Skip to main content
. Author manuscript; available in PMC: 2019 Apr 1.
Published in final edited form as: Neuroimage. 2017 Dec 24;169:407–418. doi: 10.1016/j.neuroimage.2017.12.059

Figure 5. Inclusion model to identify unusable images.

Figure 5

A-C: Logistic models in training (A), internal testing (B), and external testing (C) datasets were used to evaluate the ability of each quantitative measure of image quality to discriminate usable (rated 1-2) and unusable (rated 0) images. Area under the curve (AUC) was used to summarize model performance. In all datasets, the Euler number was the best-performing metric; adding additional metrics to the Euler number did not improve model performance. D-F: Receiver Operator Characteristic (ROC) curves for the Euler number in each dataset.