Fig. 3From: Relaxometric learning: a pattern recognition method for T2 relaxation curves based on machine learning supported by an analytical frameworkPerformance evaluation of the bootstrap resampling-based matrixing approach based on conventional SVM classifications. The performance of the approach was evaluated with the number of datasets generated by the bootstrap resampling set at 100 (closed blue symbols) and 10 (open symbols) matrices. a AUC (circles) and accuracy (diamonds). b CCR-A (triangles) and CCR-B (squares)Back to article page