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

Table 10

Detailed BER results for each time point for the best 6 supervised classifiers when using the leave-one-patient-out method on complete spectroscopy features. The decision moment marked by bold font. Some time points do not have results because there were no complete spectroscopy measurements.

BER on spectroscopy	Random forests	dLDA	SVM-lin	LogitBoost	RobustBoost	SVM-mlp
	—	—	—	—	—	—
	—	—	—	—	—	—
L
				0.5	0.562	0.687
				0.625	0.75	0.875
				0.5	0.5	0.25
				0.5	0.5	1
				1	1	1
				0.5	0.5	0.5
				0	0	0
	—	—	—	—	—	—
				1	1	0
	—	—	—	—	—	—
				1	1	0