Table 4.
Applications of radiomics-based survival prediction
| Image modality | Number of patients | Cancer | Target | Number of radiomics features | Commercial or open-source software | Method | References |
|---|---|---|---|---|---|---|---|
| CT | 878 | Lung cancer and HNSCC | Patient survival | Unspecified | Matlab, R |
ML: LR, Consensus clustering, Hierarchical clustering SM: Jaccard index, Pearson correlation analysis |
[15] |
| CT | 188 | HNSCC | The death prognosis | 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 ACM | 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] |
| PET, CT, PET/CT | 311 | Oropharyngeal squamous cell carcinoma | PFS, OS | Unspecified | 3D Slicer, PyRadiomics, R, ggplot2 |
ML: Random survival forest, Threefold stratified CV SM: t-test, Kaplan–Meier analysis, log-rank test, C-index |
[30] |
| CT | 44 | Laryngeal and hypo-pharyngeal cancers | DFS | 26 | Perfusion-4, ROCKIT |
ML: Two-loop leave-one-out, Linear discriminant analysis SM: t-test, ICC, Kappa analysis |
[31] |
| MRI | 136 | EBV-related NPC | OS | 2 | Matlab, 3D Slicer, PyRadiomics |
ML: Cox regression model, tenfold CV SM: Kaplan–Meier analysis, log-rank test, Mann–Whitney test or Spearman correlation analysis, ICC |
[32] |
| MRI | 504 | NPC | Long-term survival | 17 | AccuContour, PyRadiomics, X-tile, R |
ML: LASSO, Cox regression model, tenfold CV SM: Mann–Whitney U test or t-test, Kaplan–Meier analyses, log-rank test, Hosmer–Lemeshow test, C-index |
[33] |
| MRI | 236 | Tongue cancer | DFS, OS | 15/17/18/25/10 | ITK-SNAP, AIMT, Python, R, SPSS |
ML: PCA, SVM, Cox regression analysis, fivefold CV SM: DeLong test, Spearman correlation analysis, Kaplan–Meier analysis, log-rank test, ICC |
[34] |
| MRI | 346 | Rectal cancer | 3-year recurrence-free survival | 4/5/10 | GE Healthcare, 3D Slicer, R, SPSS |
ML: LASSO, LR, Cox analysis SM: ICC, Wilcoxon test, Hosmer–Lemeshow test, t-test, Nonparametric test, Chi-square test and Fisher’s exact test, DeLong test |
[35] |
CT computed tomography, MRI magnetic resonance imaging, FDG fluorodeoxyglucose, PET positron emission tomography, ML machine learning, SM statistical method, DL deep learning, HNSCC head and neck squamous cell carcinoma, OPC oropharyngeal cancer, NPC nasopharyngeal carcinoma, ACM all-cause mortality, PFS progression-free survival, OS overall survival, DFS disease-free survival, LR logistic regression, LOOCV leave one out cross validation, CV cross validation, ICC intraclass correlation coefficients, LASSO least absolute shrinkage and selection operator, PCA principal component analysis, SVM support vector machine