Radiomic Machine-Learning Classifiers for Prognostic Biomarkers of Advanced Nasopharyngeal Carcinoma

• Published in: Cancer letters Vol. 403; pp. 21 - 27
• Main Authors: Zhang, Bin, He, Xin, Ouyang, Fusheng, Gu, Dongsheng, Dong, Yuhao, Zhang, Lu, Mo, Xiaokai, Huang, Wenhui, Tian, Jie, Zhang, Shuixing
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 10.09.2017; Elsevier Limited
• Subjects: Algorithms; Area Under Curve; Biomarkers; Carcinoma - diagnostic imaging; Carcinoma - pathology; Carcinoma - therapy; Classification; Clinical decision making; Decision making; Decision Support Techniques; Diagnosis, Computer-Assisted - methods; Gene expression; Genotype & phenotype; Hematology, Oncology and Palliative Medicine; High-Throughput Screening Assays; Histology; Humans; Image Interpretation, Computer-Assisted - methods; Imaging; Learning algorithms; Linear Models; Lung cancer; Machine learning; Machinery; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Medical imaging; Medical prognosis; Nasopharyngeal Carcinoma; Nasopharyngeal Neoplasms - diagnostic imaging; Nasopharyngeal Neoplasms - pathology; Nasopharyngeal Neoplasms - therapy; Oncology; Patients; Precision medicine; Predictive Value of Tests; Radiation therapy; Radiomics; Reproducibility of Results; Risk Assessment; Risk Factors; ROC Curve; Support Vector Machine; Throat cancer; Treatment Failure; NPC; Adaptive Boosting; L 1-LOG; LDA; KNN; Linear Support Vector Machines; Radiomics; AUC; Random Forest; Nasopharyngeal carcinoma; SD; Imaging; Standard deviation; Linear discriminant analysis; PFS; L 1-Logistic Regression; LSVM; EN-LOG; K-nearest neighborhood; L 1-SVM; L 1-Support Vector Machine; Nnet; Distance Correlation; Area under the receiver operating characteristic curve; AdaBoost; Neural Network; Naive Bayes; RF; L 2-Logistic Regression; NB; Sure Independence Screening; SIS; KSVM; Machine-learning; Progression-free survival; Kernel Support Vector Machines; DC; Elastic Net Logistic Regression; L 2-LOG; L1-LOG; L1-SVM; L2-LOG
• ISSN: 0304-3835; 1872-7980
• DOI: 10.1016/j.canlet.2017.06.004

Abstract We aimed to identify optimal machine-learning methods for radiomics-based prediction of local failure and distant failure in advanced nasopharyngeal carcinoma (NPC). We enrolled 110 patients with advanced NPC. A total of 970 radiomic features were extracted from MRI images for each patient. Six feature selection methods and nine classification methods were evaluated in terms of their performance. We applied the 10-fold cross-validation as the criterion for feature selection and classification. We repeated each combination for 50 times to obtain the mean area under the curve (AUC) and test error. We observed that the combination methods Random Forest (RF) + RF (AUC, 0.8464 ± 0.0069; test error, 0.3135 ± 0.0088) had the highest prognostic performance, followed by RF + Adaptive Boosting (AdaBoost) (AUC, 0.8204 ± 0.0095; test error, 0.3384 ± 0.0097), and Sure Independence Screening (SIS) + Linear Support Vector Machines (LSVM) (AUC, 0.7883 ± 0.0096; test error, 0.3985 ± 0.0100). Our radiomics study identified optimal machine-learning methods for the radiomics-based prediction of local failure and distant failure in advanced NPC, which could enhance the applications of radiomics in precision oncology and clinical practice.