Skip to main content
. Author manuscript; available in PMC: 2021 Jun 10.
Published in final edited form as: Int J Med Inform. 2021 Jan 28;148:104402. doi: 10.1016/j.ijmedinf.2021.104402

Fig. 3.

Fig. 3.

Confusion matrices showing results of test set for the best performing model (Densenet121 Not pretrained), and poorest performing model (Resnet34 Pretrained). Taken from a single representative fold during cross validation.