Figure 4:
(A) and (B) are two examples showing anteroposterior (AP) and lateral digital subtraction angiography (DSA) sequences, the normalized peak height (PH) maps generated from those sequences, the class activation maps (CAMs) as well as the classifications from the convolutional neural network (CNN) for each view and the ensembled CNN for both views. In (A), the AP view CNN incorrectly classifies the PH map as being mTICI 2b, 2c or 3 while the lateral view CNN and ensembled CNN both correctly classify the PH map as mTICI 0,1 or 2a. In (B), the lateral view CNN incorrectly classifies the PH map as being mTICI 0,1 or 2a while the AP view CNN and ensembled CNN both correctly classify the PH map as mTICI 2b, 2c or 3. This shows that misclassifications can occur when either AP or lateral views are used independently, however, when information from both views are combined using an ensemble network, the tool is able to correctly classify the DSA into the appropriate group. In each CNN classification table, the green highlight indicates the network classification. All the CAMs show that the activation occurs in the vessels with the larger vessels causing a higher activation.