Skip to main content
. 2021 Sep 22;16(9):e0257635. doi: 10.1371/journal.pone.0257635

Table 1. Number of correct predictions relative to the amount of samples split into the diagnostic groups of the initial dataset.

Results are shown for the feature-based classification (FBC) and deep learning-based classification (DLC).

diagnosis FBC DLC
FTC 26/32 (81%) 27/32 (84%)
FA 52/53 (98%) 49/53 (92%)
NIFTP 6/9 (67%) 5/9 (56%)
FVPTC 8/9 (89%) 8/9 (89%)
CPTC 48/53 (91%) 50/53 (94%)