Skip to main content
. Author manuscript; available in PMC: 2024 Apr 1.
Published in final edited form as: IEEE Trans Artif Intell. 2022 Mar 15;4(2):383–397. doi: 10.1109/tai.2022.3159510

TABLE V.

OOD detection accuracy in an experiment where in-distribution data came from CP-younger fetus, CP-older fetus, Prostate, Heart, Liver-CT, Liver-MRI-SPIR, Liver-MRI-DUAL-In and Liver-MRI-DUAL-Out datasets, and OOD data came from Pancreas, Hippocampus, and Spleen datasets.

Method accuracy sensitivity specificity AUC
Proposed method 1.00 0.98 1.00 0.98
UNC-Dropout 0.55 0.48 0.63 0.62
DkNN 0.76 0.67 0.82 0.79
UNC-Ensemble 0.84 0.87 0.71 0.82
Outlier exposure 0.83 0.80 0.86 0.80
Lee-2017 0.76 0.69 0.78 0.77
ODIN 0.70 0.61 0.68 0.67
Mah-Dist 0.74 0.66 0.80 0.77