Skip to main content
. Author manuscript; available in PMC: 2019 Nov 22.
Published in final edited form as: Proc SPIE Int Soc Opt Eng. 2019 Mar 15;10949:1094917. doi: 10.1117/12.2512541

Figure 3.

Figure 3.

Two strategies of training a CAC classification network. The “Strategy 1” is the traditional design for a two-class classification task. To further leverage the performance, we split the CAC to two sub-categories: (Agatston score < 400 and Agatston score ≥ 400). Then, the 3×3 classification matrix for prediction were converted to two class problem for better prediction performance.