Skip to main content
European Radiology Experimental
Fig. 3 | European Radiology Experimental

Fig. 3

From: Evaluation of a CTA-based convolutional neural network for infarct volume prediction in anterior cerebral circulation ischaemic stroke

Fig. 3

Confusion matrices for the convolutional neural network (CNN) detections by the ten individual Alberta Stroke Programme Early CT Score (ASPECTS) regions (M1–6, C, IC, L, and I) for 83 patients. The total sums from the left and right hemispheres (whichever was the infarcted side) were combined for true positives (TP), true negatives (TN), false positives (FP), and false negatives (FN)

Back to article page