European Radiology

, Volume 28, Issue 5, pp 2058–2067 | Cite as

Can CT-based radiomics signature predict KRAS/NRAS/BRAF mutations in colorectal cancer?

  • Lei Yang
  • Di DongEmail author
  • Mengjie Fang
  • Yongbei Zhu
  • Yali Zang
  • Zhenyu Liu
  • Hongmei Zhang
  • Jianming Ying
  • Xinming ZhaoEmail author
  • Jie TianEmail author



To investigate whether CT-based radiomics signature can predict KRAS/NRAS/BRAF mutations in colorectal cancer (CRC).


This retrospective study consisted of a primary cohort (n = 61) and a validation cohort (n = 56) with pathologically confirmed CRC. Patients underwent KRAS/NRAS/BRAF mutation tests and contrast-enhanced CT before treatment. A total of 346 radiomics features were extracted from portal venous-phase CT images of the entire primary tumour. Associations between the genetic mutations and clinical background, tumour staging, and histological differentiation were assessed using univariate analysis. RELIEFF and support vector machine methods were performed to select key features and build a radiomics signature.


The radiomics signature was significantly associated with KRAS/NRAS/BRAF mutations (P < 0.001). The area under the curve, sensitivity, and specificity for predicting KRAS/NRAS/BRAF mutations were 0.869, 0.757, and 0.833 in the primary cohort, respectively, while they were 0.829, 0.686, and 0.857 in the validation cohort, respectively. Clinical background, tumour staging, and histological differentiation were not associated with KRAS/NRAS/BRAF mutations in both cohorts (P>0.05).


The proposed CT-based radiomics signature is associated with KRAS/NRAS/BRAF mutations. CT may be useful for analysis of tumour genotype in CRC and thus helpful to determine therapeutic strategies.

Key Points

Key features were extracted from CT images of the primary colorectal tumour.

The proposed radiomics signature was significantly associated with KRAS/NRAS/BRAF mutations.

In the primary cohort, the proposed radiomics signature predicted mutations.

Clinical background, tumour staging, and histological differentiation were unable to predict mutations.


Colorectal neoplasms Adenocarcinoma Mutation Diagnostic imaging ROC curve 

Abbreviations and Acronyms


Alpha fetoprotein


Area under curve


Carbohydrate antigen 199


Carbohydrate antigen 242


Carbohydrate antigen 724


Carcinoembryonic antigen


Confidence interval


Colorectal cancer


Computed tomography


Epidermal growth factor receptor


Positron emession tomography/computerd tomography with 18F-fluorodexyglucose


Formalin-fixed paraffin- embedded


Gray-level co-occurrence matrix


Gray-level run-length matrix


Intra-/inter-class correlation coefficients


Nationgal comprehensive cancer network


Next-generation sequencing


Odds ratio


Picture archiving and communication system


Receiver operating characteristic


Standardized uptake value


Tissue polypeptide specific antigen





This study has received funding by the National Natural Science Foundation of China (grant numbers 81227901, 81771924, 61231004, 81501616, 81671851, 81527805, 81501549, 81671829 and 81671757), the National Key R&D Program of China (grant numbers 2017YFA0205200, 2017YFC1308700, 2017YFC1309100, and 2017YFC1308701), the Science and Technology Service Network Initiative of the Chinese Academy of Sciences (grant number KFJ-SW-STS-160), the Instrument Developing Project (grant number YZ201502), the Beijing Municipal Science and Technology Commission (grant number Z161100002616022), and the Youth Innovation Promotion Association CAS.

Compliance with ethical standards


The scientific guarantor of this publication is Jie Tian.

Conflict of interest

The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.

Statistics and biometry

No complex statistical methods were necessary for this paper.

Informed consent

Written informed consent was waived in this study.

Ethical approval

Institutional Review Board approval was obtained.


• retrospective

• diagnostic experimental

• performed at one institution

Supplementary material

330_2017_5146_MOESM1_ESM.docx (555 kb)
ESM 1 (DOCX 555 kb)


  1. 1.
    van de Velde CJ, Boelens PG, Borras JM et al (2014) EURECCA colorectal: multidisciplinary management: European consensus conference colon & rectum. Eur J Cancer 50:1.e1–1.e34CrossRefGoogle Scholar
  2. 2.
    Cremolini C, Loupakis F, Antoniotti C et al (2015) FOLFOXIRI plus bevacizumab versus FOLFIRI plus bevacizumab as first-line treatment of patients with metastatic colorectal cancer: updated overall survival and molecular subgroup analyses of the open-label, phase 3 TRIBE study. Lancet Oncol 16:1306–1315CrossRefPubMedGoogle Scholar
  3. 3.
    Strickler JH, Wu C, Bekaii-Saab T (2017) Targeting BRAF in metastatic colorectal cancer: maximizing molecular approaches. Cancer Treat Rev 60:109–119CrossRefPubMedGoogle Scholar
  4. 4.
    Sundar R, Hong DS, Kopetz S, Yap TA (2017) Targeting BRAF-mutant colorectal cancer: progress in combination strategies. Cancer Discov 7:558–560CrossRefPubMedGoogle Scholar
  5. 5.
    De Roock W, Claes B, Bernasconi D et al (2010) Effects of KRAS, BRAF, NRAS, and PIK3CA mutations on the efficacy of cetuximab plus chemotherapy in chemotherapy-refractory metastatic colorectal cancer: a retrospective consortium analysis. Lancet Oncol 11:753–762CrossRefPubMedGoogle Scholar
  6. 6.
    Van Cutsem E, Lenz HJ, Köhne CH et al (2015) Fluorouracil, leucovorin, and irinotecan plus cetuximab treatment and RAS mutations in colorectal cancer. J Clin Oncol 33:692–700CrossRefPubMedGoogle Scholar
  7. 7.
    Peeters M, Oliner KS, Price TJ et al (2015) Analysis of KRAS/NRAS mutations in a phase III study of panitumumab with FOLFIRI compared with FOLFIRI alone as second-line treatment for metastatic colorectal cancer. Clin Cancer Res 21:5469–5479CrossRefPubMedGoogle Scholar
  8. 8.
    Barras D, Missiaglia E, Wirapati P et al (2017) BRAF V600E mutant colorectal cancer subtypes based on gene expression. Clin Cancer Res 23:104–115CrossRefPubMedGoogle Scholar
  9. 9.
    Douillard JY, Oliner KS, Siena S et al (2013) Panitumumab-FOLFOX4 treatment and RAS mutations in colorectal cancer. N Engl J Med 369:1023–1034CrossRefPubMedGoogle Scholar
  10. 10.
    Tabernero J, Lenz HJ, Siena S et al (2015) Analysis of circulating DNA and protein biomarkers to predict the clinical activity of regorafenib and assess prognosis in patients with metastatic colorectal cancer: a retrospective, exploratory analysis of the CORRECT trial. Lancet Oncol 16: 937-948.Google Scholar
  11. 11.
    Lubner MG, Stabo N, Lubner SJ et al (2015) CT textural analysis of hepatic metastatic colorectal cancer: pre-treatment tumour heterogeneity correlates with pathology and clinical outcomes. Abdom Imaging 40:2331–2337CrossRefPubMedGoogle Scholar
  12. 12.
    Kawada K, Nakamoto Y, Kawada M et al (2012) Relationship between 18F-fluorodeoxyglucose accumulation and KRAS/BRAF mutations in colorectal cancer. Clin Cancer Res 18:1696–1703CrossRefPubMedGoogle Scholar
  13. 13.
    Miles KA, Ganeshan B, Rodriguez-Justo M et al (2014) Multifunctional imaging signature for V-KI-RAS2 Kirsten rat sarcoma viral oncogene homolog (KRAS) mutations in colorectal cancer. J Nucl Med 55:386–391CrossRefPubMedGoogle Scholar
  14. 14.
    Kawada K, Toda K, Nakamoto Y et al (2015) Relationship between 18F-FDG PET/CT scans and KRAS mutations in metastatic colorectal cancer. J Nucl Med 56:1322–1327CrossRefPubMedGoogle Scholar
  15. 15.
    Chen SW, Chiang HC, Chen WT et al (2014) Correlation between PET/CT parameters and KRAS expression in colorectal cancer. Clin Nucl Med 39:685–689CrossRefPubMedGoogle Scholar
  16. 16.
    Lovinfosse P, Koopmansch B, Lambert F et al (2016) 18 F-FDG PET/CT imaging in rectal cancer: relationship with the RAS mutational status. Br J Radiol 89:20160212CrossRefPubMedPubMedCentralGoogle Scholar
  17. 17.
    Krikelis D, Skoura E, Kotoula V et al (2014) Lack of association between KRAS mutations and 18F-FDG PET/CT in Caucasian metastatic colorectal cancer patients. Anticancer Res 34:2571–2579PubMedGoogle Scholar
  18. 18.
    Huang YQ, Liang CH, He L et al (2016) Development and Validation of a Radiomics Nomogram for Preoperative Prediction of Lymph Node Metastasis in Colorectal Cancer. J Clin Oncol 34:2157–2164CrossRefPubMedGoogle Scholar
  19. 19.
    Nie K, Shi L, Chen Q et al (2016) Rectal cancer: assessment of neoadjuvant chemoradiation outcome based on radiomics of multiparametric MRI. Clin Cancer Res 22:5256–5264CrossRefPubMedGoogle Scholar
  20. 20.
    Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278:563–577CrossRefPubMedGoogle Scholar
  21. 21.
    Zhang B, Tian J, Dong D et al (2017) Radiomics features of multiparametric MRI as novel prognostic factors in advanced nasopharyngeal carcinoma. Clin Cancer Res 23:4259–4269CrossRefPubMedGoogle Scholar
  22. 22.
    Coroller TP, Grossmann P, Hou Y et al (2015) CT-based radiomic signature predicts distant metastasis in lung adenocarcinoma. Radiother Oncol 114:345–350CrossRefPubMedPubMedCentralGoogle Scholar
  23. 23.
    Vallières M, Kay-Rivest E, Perrin LJ (2017) Radiomics strategies for risk assessment of tumour failure in head-and-neck cancer. Sci Rep 7:10117CrossRefPubMedPubMedCentralGoogle Scholar
  24. 24.
    Liu Z, Zhang XY, Shi YJ et al (2017) Radiomics analysis for evaluation of pathological complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer. Clin Cancer Res.
  25. 25.
    Aerts HJ, Velazquez ER, Leijenaar RT et al (2014) Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun 5:4006PubMedPubMedCentralGoogle Scholar
  26. 26.
    Boonstra K, Weersma RK, van Erpecum KJ, Rauws EA, Spanier BW, Poen AC (2013) Population-based epidemiology, malignancy risk, and outcomeof primary sclerosing cholangitis. Hepatology 58:2045–2055CrossRefPubMedGoogle Scholar
  27. 27.
    Reyes O, Morell C, Ventura S (2015) Scalable extensions of the ReliefF algorithm for weighting and selecting features on the multi-label learning context. Neurocomputing 161:168–182CrossRefGoogle Scholar
  28. 28.
    Vandenberghe R, Nelissen N, Salmon E et al (2013) Binary classification of 18 F-flutemetamol PET using machine learning: comparison with visual reads and structural MRI. Neuroimage 64:517–525CrossRefPubMedGoogle Scholar
  29. 29.
    Roffo G, Melzi S, Cristani M (2015) Infinite feature selection. Proceedings of the IEEE International Conference on Computer Vision 4202–4210Google Scholar
  30. 30.
    Liu S, Liu S, Ji C et al (2017) Application of CT texture analysis in predicting histopathological characteristics of gastric cancers. Eur Radiol.
  31. 31.
    Shiri I, Rahmim A, Ghaffarian P, Geramifar P, Abdollahi H, Bitarafan-Rajabi A (2017) The impact of image reconstruction settings on 18F-FDG PET radiomic features: multi-scanner phantom and patient studies. Eur Radiol.
  32. 32.
    Baldus SE, Schaefer KL, Engers R, Hartleb D, Stoecklein NH, Gabbert HE (2010) Prevalence and heterogeneity of KRAS, BRAF, and PIK3CA mutations in primary colorectal adenocarcinomas and their corresponding metastases. Clin Cancer Res 16:790–799CrossRefPubMedGoogle Scholar
  33. 33.
    Esteva A, Kuprel B, Novoa RA et al (2017) Dermatologist-level classification of skin cancer with deepneural networks. Nature 542:115–118CrossRefPubMedGoogle Scholar
  34. 34.
    Anthimopoulos M, Christodoulidis S, Ebner L, Christe A, Mougiakakou S (2016) Lung pattern classification for interstitial lung diseases using a deep convolutional neural network. IEEE Trans Med Imaging 35:1207–1216CrossRefPubMedGoogle Scholar
  35. 35.
    Emblem KE, Pinho MC, Zöllner FG et al (2015) A generic support vector machine model for preoperative glioma survival associations. Radiology 275:228–234CrossRefPubMedGoogle Scholar

Copyright information

© European Society of Radiology 2018

Authors and Affiliations

  1. 1.Department of Diagnostic RadiologyNational Cancer Center/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical CollegeBeijingChina
  2. 2.CAS Key Laboratory of Molecular Imaging, Institute of AutomationChinese Academy of SciencesBeijingChina
  3. 3.University of Chinese Academy of SciencesBeijingChina
  4. 4.Beijing Key Lab of Molecular ImagingBeijingChina
  5. 5.Department of PathologyNational Cancer Center/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical CollegeBeijingChina
  6. 6.The State Key Laboratory of Management and Control for Complex Systems, Institute of AutomationChinese Academy of SciencesBeijingChina

Personalised recommendations