Feasibility of CT texture analysis in differentiating c-kit/PDGFRA gene mutations in gastrointestinal stromal tumors

REN Caiyue; WANG Shengping; REN Min; LIU Zhuang; ZHANG Shengjian; PENG Weijun

doi:10.19732/j.cnki.2096-6210.2019.02.007

您当前的位置：

首页 >

文章列表页 >

Feasibility of CT texture analysis in differentiating c-kit/PDGFRA gene mutations in gastrointestinal stromal tumors

更新时间：2025-12-15

- Feasibility of CT texture analysis in differentiating c-kit/PDGFRA gene mutations in gastrointestinal stromal tumors
- Vol. 28, Issue 2, Pages: 101-105(2019)
- 作者机构：
  
  复旦大学附属肿瘤医院放射诊断科，复旦大学上海医学院肿瘤学系,上海,200032
- 作者简介：
- 基金信息：
- DOI：10.19732/j.cnki.2096-6210.2019.02.007
  CLC：
- Published Online：24 May 2019，
  
  Published：24 May 2019
- 稿件说明：
移动端阅览
任采月,王升平,任敏,等. CT纹理分析鉴别胃肠道间质瘤c-kit/PDGFRA基因突变的初步研究[J]. 肿瘤影像学, 2019, 28(2): 101-105 https://doi.

org/10.19732/j.cnki.2096-6210.2019.02.007
任采月,王升平,任敏,等. CT纹理分析鉴别胃肠道间质瘤c-kit/PDGFRA基因突变的初步研究[J]. 肿瘤影像学, 2019, 28(2): 101-105 https://doi. DOI： 10.19732/j.cnki.2096-6210.2019.02.007.

org/10.19732/j.cnki.2096-6210.2019.02.007 DOI：

摘要

目的：

探讨CT纹理分析在鉴别胃肠道间质瘤（gastrointestinal stromal tumor，GIST）

c-kit

/血小板源性生长因子受体（platelet-derived growth factor receptor alpha，PDGFRA）基因突变类型中的价值。

方法：

回顾性分析140例经分子病理学检查证实的GIST患者的CT增强图像，其中

c-kit

突变型126例，

PDGFRA

突变型14例。采用LIFEx软件对CT门静脉期图像进行分析，共提取41种纹理特征。采用Mann-Whitney

检验比较两组间各参数的差异并绘制受试者工作特征（receiver operating characteristic，ROC）曲线。

结果：

短区域因子（short-zone emphasis，SZE）、短区高灰度级因子（short-zone high gray-level emphasis，SZHGE）及区域百分比（zone percentage，ZP）在

c-kit

突变型GIST中高于PDGFRA突变型GIST（

＜0.05）。两组间其余纹理参数差异均无统计学意义（

＞0.05）。SZE、SZHGE和ZP鉴别两者的曲线下面积（area under curve，AUC）分别为0.69、0.70和0.71（

＜0.05），灵敏度分别为46.03%、47.62%及78.57%，特异度分别为92.86%、92.86%及64.29%，准确率分别为83.57%、83.57%及90.00%。

结论：

CT纹理分析能够为鉴别GIST

c-kit/PDGFRA

基因突变提供一定的诊断信息。

Abstract

Objective：

To investigate the feasibility of differentiating

c-kit

/platelet-derived growth factor receptor alpha (

PDGFRA

) gene mutations in gastrointestinal stromal tumors (GI

STs) based on CT texture analysis.

Methods:

The contrast-enhanced CT features of 140 GIST patients confirmed by molecular pathology were retrospectively analyzed (126 with

c-kit

mutation

14 with

PDGFRA

mutation). Texture features were extracted using LIFEx package. Mann-Whitney

test was used to compare the difference in the parameters between the patients with

c-kit

and

PDGFRA

mutations. The differentiation performance was evaluated by the area under curve (AUC) of receiver operating characteristic (ROC) curve.

Results:

GIST patients with

c-kit

mutation exhibited higher short-zone emphasis (SZE)

higher short-zone high gray-level emphasis (SZHGE) and higher zone percentage (ZP) than those with

PDGFRA

mutation (

＜0.05). There was no statistically significant difference in other texture parameters between the two groups (

＞0.05). The SZE

SZHGE and ZP successfully showed the differentiation performance between GIST patients with

c-kit

and

PDGFRA

mutations with AUCs of 0.69

0.70 and 0.71 (

＜0.05)

sensitivities of 46.03%

47.62% and 78.57%

specificities of 92.86%

92.86% and 64.29%

accuracies of 83.57%

83.57% and 90.00%

respectively.

Conclusion:

CT texture analysis has certain values in differentiating

c-kit

mutation from

PDGFRA

mutation in GIST patients.

关键词

Keywords

references

Views

1849

下载量

CNKI被引量

Alert me when the article has been cited

提交

Tools

Publicity Resources

The value of CT texture analysis in preoperative evaluation of colon cancer

The value of color doppler ultrasound in the diagnosis of liver metastasis of gastrointestinal and extragastrointestinal malignant stromal tumor

CT signs and clinicopathological features of gastrointestinal stromal tumor

Application progress of deep learning techniques in lung cancer imaging diagnosis

Radiomics models in differentiating parotid pleomorphic adenoma from Warthin tumor

Related Author

WEN Deying

DING Jingjing

YANG Lie

LI Yuan

SUN Jiayu

MENG Xiangdong

MU Yi

WANG Jing

Related Institution

Department of Radiology, West China Hospital, Sichuan University

Department of General Surgery, Xi&rsquo

Department of Imaging, Huai&rsquo

Department of Nuclear Medicine, Dazhou Central Hospital

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

AI问答

⁰