Research Article

Tumour Relapse Prediction Using Multiparametric MR Data Recorded during Follow-Up of GBM Patients

Table 4

Weighted BER for the best 6 supervised classifiers when using the leave-one-patient-out method with complete features for each MR modality separately.

Weighted BER Random forests dLDA SVM-lin LogitBoost RobustBoost SVM-mlp

Perfusion 0.148 0.256 0.220 0.148 0.148 0.193
Diffusion 0.358 0.259 0.255 0.367 0.367 0.349
Spectroscopy 0.571 0.561 0.600 0.609 0.623 0.629