically resected specimens will be used as the reference standard to determine the presence or absence of tumor deposits (TD) in patients with colorectal cancer.

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）：

基于术前增强CT图像构建的影像组学模型、深度学习模型及融合模型，用于术前预测结直肠癌患者肿瘤沉积（TD）状态。

Index test:

Radiomics, deep learning and combined models based on preoperative contrast-enhanced CT images will be used to predict the status of tumor deposits (TD) in patients with colorectal cancer.

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）

经手术切除并经术后病理证实的原发性结直肠癌患者，包括结肠癌和直肠癌患者；患者术前接受增强CT检查，且临床、影像及病理资料完整。

例数:

Sample size:

400

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 condition is tumor deposits (TD) in patients with primary colorectal cancer, including colon cancer and rectal cancer, confirmed by postoperative pathology after surgical resection.

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）：

无

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:

None

研究实施地点：

Countries of recruitment and research settings：

国家：

 中国

省(直辖市)：

 安徽 

市(区县)：

  

Country：

China

Province：

Anhui

City：

单位(医院)：

 合肥市第一人民医院 

单位级别：

 三级甲等 

Institution
hospital：

Hefei First People's Hospital

Level of the institution：

Tertiary A

测量指标：

Outcomes：

指标中文名：

受试者工作特征曲线下面积（AUC）

指标类型：

主要指标

Outcome：

Area under the receiver operating characteristic curve, AUC

Type：

Primary indicator

测量时间点：

术后病理明确且完成模型验证后

测量方法：

以术后病理检查明确的肿瘤沉积（tumor deposits，TD）状态作为参考标准，根据影像组学模型、深度学习模型及融合模型输出的预测概率绘制受试者工作特征曲线（ROC曲线），计算曲线下面积（AUC）及其95%置信区间，用于评价模型术前识别结直肠癌肿瘤沉积的诊断效能。

Measure time point of outcome：

After postoperative pathological is confirmed and validation of the model is completed

Measure method：

The TD status determined by postoperative pathological examination will be used as the reference standard. ROC curves will be generated based on the predicted probabilities from the radiomics model, deep learning model and combined model. The area under the curve (AUC) and its 95% confidence interval will be calculated to evaluate the diagnostic performance of the models for preoperative identification of tumor deposits in colorectal cancer.

指标中文名：

模型预测结直肠癌肿瘤沉积状态的敏感度、特异度、准确率、阳性预测值和阴性预测值

指标类型：

次要指标

Outcome：

Sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of the model for predicting tumor deposits in colorectal cancer

Type：

Secondary indicator

测量时间点：

术后病理肿瘤沉积状态明确并完成模型验证后

测量方法：

以术后病理 TD 状态作为参考标准，根据训练集中确定的 AI-TD score 最佳截断值，在内部验证集和/或外部验证集中计算敏感度、特异度、准确率、阳性预测值、阴性预测值及其 95% 置信区间。

Measure time point of outcome：

After postoperative pathological tumor deposit status is confirmed and model validation is completed

Measure method：

Using postoperative pathological TD status as the reference standard, the optimal cutoff value of the AI-TD score determined in the training cohort will be applied to the internal and/or external validation cohorts to calculate sensitivity, specificity, accuracy, positive predictive value, negative predictive value, and their 95% confidence intervals.

指标中文名：

模型的临床应用价值

指标类型：

次要指标

Outcome：

Clinical utility of the model

Type：

Secondary indicator

测量时间点：

完成模型内部验证和/或外部验证时

测量方法：

采用决策曲线分析评价 AI-TD 融合模型在不同阈值概率下用于术前 TD 风险分层的净获益。

Measure time point of outcome：

When internal and/or external validation of the model is completed

Measure method：

Decision curve analysis will be performed to evaluate the net benefit of the AI-TD fusion model for preoperative TD risk stratification across different threshold probabilities.

指标中文名：

模型的校准性能

指标类型：

次要指标

Outcome：

Calibration performance of the model

Type：

Secondary indicator

测量时间点：

完成模型内部验证和/或外部验证时

测量方法：

采用校准曲线、校准截距、校准斜率、Brier score 及 Hosmer-Lemeshow 检验评价模型预测 TD 阳性概率与实际病理 TD 状态之间的一致性。

Measure time point of outcome：

When internal and/or external validation of the model is completed

Measure method：

Calibration curves, calibration intercept, calibration slope, Brier score, and the Hosmer-Lemeshow test will be used to evaluate the agreement between the predicted probability of TD positivity and the actual pathological TD status.

指标中文名：

AI-TD风险分数与无病生存期的关系

指标类型：

次要指标

Outcome：

Association between the AI-TD risk score and disease-free survival

Type：

Secondary indicator

测量时间点：

术后每 6 个月随访一次，计划随访 2 年。

测量方法：

无病生存期定义为自手术日期至首次肿瘤复发、远处转移或死亡的时间。采用 Kaplan-Meier 曲线和 Log-rank 检验比较 AI-TD 高风险组与低风险组的无病生存期差异；采用 Cox 比例风险模型计算风险比及 95% 置信区间。若随访事件数不足，仅报告探索性趋势和风险比。

Measure time point of outcome：

Follow-up will be conducted every 6 months after surgery for a planned duration of 2 years.

Measure method：

Disease-free survival is defined as the time from surgery to the first occurrence of tumor recurrence, distant metastasis, or death. Kaplan-Meier curves and the log-rank test will be used to compare disease-free survival between the AI-TD high-risk and low-risk groups. Cox proportional hazards regression will be used to estimate the hazard ratio and 95% confidence interval. If the number of events is insufficient, only exploratory trends and hazard ratios will be reported.

采集人体标本：

Collecting sample(s)
from participants：

标本中文名：

结直肠癌患者病理蜡块

组织：

Sample Name：

FFPE blocks from colorectal cancer patients

Tissue：

人体标本去向

 使用后保存  

说明

Fate of sample：

Preservation after use  

Note：

标本中文名：

结直肠癌患者手术标本

组织：

Sample Name：

Colorectal cancer surgical specimens

Tissue：

人体标本去向

 使用后保存  

说明

Fate of sample：

Preservation after use  

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 岁 years
最大 Max age 岁 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）：

无

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:

不公开/Private

盲法：

无

Blinding：

None

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）：

无

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

None

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：

本研究为回顾性研究，研究数据来源于医院既往诊疗过程中形成的临床资料、术前增强CT影像资料及术后病理资料。研究者根据统一制定的病例报告表（Case Record Form，CRF）收集患者基本信息、临床资料、影像资料及病理结果，并建立电子数据库进行管理。所有数据在录入前进行去标识化处理，由专人负责数据录入、核查和质量控制，确保数据真实、完整、准确。研究数据仅供本课题研究使用，并按照伦理委员会及医院数据安全管理要求进行保存和管理。

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

This is a retrospective study. The study data will be obtained from clinical records, preoperative contrast-enhanced CT images and postoperative pathological reports generated during routine clinical practice. Data including demographic information, clinical characteristics, imaging data and pathological results will be collected using a standardized case record form (CRF) and managed in an electronic database. All data will be de-identified before analysis. Data entry, verification and quality control will be performed by designated researchers to ensure data authenticity, completeness and accuracy. The study data will be used only for this research and stored in accordance with the requirements of the ethics committee and hospital data security regulations.

数据与安全监察委员会：

Data and Safety Monitoring Committee：

无/No

注册人：

Name of Registration：

  2026-06-04 16:22:35