Radiomic signature based on MR T2-weighted images for predicting KRAS mutation statue in rectal cancer
Li Dandan1, Cui Yanfen2, Yang Xiaotang2
1Department of Medical Imaging, Shanxi Medical University, Taiyuan 030000, China; 2Department of Radiology, Shanxi Province Tumor Hospital, Taiyuan 030000, China
Abstract:Objective To investigate the potential value of a radiomic signature based on T2-weighted images(T2WI) for predicting KRAS mutation statue in rectal cancer.Methods The clinical and imaging data of 304 patients with pathologically confirmed rectal cancers in the Shanxi Province Tumor Hospital from April 2017 to April 2019 were retrospectively analyzed (175 males and 129 females; median age, 59.6 years). All patients underwent KRAS mutation tests and pelvic MRI examination before operation. These patients were randomly divided into the primary cohort (n=213) and the validation cohort (n=91). T2WI images of each patient were selected for manual segmentation and radiomic feature extraction. Subsequently, univariate statistical tests were applied for feature selection in the primary cohort. The logistic regression (LR), decision tree (DT), and support vector machine (SVM) algorithms were applied to build a radiomic signature for KRAS prediction in the primary cohort. Meanwhile, the predictive performance of the radiomic signature was evaluated by receiver operating characteristics curve (ROC) analysis and then validated in the validation cohort. Finally, decision curve analysis (DCA) was performed to determine the clinical usefulness of the three radiomic models.Results No significant differences were found in the distribution of baseline data between the primary and validation cohorts and in the clinicopathological characteristics between the mutated and wild-type groups (all P values>0.05). A total of 960 features were extracted from the T2WI image of each patient. Seven radiomic features were selected after feature selection, which was significantly associated with KRAS mutations (all P values<0.05). The area under the ROC curve (AUC) values of the LR, DT, and SVM algorithms were 0.677, 0.604, and 0.722 in the primary cohort, respectively, and 0.626, 0.600, and 0.682 in the validation cohort, respectively. Among the three models, the SVM algorithm showed the best performance for evaluating KRAS mutation, which was validated in the validation cohort with AUCs, sensitivity, specificity, and accuracy of 0.682, 0.713, 0.655, and 0.681, respectively. The DCA curve shows that the three radiomic models have certain clinical benefits, among which the SVM prediction model has the largest net profit.Conclusions The radiomic signature based on T2WI exhibits potential for predicting KRAS mutation status in rectal cancer.
李丹丹, 崔艳芬, 杨晓棠. 基于MR T2加权成像的影像组学标签预测直肠癌KRAS基因突变的价值[J]. 中华解剖与临床杂志, 2021, 26(1): 7-14.
Li Dandan, Cui Yanfen, Yang Xiaotang. Radiomic signature based on MR T2-weighted images for predicting KRAS mutation statue in rectal cancer. Chinese Journal of Anatomy and Clinics, 2021, 26(1): 7-14.
Torre LA, Bray F, Siegel RL, et al. Global cancer statistics, 2012[J]. CA Cancer J Clin, 2015, 65(2): 87-108. DOI:10.3322/caac.21262.
[2]
Arnold M, Sierra MS, Laversanne M, et al. Global patterns and trends in colorectal cancer incidence and mortality[J]. Gut, 2017, 66(4): 683-691. DOI:10.1136/gutjnl-2015-310912.
[3]
Bokemeyer C, Köhne CH, Ciardiello F, et al. FOLFOX4 plus cetuximab treatment and RAS mutations in colorectal cancer[J]. Eur J Cancer, 2015, 51(10): 1243-1252. DOI:10.1016/j.ejca.2015.04.007.
[4]
De Roock W, Claes B, Bernasconi D, et al. 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[J]. Lancet Oncol, 2010, 11(8): 753-762. DOI:10.1016/S1470-2045(10)70130-3.
[5]
Karapetis CS, Khambata-Ford S, Jonker DJ, et al. K-ras mutations and benefit from cetuximab in advanced colorectal cancer[J]. N Engl J Med, 2008, 359(17): 1757-1765. DOI:10.1056/NEJMoa0804385.
[6]
Lièvre A, Bachet JB, Boige V, et al. KRAS mutations as an independent prognostic factor in patients with advanced colorectal cancer treated with cetuximab[J]. J Clin Oncol, 2008, 26(3): 374-379. DOI:10.1200/JCO.2007.12.5906.
[7]
Allegra CJ, Rumble RB, Hamilton SR, et al. Extended RAS gene mutation testing in metastatic colorectal carcinoma to predict response to anti-epidermal growth factor receptor monoclonal antibody therapy: American Society of Clinical Oncology provisional clinical opinion update 2015[J]. J Clin Oncol, 2016, 34(2): 179-185. DOI:10.1200/JCO.2015.63.9674.
[8]
Watanabe T, Kobunai T, Yamamoto Y, et al. Heterogeneity of KRAS status may explain the subset of discordant KRAS status between primary and metastatic colorectal cancer[J]. Dis Colon Rectum, 2011, 54(9): 1170-1178. DOI:10.1097/DCR.0b013e31821d37a3.
[9]
Sundström M, Edlund K, Lindell M, et al. KRAS analysis in colorectal carcinoma: analytical aspects of pyrosequencing and allele-specific PCR in clinical practice[J]. BMC Cancer, 2010, 10: 660. DOI:10.1186/1471-2407-10-660.
[10]
Lambin P, Rios-Velazquez E, Leijenaar R, et al. Radiomics: extracting more information from medical images using advanced feature analysis[J]. Eur J Cancer, 2012, 48(4): 441-446. DOI:10.1016/j.ejca.2011.11.036.
[11]
Zhou X, Yi Y, Liu Z, et al. Radiomics-based pretherapeutic prediction of non-response to neoadjuvant therapy in locally advanced rectal cancer[J]. Ann Surg Oncol, 2019, 26(6): 1676-1684. DOI:10.1245/s10434-019-07300-3.
[12]
Liang M, Cai Z, Zhang H, et al. Machine learning-based analysis of rectal cancer mri radiomics for prediction of metachronous liver metastasis[J]. Acad Radiol, 2019, 26(11): 1495-1504. DOI:10.1016/j.acra.2018.12.019.
[13]
van Griethuysen J, Fedorov A, Parmar C, et al. Computational radiomics system to decode the radiographic phenotype[J]. Cancer Res, 2017, 77(21): e104-104e107. DOI:10.1158/0008-5472.CAN-17-0339.
[14]
Kramer AA, Zimmerman JE. Assessing the calibration of mortality benchmarks in critical care: the Hosmer-Lemeshow test revisited[J]. Crit Care Med, 2007, 35(9): 2052-2056. DOI:10.1097/01.CCM.0000275267.64078.B0.
[15]
Lovinfosse P, Koopmansch B, Lambert F, et al. (18)F-FDG PET/CT imaging in rectal cancer: relationship with the RAS mutational status[J]. Br J Radiol, 2016, 89(1063): 20160212. DOI:10.1259/bjr.20160212.
[16]
Kim SJ, Pak K, Kim K. Diagnostic performance of F-18 FDG PET/CT for prediction of KRAS mutation in colorectal cancer patients: a systematic review and meta-analysis[J]. Abdom Radiol (NY), 2019, 44(5): 1703-1711. DOI:10.1007/s00261-018-01891-3.
[17]
Shin YR, Kim KA, Im S, et al. Prediction of KRAS mutation in rectal cancer using MRI[J]. Anticancer Res, 2016, 36(9): 4799-4804. DOI:10.21873/anticanres.11039.
[18]
Liu Y, Kim J, Balagurunathan Y, et al. Radiomic features are associated with egfr mutation status in lung adenocarcinomas[J]. Clin Lung Cancer, 2016, 17(5): 441-448.e6. DOI:10.1016/j.cllc.2016.02.001.
[19]
Ma W, Zhao Y, Ji Y, et al. Breast cancer molecular subtype prediction by mammographic radiomic features[J]. Acad Radiol, 2019, 26(2): 196-201. DOI:10.1016/j.acra.2018.01.023.
[20]
Yang L, Dong D, Fang M, et al. Can CT-based radiomics signature predict KRAS/NRAS/BRAF mutations in colorectal cancer?[J]. Eur Radiol, 2018, 28(5): 2058-2067. DOI:10.1007/s00330-017-5146-8.
[21]
Huang YQ, Liang CH, He L, et al. Development and validation of a radiomics nomogram for preoperative prediction of lymph node metastasis in colorectal cancer[J]. J Clin Oncol, 2016, 34(18): 2157-2164. DOI:10.1200/JCO.2015.65.9128.
[22]
Oh JE, Kim MJ, Lee J, et al. Magnetic resonance-based texture analysis differentiating KRAS mutation status in rectal cancer[J]. Cancer Res Treat, 2020, 52(1): 51-59. DOI:10.4143/crt.2019.050.