Table 2.xls (5.5 kB)
Table of averaged results over 100 train-test splits with a ratio of 0.33.
dataset
posted on 2019-07-11, 17:43 authored by Betty Wutzl, Kenji Leibnitz, Frank Rattay, Martin Kronbichler, Masayuki Murata, Stefan Martin GolaszewskiThe AUC of the precision and recall curve is shown (AUC with feature selection) for training and testing with the most important ROIs and with all ROIs (AUC without feature selection).
