Table 3: Comparison of performance for MC classification on different sets of features.

MethodAccuracyPrecisionSpecificityAUCSensitivity

CNN0.8768 ± 0.04310.8891 ± 0.03490.8667 ± 0.04570.9336 ± 0.02380.8701 ± 0.0144

Morphological0.8525 ± 0.02030.8624 ± 0.02670.8311 ± 0.04710.9256 ± 0.02110.8492 ± 0.0246
CNN + morphological0.8828 ± 0.04370.8911 ± 0.04470.8667 ± 0.06020.9385 ± 0.02380.8761 ± 0.0104
CNN filtered by morphologic0.8859±0.03630.8932±0.03840.8689±0.05280.9392 ± 0.02400.8843±0.0344

Textural0.7677 ± 0.06340.7964 ± 0.06590.7511 ± 0.09240.8721 ± 0.05300.7703 ± 0.0544
CNN + textural0.8727 ± 0.05000.8853 ± 0.04100.8622 ± 0.05220.9338 ± 0.02480.8801 ± 0.0434
CNN filtered by textural0.8747 ± 0.03870.8842 ± 0.04230.8578 ± 0.06030.9434±0.02200.8831 ± 0.0276

Morphological + textural0.8667 ± 0.02230.8768 ± 0.03090.8489 ± 0.05110.9381 ± 0.02190.8601 ± 0.0251
CNN + morphological + textural0.8818 ± 0.04340.8895 ± 0.04570.8644 ± 0.06240.9379 ± 0.02370.8791 ± 0.0124
CNN filtered by morphological + textural0.8747 ± 0.03760.8873 ± 0.02380.8644 ± 0.03390.9398 ± 0.02420.8751 ± 0.0328