Fig. 5

Accuracy of each model (MVnet) trained and evaluated on its own dataset, by the mean Euclidean distance error (first two columns) and angular distance error (third column), stratified by the output of the first stage (stage 1), second stage (stage 1+2), and an iteration of the second stage (stage 1+2+2). Accuracy assessed for 2Ch in its a anterior and b inferior point distance error, and c angular distance error; and for 4Ch in its d left ventricular lateral and e septal point distance error, and f angular distance error. Each bar represents the mean, and error bar the standard deviation of each accuracy metric. 2Ch two-chamber view, 4Ch four-chamber view