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

Table 11

Detailed BER results for each time point for the best 6 supervised classifiers when using the leave-one-patient-out method on imputed perfusion features. The decision moment marked by bold font.

BER on perfusion	Random forests	dLDA	SVM-lin	LogitBoost	RobustBoost	SVM-mlp
				0	0	0
				0	0	0
				0	0	0.25
				0.125	0	0.125
				0.171	0.071	0
L				0.127	0.043	0.109
				0.214	0.130	0.279
				0.389	0.444	0.417
				0.373	0.418	0.281
				0.412	0.475	0.512
				0.625	0.687	0.562
				0.567	0.567	0.567
				0.5	0.5	0.5
				0.5	0.5	0.5
				0.333	0.333	0.333
				0.5	0.5	0.25
				0.5	0.5	0