Multiple Instance Learning with random sampling for Whole Slide Image Classification

arXiv:2403.05351v1 Announce Type: new
Abstract: In computational pathology, random sampling of patches during training of Multiple Instance Learning (MIL) methods is computationally efficient and serves as a regularization strategy. Despite its promising benefits, questions concerning performance trends for varying sample sizes and its influence on model interpretability remain. Addressing these, we reach an optimal performance enhancement of 1.7% using thirty percent of patches on the CAMELYON16 dataset, and 3.7% with only eight samples on the TUPAC16 dataset. We also find …

abstract arxiv benefits classification computational cs.cv image influence instance interpretability mil model interpretability multiple pathology performance questions random regularization sample sampling strategy training trends type