Radiomics-based prediction of microsatellite instability in colorectal cancer at initial computed tomography evaluation
- 53 Downloads
To predict microsatellite instability (MSI) status of colon cancer on preoperative CT imaging using radiomic analysis.
This retrospective study involved radiomic analysis of preoperative CT imaging of patients who underwent resection of stage II–III colon cancer from 2004 to 2012. A radiologist blinded to MSI status manually segmented the tumor region on CT images. 254 Intensity-based radiomic features were extracted from the tumor region. Three prediction models were developed with (1) only clinical features, (2) only radiomic features, and (3) “combined” clinical and radiomic features. Patients were randomly separated into training (n = 139) and test (n = 59) sets. The model was constructed from training data only; the test set was reserved for validation only. Model performance was evaluated using AUC, sensitivity, specificity, PPV, and NPV.
Of the total 198 patients, 134 (68%) patients had microsatellite stable tumors and 64 (32%) patients had MSI tumors. The combined model performed slightly better than the other models, predicting MSI with an AUC of 0.80 for the training set and 0.79 for the test set (specificity = 96.8% and 92.5%, respectively), whereas the model with only clinical features achieved an AUC of 0.74 and the model with only radiomic features achieved an AUC of 0.76. The model with clinical features alone had the lowest specificity (70%) compared with the model with radiomic features alone (95%) and the combined model (92.5%).
Preoperative prediction of MSI status via radiomic analysis of preoperative CT adds specificity to clinical assessment and could contribute to personalized treatment selection.
KeywordsColon Colonic neoplasms Microsatellite repeats Microsatellite instability Immunotherapy
The authors thank Joanne Chin, MFA, for her editorial support of this article. This study has received funding from NIH/NCI P30 CA008748 Cancer Center Support Grant and the Colorectal Cancer Research Center CC50367 at Memorial Sloan Kettering.
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
All procedures performed in studies involving human participants were in accordance with the Ethical Standards of the Institutional Committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards. This article does not contain any studies with animals performed by any of the authors.
Written informed consent was waived by the Institutional Review Board.
- 7.American Cancer Society American Cancer Society Guideline for Colorectal Cancer Screening. Available via https://www.cancer.org/cancer/colon-rectal-cancer/detection-diagnosis-staging/acs-recommendations.html. Accessed November 1, 2018
- 9.Kurogochi T, Honda M, Yamashita K et al (2018) Safety and efficacy of preoperative chemotherapy followed by esophagectomy versus upfront surgery for resectable esophageal squamous cell carcinoma. Surg Today. https://doi.org/10.1007/s00595-018-1718-8
- 10.Hosoda K, Azuma M, Katada C et al (2018) A phase II study of neoadjuvant chemotherapy with docetaxel, cisplatin, and S-1, followed by gastrectomy with D2 lymph node dissection for high-risk advanced gastric cancer: results of the KDOG1001 trial. Gastric Cancer. https://doi.org/10.1007/s10120-018-0884-0
- 17.Middha S, Zhang L, Nafa K et al (2017) Reliable Pan-Cancer Microsatellite Instability Assessment by Using Targeted Next-Generation Sequencing Data. JCO Precision Oncology. https://doi.org/10.1200/po.17.00084:1-17
- 18.Haralick RM, Shanmugam K, Dinstein I (1973) Textural Features for Image Classification. IEEE Transactions on Systems, Man, and Cybernetics SMC-3:610–621Google Scholar
- 22.Mehta R, Egiazarian K (2013) Rotated Local Binary Pattern (RLBP): Rotation invariant texture descriptorInternational Conference on Pattern Recognition Applications and Methods. Institute of Electrical and Electronics Engineers IEEE, Barcelona, Spain, pp 497–502Google Scholar
- 24.Costa AF, Humpire-Mamani G, Traina AJM (2012) An Efficient Algorithm for Fractal Analysis of Textures2012 25th SIBGRAPI Conference on Graphics, Patterns and Images, Ouro Preto, Brazil, pp 39–46Google Scholar
- 26.Chakraborty J, Rangayyan RM, Banik S, Mukhopadhyay S, Desautels JL (2012) Detection of architectural distortion in prior mammograms using statistical measures of orientation of textureMedical Imaging 2012: Computer-Aided Diagnosis. International Society for Optics and Photonics, pp 831521Google Scholar
- 27.Attiyeh MA, Chakraborty J, Gazit L et al (2018) Preoperative risk prediction for intraductal papillary mucinous neoplasms by quantitative CT image analysis. HPB (Oxford). https://doi.org/10.1016/j.hpb.2018.07.016
- 29.Biau G (2012) Analysis of a Random Forests Model. Journal of Machine Learning Research 12:1063–1095Google Scholar
- 32.Gado A, Ebeid B, Abdelmohsen A, Axon A (2011) Improving the Yield of Histological Sampling in Patients With Suspected Colorectal Cancer During Colonoscopy by Introducing a Colonoscopy Quality Assurance Program. Gastroenterology Res 4:157–161Google Scholar
- 33.Perrin T, Midya A, Yamashita R et al (2018) Short-term reproducibility of radiomic features in liver parenchyma and liver malignancies on contrast-enhanced CT imaging. Abdom Radiol (NY). https://doi.org/10.1007/s00261-018-1600-6
- 34.National Comprehensive Cancer Network (NCCN) (2018) NCCN Clinical Practice Guidelines in Oncology (NCCN guidelines): Colon Cancer. Version 4.2018. Available via https://www.nccn.org/professionals/physician_gls/pdf/colon.pdf. Accessed December 7, 2018