From: Deep semi-supervised learning for brain tumor classification
(a)Average accuracy, sensitivity and specificity on the test sets, where | |||
---|---|---|---|
the standard deviation is included in (·) after each performance value. | |||
Dataset | Accuracy (|σ|) | Sensitivity (|σ|) | Specificity (|σ|) |
TCGA | 86.53(4.24) | 73.75(8.15) | 92.73(3.45) |
MICCAI | 90.70(1.42) | 84.35(6.59) | 93.01(1.42) |
(b) The confusion matrix from test results on the TCGA dataset. | |||
True ∖ Classified | IDH mutation | IDH wild-type | |
IDH mutation | 73.75 | 26.25 | |
IDH wild-type | 7.27 | 92.73 | |
(c) The confusion matrix from test results on the MICCAI dataset. | |||
True ∖Classified | HGG | LGG | |
HGG | 93.01 | 6.99 | |
LGG | 15.65 | 84.35 |