UR-017 SHERLOCK: Self-supervised Histopathological Evaluation for Recognition of Lymphocytes and Other Cancerous Kinds

Whole Slide Images (WSI) are gigantic images (e.g. 100k x 100k pixels) of tissue samples. The goal of SHERLOCK is to detect cancer cells in those tissue samples. We do this by using a pretrained Masked Autoencoder (MAE), from Facebook’s research lab, that we finetune on the PanNuke dataset. The benefit of using an MAE is that unlike supervised learning the WSI’s don’t need to be labeled. This is important because it will save a lot of time and money that would be spent on labeling WSI’s.