The value of enhanced CT radiomics in differential diagnosis of small renal cell carcinoma and fat-poor renal angiomyolipoma

XIANG Lingling; WU Jingtao; GAO Yankun; LUO Xianfu; ZHU Qingqiang; TIAN Tongtong

doi:10.19732/j.cnki.2096-6210.2021.03.008

您当前的位置：

首页 >

文章列表页 >

The value of enhanced CT radiomics in differential diagnosis of small renal cell carcinoma and fat-poor renal angiomyolipoma

更新时间：2025-12-15

- The value of enhanced CT radiomics in differential diagnosis of small renal cell carcinoma and fat-poor renal angiomyolipoma
- Vol. 30, Issue 3, Pages: 185-190(2021)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.19732/j.cnki.2096-6210.2021.03.008
  CLC：
- Published Online：28 June 2021，
  
  Published：28 June 2021
- 稿件说明：
移动端阅览
向玲玲,吴晶涛,郜言坤,等. 增强CT影像组学鉴别小肾癌与乏脂肪肾血管平滑肌脂肪瘤的价值[J]. 肿瘤影像学, 2021, 30(3): 185-190 https://doi.

org/10.19732/j.cnki.2096-6210.2021.03.008
向玲玲,吴晶涛,郜言坤,等. 增强CT影像组学鉴别小肾癌与乏脂肪肾血管平滑肌脂肪瘤的价值[J]. 肿瘤影像学, 2021, 30(3): 185-190 https://doi. DOI： 10.19732/j.cnki.2096-6210.2021.03.008.

org/10.19732/j.cnki.2096-6210.2021.03.008 DOI：

摘要

目的：

探讨3期增强计算机体层成像（computed tomography，CT）影像组学特征建立的影像组学模型鉴别小肾癌（直径4 cm）与乏脂肪肾血管平滑肌脂肪瘤（fat-poor renal angiomyolipoma，fpAML）的价值。

方法：

回顾并分析125例直径4 cm的肾脏肿瘤患者术前CT增强扫描图像，包括小肾癌80例，fpAML 45例。分别在皮髓质期、实质期与排泄期图像上勾画三维感兴趣区（region of interest，ROI），按照3∶1的比例划分训练集（93例）与测试集（32例），提取并筛选影像组学特征后，分别建立支持向量机（support vector machine，SVM）、逻辑回归（logistic regression，LR）模型，采用受试者工作特征（receiver operating characteristic，ROC）曲线评价模型对小肾癌与fpAML鉴别诊断的效能。

结果：

通过降维筛选出最优特征91个，其中皮髓质期39个、实质期25个、排泄期27个。基于皮髓质期特征构建的SVM模型鉴别效能最佳，其训练集所对应的曲线下面积（area under curve，AUC）、特异度、灵敏度和准确度分别为0.961、0.917、0.939和0.882；测试集分别为0.825、0.900、0.750和0.875。

结论：

基于3期增强CT影像组学模型在小肾癌与fpAML鉴别中具有较强的效能，其中肾皮髓质期鉴别效能优于实质期与排泄期，且SVM模型鉴别价值较LR模型更高。

Abstract

Objective:

To investigate the value of radiological models in differenting small renal cell carcinoma (diameter 4 cm) from fat-poor renal angiomyolipoma (fpAML) through three-phase enhanced computed tomography (CT) radiomic features.

Methods:

A total of 125 cases with renal tumors with diameter 4 c

m were retrospectively studied

which including small renal carcinoma（

=80）and fpAML（

=45）. The region of interest（ROI） was delineated on the images of the corticomedullary phase

the nephrographic phase and the excretion phase

respectively. Then the training set (

=93) and the testing set (

=32) were divided according to the ratio of 3∶1. After radiomics features were extracted and screened

support vector machine (SVM) model and logistic regression (LR) model were established respectively. using receiver operating characteristic (ROC) curve evaluation model for differential diagnosis of small renal cell carcinoma and fpAML. ROC curve was used to evaluate the effectiveness of model in differential diagnosis of small renal cell carcinoma and fpAML.

Results:

A total of 91 optimal features were selected by dimensionality reduction

39 in corticomedullary phase

25 in nephrographic phase and 27 in excretion phase. The radiological model based on the image of corticomedullary phase has the best discriminative efficacy

and the area under curve (AUC)

specificity

sensitivity and accuracy of the training set were 0.961

0.917

0.939

0.882

of the training set were 0.825

0.900

0.750 and 0.875

respectively.

Conclusion:

Three phase enhanced CT adiological models have a strong effectiveness in the differential diagnosis of small renal cell carcinoma and fpAML

in which the differential efficiency of the corticomedullary phase is better than the nephrographic phase and excretion phase

and the differential value of SVM model is higher than LR model.

关键词

Keywords

references

Views

2091

下载量

CNKI被引量

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on a prediction model for superficial lymphoma based on multimodal ultrasound radiomics

Intelligent imaging for precision diagnosis and treatment of pancreatic tumors: current applications and future perspectives

Multi-region radiomics features from enhanced CT combined with clinical risk factors for preoperative prediction of lymphovascular invasion in colon cancer

The predictive value of CT radiomics model for immunotherapy efficacy in non-small cell lung cancer

Value of a multiparameter MRI radiomics nomogram for preoperative prediction of endometrial carcinoma risk stratification

Related Author

XU Jianhua

NIE Fang

TANG Wei

YUAN Xiaohan

YU Xianjun

TONG Tong

Wanping LI

Wenbin ZHENG

Related Institution

Department of Ultrasonography, Lanzhou University Second Hospital

Department of Radiology, Fudan University Shanghai Cancer Center, Department of Oncology, Shanghai Medical College, Fudan University

Department of Pancreatic Surgery, Fudan University Shanghai Cancer Center, Department of Oncology, Shanghai Medical College, Fudan University

Shantou University Medical School

Department of Radiology, Puning People's Hospital, Puning

AI问答

⁰