CT纹理分析：结直肠癌KRAS基因突变状态评估的潜在生物标志物

曹剑; 王国蓉; 王志伟; 金征宇

doi:10.24920/003770

Your Location：

Home >

Browse articles >

CT纹理分析：结直肠癌KRAS基因突变状态评估的潜在生物标志物

中国医学科学杂志（英文版） 2020年35卷第4期页码：306-314

Original Article | Updated：2024-04-10

- CT纹理分析：结直肠癌KRAS基因突变状态评估的潜在生物标志物
- Affiliations：
  
  Department of Radiology, Peking Union Medical College Hospital,Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing 100730, China
- Author bio：
  
  * Tel: 86-10-69159567; Fax: 86-10-69159567; E-mail: zhiweiwang1981@sina.com.
- Funds：
  
  the National Public Welfare Basic Scientific Research Program of Chinese Academy of Medical Sciences(2018PT32003)
- DOI：10.24920/003770
  中图分类号：
- 收稿日期：2020-04-30，
  
  录用日期：2020-7-16，
  
  网络出版日期：2020-12-31，
  
  纸质出版日期：2020-12-31
- Accepted：
Scan QR Code
曹剑, 王国蓉, 王志伟, 等. CT纹理分析：结直肠癌KRAS基因突变状态评估的潜在生物标志物[J]. 中国医学科学杂志（英文版）, 2020,35(4):306-314.

Cao Jian, Wang Guorong, Wang Zhiwei, et al. CT Texture Analysis: A Potential Biomarker for Evaluating KRAS Mutational Status in Colorectal Cancer[J]. Chinese medical sciences journal, 2020, 35(4): 306-314.
曹剑, 王国蓉, 王志伟, 等. CT纹理分析：结直肠癌KRAS基因突变状态评估的潜在生物标志物[J]. 中国医学科学杂志（英文版）, 2020,35(4):306-314. DOI： 10.24920/003770.

Cao Jian, Wang Guorong, Wang Zhiwei, et al. CT Texture Analysis: A Potential Biomarker for Evaluating KRAS Mutational Status in Colorectal Cancer[J]. Chinese medical sciences journal, 2020, 35(4): 306-314. DOI： 10.24920/003770.

摘要

目的

纹理分析可以反映肉眼难以察觉到的肿瘤内异质性。本研究旨在评估CT纹理分析技术鉴别结直肠癌患者KRAS基因突变状态的可行性。

方法

回顾性纳入92例经病理证实且术前接受了腹部增强CT检查的结直肠癌患者。将患者分为训练集（

=51）和验证集（

=41）。使用TexRad纹理分析软件在选定的轴位CT图像上肿瘤区域放置感兴趣区

获得基于不同空间缩放因子（spatial scaling factor

SSF）的特征性纹理参数值

包括均值（mean）、标准差（SD）、熵值（entropy）、偏度值（skewness）、峰值（kurtosis）和正像素均值（mean of positive pixels

MPP）。比较训练集和验证集KRAS突变型患者和野生型患者的CT图像纹理参数值和临床特征（年龄

性别

肿瘤位置

组织病理学

肿瘤大小

TNM分期）。使用皮尔森相关系数计算所有纹理特征的相关性。若某两个纹理特征具有显着的相关性

则删掉较低曲线下面积（area under the curve

AUC）的特征值;纳入最具区分性的单一特征参数

并组合以训练多特征的支持向量机分类器。使用受试者工作特征曲线（receiver operating characteristic

ROC）法评估纹理参数对鉴别结直肠癌患者KRAS突变型与野生型的诊断效能。

结果

在训练集和验证集中

KRAS突变型与野生型患者两组之间的临床特征均无显着差异（

0.05）。预测结直肠癌患者KRAS突变的最佳模型包括6个纹理特征值

分别是平扫CT中SSF 5的偏度值、SSF 2的熵值、SSF 0的偏度值和峰度值

以及增强CT中SSF3的峰度值和均值。以此建立的诊断模型在训练集中诊断患者KRAS基因突变的曲线下面积为0.951（95%

：0.895~1

0.001）

当阈值为0.46时

诊断灵敏度为88.9%

特异度为91.7%。应用于验证集中的曲线下面积为0.995（95%

：0.982~1

0.001）

当阈值为0.28时

诊断KRAS突变的灵敏度和特异度分别为100%和93.7%。

结论

利用CT纹理分析技术评估结直肠癌患者KRAS突变状态是可行的。

Abstract

Objective

Texture analysis is deemed to reflect intratumor heterogeneity invisible to the naked eyes. The aim of this study was to evaluate the feasibility of assessing the KRAS mutational status in colorectal cancer (CRC) patients using CT texture analysis.

Methods

This retrospective study included 92 patients who had histopathologically confirmed CRC and underwent preoperative contrast-enhanced CT examinations. The patients were assigned into a training cohort (

=51) and a validation cohort (

=41). We placed the region of interest in the tumour regions on the selected axial images using software of TexRad to extract a series of quantitative parameters based on the spatial scaling factors (SSFs)

including mean

standard deviation (SD)

entropy

mean of positive pixels (MPP)

skewness

and kurtosis. The texture parameters and clinical characteristics (age

gender

tumour location

histopathology

tumour size

M stages) were compared between the mutated and wild-type KRAS patient groups in training cohort and validation cohort. Before building the multiple feature classifier

we calculated the correlations of the features using Pearson’s correlation coefficient

and if any two features were significantly correlated

the one with lower AUC was removed. Ultimately

only the most discriminative isolated features were combined to train a supporting vector machine (SVM) classifier. The receiver operating characteristic (ROC) curve was processed for evaluating the diagnostic efficiency of texture parameters in differentiating CRC patients with mutated KRAS from those with wild-type KRAS.

Results

None of the clinical characteristics were significant different between CRC patients with wild-type KRAS and mutated KRAS in both cohorts. For predicting the expression of mutated KRAS in CRC patients

the perfect model which combined skewness on SSF 5 by unenhanced CT

entropy on SSF 2

skewness and kurtosis on SSF 0

and kurtosis and mean on SSF 3 by enhanced CT

showed a desirable AUC of 0.951 (95%

: 0.895-1

0.001)

with a sensitivity of 88.9% and a specificity of 91.7%

when the cut-off value was 0.46 in the training cohort; while in the validation cohort

the AUC value was 0.995 (95%

: 0.982-1

0.001)

the sensitivity was 100%

and the specificity was 93.7% when the cut-off value was 0.28.

Conclusion

It is feasible to evaluate the KRAS mutational status in CRC using CT texture analysis.

关键词

Keywords

references

Bray F , Ferlay J , Soerjomataram I , et al . Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries . CA Cancer J Clin 2018 ; 68 ( 6 ): 394 - 424 . doi: 10.3322/caac.21492 10.3322/caac.21492 . DOI: 10.3322/caac.21492 http://doi.org/10.3322/caac.21492 https://www.ncbi.nlm.nih.gov/pubmed/30207593 https://www.ncbi.nlm.nih.gov/pubmed/30207593

Freeman HJ . Heterogeneity of colorectal adenomas, the serrated adenoma, and implications for screening and surveillance . World J Gastroenterol 2008 ; 14 ( 22 ): 3461 - 3 . doi: 10.3748/wjg.14.3461 10.3748/wjg.14.3461 . DOI: 10.3748/wjg.14.3461 http://doi.org/10.3748/wjg.14.3461 https://www.ncbi.nlm.nih.gov/pubmed/18567071 https://www.ncbi.nlm.nih.gov/pubmed/18567071

Yu GZ , Chen Y , Long YQ , et al . New insight into the key proteins and pathways involved in the metastasis of colorectal carcinoma . Oncol reports 2008 ; 19 ( 5 ): 1191 - 204 . doi: 10.3892/or.19.5.1191 10.3892/or.19.5.1191 .

Labianca R , Nordlinger B , Beretta GD , et al . Primary colon cancer: ESMO Clinical Practice Guidelines for diagnosis, adjuvant treatment and follow-up . Ann Oncol 2010 ; 21 ( Suppl 5 ): v70 - 7 . doi: 10.1093/annonc/mdq168 10.1093/annonc/mdq168 . DOI: 10.1093/annonc/mdq168 http://doi.org/10.1093/annonc/mdq168 https://linkinghub.elsevier.com/retrieve/pii/S0923753419396164 https://linkinghub.elsevier.com/retrieve/pii/S0923753419396164

Ulivi P , Capelli L , Valgiusti M , et al . Predictive role of multiple gene alterations in response to cetuximab in metastatic colorectal cancer: a single center study . J Translation Med 2012 ; 10 : 87 . doi: 10.1186/1479-5876-10-87 10.1186/1479-5876-10-87 . DOI: 10.1186/1479-5876-10-87 http://doi.org/10.1186/1479-5876-10-87 http://translational-medicine.biomedcentral.com/articles/10.1186/1479-5876-10-87 http://translational-medicine.biomedcentral.com/articles/10.1186/1479-5876-10-87

Berger MD , Stintzing S , Heinemann V , et al . Impact of genetic variations in the MAPK signaling pathway on outcome in metastatic colorectal cancer patients treated with first-line FOLFIRI and bevacizumab: data from FIRE-3 and TRIBE trials . Ann Oncol 2017 ; 28 ( 11 ): 2780 - 85 . doi: 10.1093/annonc/mdx412 10.1093/annonc/mdx412 . https://www.ncbi.nlm.nih.gov/pubmed/29045529 https://www.ncbi.nlm.nih.gov/pubmed/29045529

Baselga J . The EGFR as a target for anticancer therapy:focus on cetuximab . Eur J Cancer 2001 ; 37 ( Suppl 4 ): S16 - 22 . doi: 10.1016/s0959-8049(01)00233-7 10.1016/s0959-8049(01)00233-7 .

Napolitano S , Martini G , Martinelli E , et al . Therapeutic efficacy of SYM004, a mixture of two anti-EGFR antibodies in human colorectal cancer with acquired resistance to cetuximab and MET activation . Oncotarget 2017 ; 8 ( 40 ): 67592 - 604 . doi: 10.18632/oncotarget.18749 10.18632/oncotarget.18749 . DOI: 10.18632/oncotarget.18749 http://doi.org/10.18632/oncotarget.18749 https://www.ncbi.nlm.nih.gov/pubmed/28978055 https://www.ncbi.nlm.nih.gov/pubmed/28978055

Cremolini C , Schirripa M , Antoniotti C , et al . First-line chemotherapy for mCRC-a review and evidence-based algorithm . Nature Reviews Clin Oncol 2015 ; 12 ( 10 ): 607 - 19 . doi: 10.1038/nrclinonc.2015.129 10.1038/nrclinonc.2015.129 . DOI: 10.1038/nrclinonc.2015.129 http://doi.org/10.1038/nrclinonc.2015.129 https://doi.org/10.1038/nrclinonc.2015.129 https://doi.org/10.1038/nrclinonc.2015.129

Michl M , Stintzing S , Fischer von Weikersthal L , et al . CEA response is associated with tumor response and survival in patients with KRAS exon 2 wild-type and extended RAS wild-type metastatic colorectal cancer receiving first-line FOLFIRI plus cetuximab or bevacizumab (FIRE-3 trial) . Ann Oncol 2016 ; 27 ( 8 ): 1565 - 72 . doi: 10.1093/annonc/mdw222 10.1093/annonc/mdw222 . https://www.ncbi.nlm.nih.gov/pubmed/27234640 https://www.ncbi.nlm.nih.gov/pubmed/27234640

Tsujikawa T , Yamamoto M , Shono K , et al . Assessment of intratumor heterogeneity in mesenchymal uterine tumor by an (18)F-FDG PET/CT texture analysis . Ann Nucl Med 2017 ; 31 ( 10 ): 752 - 57 . doi: 10.1007/s12149-017-1208-x 10.1007/s12149-017-1208-x . https://www.ncbi.nlm.nih.gov/pubmed/28905201 https://www.ncbi.nlm.nih.gov/pubmed/28905201

Zhang GM , Shi B , Sun H , et al . Differentiating pheochromocytoma from lipid-poor adrenocortical adenoma by CT texture analysis: feasibility study . Abd Radiol 2017 ; 42 ( 9 ): 2305 - 13 . doi: 10.1007/s00261-017-1118-3 10.1007/s00261-017-1118-3 .

Liu S , Zheng H , Pan X , et al . Texture analysis of CT imaging for assessment of esophageal squamous cancer aggressiveness . J Thorac Dis 2017 ; 9 ( 11 ): 4724 - 32 . doi: 10.21037/jtd.2017.06.46 10.21037/jtd.2017.06.46 . https://www.ncbi.nlm.nih.gov/pubmed/29268543 https://www.ncbi.nlm.nih.gov/pubmed/29268543

Liu Y , Liu S , Qu F , et al . Tumor heterogeneity assessed by texture analysis on contrast-enhanced CT in lung adenocarcinoma: association with pathologic grade . Oncotarget 2017 ; 8 ( 32 ): 53664 - 74 . doi: 10.18632/oncotarget.15399 10.18632/oncotarget.15399 . DOI: 10.18632/oncotarget.15399 http://doi.org/10.18632/oncotarget.15399 https://www.ncbi.nlm.nih.gov/pubmed/28881840 https://www.ncbi.nlm.nih.gov/pubmed/28881840

Kim HS , Kim JH , Yoon YC , et al . Tumor spatial heterogeneity in myxoid-containing soft tissue using texture analysis of diffusion-weighted MRI . PLoS One 2017 ; 12 ( 7 ): e0181339 . doi: 10.1371/journal.pone.0181339 10.1371/journal.pone.0181339 . https://www.ncbi.nlm.nih.gov/pubmed/28708850 https://www.ncbi.nlm.nih.gov/pubmed/28708850

Craigie M , Squires J , Miles K . Can CT measures of tumour heterogeneity stratify risk for nodal metastasis in patients with non-small cell lung cancer? Clin Radiol 2017 ; 72 ( 10 ): 899.e1 - 9899.e7 . doi: 10.1016/j.crad.2017.04.013 10.1016/j.crad.2017.04.013 . DOI: 10.1016/j.crad.2017.04.013 http://doi.org/10.1016/j.crad.2017.04.013 https://linkinghub.elsevier.com/retrieve/pii/S000992601730168X https://linkinghub.elsevier.com/retrieve/pii/S000992601730168X

Miles KA , Ganeshan B , Rodriguez-Justo M , et al . Multifunctional imaging signature for V-KI-RAS2 Kirsten rat sarcoma viral oncogene homolog (KRAS) mutations in colorectal cancer . J Nucl Med 2014 ; 55 ( 3 ): 386 - 91 . doi: 10.2967/jnumed.113.120485 10.2967/jnumed.113.120485 . DOI: 10.2967/jnumed.113.120485 http://doi.org/10.2967/jnumed.113.120485 http://dx.doi.org/10.2967/jnumed.113.120485 http://dx.doi.org/10.2967/jnumed.113.120485

Ukweh ON , Ugbem TI , Okeke CM , et al . Value and diagnostic efficacy of fetal morphology assessment using ultrasound in a poor-resource setting . Diagnost 2019 ; 9 ( 3 ): 109 . doi: 10.3390/diagnostics9030109 10.3390/diagnostics9030109 . DOI: 10.3390/diagnostics9030109 http://doi.org/10.3390/diagnostics9030109 https://www.mdpi.com/2075-4418/9/3/109 https://www.mdpi.com/2075-4418/9/3/109

Feng C , Lu F , Shen Y , et al . Tumor heterogeneity in gastrointestinal stromal tumors of the small bowel: volumetric CT texture analysis as a potential biomarker for risk stratification . Cancer imaging 2018 ; 18 ( 1 ): 46 . doi: 10.1186/s40644-018-0182-4 10.1186/s40644-018-0182-4 . DOI: 10.1186/s40644-018-0182-4 http://doi.org/10.1186/s40644-018-0182-4 https://www.ncbi.nlm.nih.gov/pubmed/30518436 https://www.ncbi.nlm.nih.gov/pubmed/30518436

Lubner MG , Smith AD , Sandrasegaran K , et al . CT texture analysis: definitions, applications, biologic correlates, and challenges . Radiographics 2017 ; 37 ( 5 ): 1483 - 503 . doi: 10.1148/rg.2017170056 10.1148/rg.2017170056 . DOI: 10.1148/rg.2017170056 http://doi.org/10.1148/rg.2017170056 https://www.ncbi.nlm.nih.gov/pubmed/28898189 https://www.ncbi.nlm.nih.gov/pubmed/28898189

Weiss GJ , Ganeshan B , Miles KA , et al . Noninvasive image texture analysis differentiates K-ras mutation from pan-wildtype NSCLC and is prognostic . PLoS One 2014 ; 9 ( 7 ): e100244 . doi: 10.1371/journal.pone.0100244 10.1371/journal.pone.0100244 . DOI: 10.1371/journal.pone.0100244 http://doi.org/10.1371/journal.pone.0100244 https://www.ncbi.nlm.nih.gov/pubmed/24987838 https://www.ncbi.nlm.nih.gov/pubmed/24987838

Ba-Ssalamah A , Muin D , Schernthaner R , et al . Texture-based classification of different gastric tumors at contrast-enhanced CT . Eur J Radiol 2013 ; 82 ( 10 ): e537 - 43 . doi: 10.1016/j.ejrad.2013.06.024 10.1016/j.ejrad.2013.06.024 . DOI: 10.1016/j.ejrad.2013.06.024 http://doi.org/10.1016/j.ejrad.2013.06.024 http://dx.doi.org/10.1016/j.ejrad.2013.06.024 http://dx.doi.org/10.1016/j.ejrad.2013.06.024

Lubner MG , Stabo N , Lubner SJ , et al . CT textural analysis of hepatic metastatic colorectal cancer: pre-treatment tumor heterogeneity correlates with pathology and clinical outcomes . Abd Imaging 2015 ; 40 ( 7 ): 2331 - 7 . doi: 10.1007/s00261-015-0438-4 10.1007/s00261-015-0438-4 .

Beckers RCJ , Trebeschi S , Maas M , et al . CT texture analysis in colorectal liver metastases and the surrounding liver parenchyma and its potential as an imaging biomarker of disease aggressiveness, response and survival . Eur J Radiol 2018 ; 102 : 15 - 21 . doi: 10.1016/j.ejrad.2018.02.031 10.1016/j.ejrad.2018.02.031 . https://www.ncbi.nlm.nih.gov/pubmed/29685529 https://www.ncbi.nlm.nih.gov/pubmed/29685529

Lee SJ , Zea R , Kim DH , et al . CT texture features of liver parenchyma for predicting development of metastatic disease and overall survival in patients with colorectal cancer . Eur Radiol 2018 ; 28 ( 4 ): 1520 - 28 . doi: 10.1007/s00330-017-5111-6 10.1007/s00330-017-5111-6 . DOI: 10.1007/s00330-017-5111-6 http://doi.org/10.1007/s00330-017-5111-6 https://www.ncbi.nlm.nih.gov/pubmed/29164382 https://www.ncbi.nlm.nih.gov/pubmed/29164382

Chee CG , Kim YH , Lee KH , et al . CT texture analysis in patients with locally advanced rectal cancer treated with neoadjuvant chemoradiotherapy: A potential imaging biomarker for treatment response and prognosis . PLoS One 2017 ; 12 ( 8 ): e0182883 . doi: 10.1371/journal.pone.0182883 10.1371/journal.pone.0182883 . DOI: 10.1371/journal.pone.0182883 http://doi.org/10.1371/journal.pone.0182883 https://www.ncbi.nlm.nih.gov/pubmed/28797063 https://www.ncbi.nlm.nih.gov/pubmed/28797063

Lovinfosse P , Koopmansch B , Lambert F , et al . (18)F-FDG PET/CT imaging in rectal cancer: relationship with the RAS mutational status . Br J Radiol 2016 ; 89 ( 1063 ): 20160212 . doi: 10.1259/bjr.20160212 10.1259/bjr.20160212 . DOI: 10.1259/bjr.20160212 http://doi.org/10.1259/bjr.20160212 https://www.ncbi.nlm.nih.gov/pubmed/27146067 https://www.ncbi.nlm.nih.gov/pubmed/27146067

Miles KA , Ganeshan B , Rodriguez-Justo M , et al . Multifunctional imaging signature for V-KI-RAS2 Kirsten rat sarcoma viral oncogene homolog (KRAS) mutations in colorectal cancer . J Nucl Med 2014 ; 55 ( 3 ): 386 - 91 . doi: 10.2967/jnumed.113.120485 10.2967/jnumed.113.120485 . DOI: 10.2967/jnumed.113.120485 http://doi.org/10.2967/jnumed.113.120485 https://www.ncbi.nlm.nih.gov/pubmed/24516257 https://www.ncbi.nlm.nih.gov/pubmed/24516257

Chen SW , Chiang HC , Chen WT , et al . Correlation between PET/CT parameters and KRAS expression in colorectal cancer . Clin Nucl Med 2014 ; 39 ( 8 ): 685 - 9 . doi: 10.1097/rlu.0000000000000481 10.1097/rlu.0000000000000481 . https://www.ncbi.nlm.nih.gov/pubmed/24978328 https://www.ncbi.nlm.nih.gov/pubmed/24978328

Kawada K , Nakamoto Y , Kawada M , et al . Relationship between 18F-fluorodeoxyglucose accumulation and KRAS/BRAF mutations in colorectal cancer . Clin Cancer Res 2012 ; 18 ( 6 ): 1696 - 703 . doi: 10.1158/1078-0432.ccr-11-1909 10.1158/1078-0432.ccr-11-1909 . https://www.ncbi.nlm.nih.gov/pubmed/22282467 https://www.ncbi.nlm.nih.gov/pubmed/22282467

Kawada K , Toda K , Nakamoto Y , et al . Relationship between 18F-FDG PET/CT scans and KRAS mutations in metastatic colorectal cancer . J Nucl Med 2015 ; 56 ( 9 ): 1322 - 7 . doi: 10.2967/jnumed.115.160614 10.2967/jnumed.115.160614 . DOI: 10.2967/jnumed.115.160614 http://doi.org/10.2967/jnumed.115.160614 https://www.ncbi.nlm.nih.gov/pubmed/26135109 https://www.ncbi.nlm.nih.gov/pubmed/26135109

Yang L , Dong D , Fang M , et al . Can CT-based radiomics signature predict KRAS/NRAS/BRAF mutations in colorectal cancer? Eur Radiol 2018 ; 28 ( 5 ): 2058 - 67 . doi: 10.1007/s00330-017-5146-8 10.1007/s00330-017-5146-8 . DOI: 10.1007/s00330-017-5146-8 http://doi.org/10.1007/s00330-017-5146-8 https://www.ncbi.nlm.nih.gov/pubmed/29335867 https://www.ncbi.nlm.nih.gov/pubmed/29335867

浏览量

470

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

关联资源

Application and Progress of Texture Analysis in the Therapeutic Effect Prediction and Prognosis of Neoadjuvant Chemoradiotherapy for Colorectal Cancer

MRI Histogram Texture Feature Analysis of the Optic Nerve in the Patients with Optic Neuritis

Value of Texture Analysis of Intravoxel Incoherent Motion Parameters in Differential Diagnosis of Pancreatic Neuroendocrine Tumor and Pancreatic Adenocarcinoma

Differential Diagnostic Value of Texture Feature Analysis of Magnetic Resonance T2 Weighted Imaging between Glioblastoma and Primary Central Neural System Lymphoma

Value of Magnetic Resonance Imaging Texture Analysis in the Differential Diagnosis of Benign and Malignant Breast Tumors