Skip to main content
. Author manuscript; available in PMC: 2022 May 13.
Published in final edited form as: Proc IEEE Int Conf Data Min. 2021 Dec;2021:1132–1137. doi: 10.1109/icdm51629.2021.00134

Fig. 1.

Fig. 1.

Model Overview. The input images are sampled in batches with a constraint that no two images in a batch are from the same patient. Learning is performed using a shared encoder (Resent-50) with triplet attention and joint loss from the supervised classification and contrastive learning module.