Skip to main content
. Author manuscript; available in PMC: 2020 Sep 18.
Published in final edited form as: IEEE Access. 2019 May 13;7:64583–64591. doi: 10.1109/access.2019.2916557

TABLE VI.

Effect of 2D/3D CNN architecture on the performance of models trained from scratch: p-values of pairwise compared ROCS Between the 3D CNN model group and two 2D CNN model groups

Comparison Method Small Input Size Middle Input Size Large Input Size Fusion
2D transverse plane 0.049 0.006 0.003 <0.001
2D multi-view plane 0.082 0.023 0.125 0.006