Fig. 2.

An overview of our method. In our method, the CT images are cropped into patches, which are then packed into MIL bags. In the $k{}^{th}$ epoch of training process, the data for supervised training consists of real bags (i.e., training CT images) and virtual bags generated in the ${(k-1)}^{th}$ epoch. Besides, real bags are also used for the auxiliary self-supervised learning task (while virtual bags are not). After the training stage, the trained MIL model will take the testing CT images (also modeled as MIL bags) as input to predict their labels (i.e., severe or non-severe).