Table 3.

Validation slice-level classification results using augmented stacked gray and segmented images scenario with four backbone CNN architectures (ResneXt-50, Densenet-161, Inception-v3, and Wide-Resnet-50).

Model	Slice-Level Classification (%)
ResneXt-50	88.51
Densenet-161	88.42
Inception-v3	88.64
Wide-Resnet-50	87.97