Skip to main content
. 2021 Mar 31;71:102046. doi: 10.1016/j.media.2021.102046

Fig. 2.

Fig. 2

Overview of the proposed method: representation of the two COVID-19 datasets (on the left) with associated Brixia score annotations, and of the other two datasets (on the right) used for the pre-training. Datasets splitting and usage is indicated (in the middle) for training/validation/test phases. The outputs of the proposed system are illustrated as well (bottom right).