Skip to main content
. 2021 Aug 3;9:e11906. doi: 10.7717/peerj.11906

Table 3. Comparison of 10-fold cross validation results of different CNN architectures on the training data set.

Filters ACC Sen Spe MCC AUC
32 0.82 0.82 0.83 0.65 0.89
64 0.80 0.79 0.79 0.60 0.88
32-64 0.78 0.76 0.80 0.57 0.87
64-128 0.78 0.78 0.78 0.56 0.87

Notes.

The highest values are highlighted in bold.