Image modality | Number of patients | Cancer | Target | Number of radiomics features | Commercial or open-source software | Method | References |
---|---|---|---|---|---|---|---|
CT | 188 | HNSCC | Cancer recurrence rate | 107 | PyRadiomics, 3D Slicer, Matlab | ML: LOOCV SM: Chi-square test DL: Deep learning artificial neural networks | [28] |
FDG-PET | 174 | OPC | The risk of local failure | 2–3 | Matlab, Stata/MP | ML: LOOCV, Cox proportional-hazards regression, Fine and Gray’s proportional sub-hazards model, LR, fivefold CV SM: Kaplan–Meier analysis, log-rank test, Spearman correlation analysis | [29] |
CT | 465 | OPC | Local recurrence | 2 | Matlab | ML: Bootstrap resampled recursive partitioning analysis, Regression model, DT, Cox proportional hazards model SM: Log-rank and Wilcoxon test, Effect likelihood ratio test, Wald test | [36] |
MRI | 285 | HNSCC | Local tumor recurrence | 20 | MITK, SPM, Matlab, R | ML: LASSO, tenfold CV SM: t-test, Chi-square test or Fisher’s exact test, Delong test, Spearman correlation analysis | [37] |
US | 83 | Breast cancer | Recurrence | 4 | Matlab, SPSS | ML: KNN, SVM SM: Shapiro–Wilk test, t-test, Mann–Whitney test, Kaplan–Meier product-limit method | [38] |