Table 6.
Summary of representative studies on 18F-FDG PET/CT radiomics-based machine learning analyses in gynecological tumors
| Authors | Years | Tumor type | Aim | Sample size | Constructed ML models | Core ML algorithm | Best ML model | Validation | Resultsa |
|---|---|---|---|---|---|---|---|---|---|
| Predicting tumor stage | |||||||||
| Lucia et al. [118] | 2023 | Cervical cancer | LNM | n = 178 |
Clinical model PET radiomics-based model Combined clinical and PET radiomics-based model Combat PET radiomics-based model Combined clinical and combat PET radiomics-based model |
Neural network | Combat PET-radiomics model | Training and validation cohorts | AUC: 0.96 |
| Zhang et al. [119] | 2022 | Cervical cancer |
COX-2 status N status |
n = 148 | PET radiomics-based model alone | LASSO + LR | – | Training and validation cohorts |
AUC for COX-2: 0.814 AUC for LNM: 0.817 |
| Li et al. [120] | 2021 | Cervical cancer | LVSI | n = 112 | PET radiomics-based model alone | LASSO + LR | – | Training and validation cohorts | AUC: 0.806 |
| Chong et al. [121] | 2021 | Cervical cancer | ITB | n = 76 | PET radiomics-based model alone | LASSO + SVM | – | Training and validation cohorts | AUC: 0.784 |
| Predicting treatment response or survival | |||||||||
| Ferreira et al. [122] | 2021 | Cervical cancer | Disease progression after CRT | n = 158 | Combined clinical + PET radiomics-based model | RF | – | Training and validation cohorts | AUC: 0.78 |
| Nakajo et al. [123] | 2022 | Cervical cancer | PFS after RT, CRT, or surgery | n = 50 | Combined clinical + PET radiomics-based model | Naïve base algorithm | – |
Internal validation (cross-validation) |
HR: 6.89 |
| Nakajo et al. [124] | 2021 | Endometrial cancer | PFS and OS after RT, CRT, or surgery | n = 53 | Combined clinical + PET radiomics-based model | kNN | – |
Internal validation (cross-validation) |
PFS—HR for coarseness: 0.65; OS—HR for coarseness: 0.52 |
AUC area under the receiver operating characteristic curve, COX-2 cyclooxygenase-2, CRT chemoradiotherapy, HR hazard ratio, ITB intratumoral budding, kNN k-nearest neighbors, LASSO least absolute shrinkage and selection operator algorithm, LNM lymph node metastasis, LR logistic regression, LVSI lymphovascular space invasion, ML machine learning, OS overall survival, PFS progression-free survival, RF random forest, RT radiotherapy, SVM support vector machine
aPerformance only presents the result of the best machine learning model