WEEP: A method for spatial interpretation of weakly supervised CNN models in computational pathology

arXiv:2403.15238v1 Announce Type: cross
Abstract: Deep learning enables the modelling of high-resolution histopathology whole-slide images (WSI). Weakly supervised learning of tile-level data is typically applied for tasks where labels only exist on the patient or WSI level (e.g. patient outcomes or histological grading). In this context, there is a need for improved spatial interpretability of predictions from such models. We propose a novel method, Wsi rEgion sElection aPproach (WEEP), for model interpretation. It provides a principled yet straightforward way to …

abstract arxiv cnn computational context cs.cv data deep learning eess.iv images interpretation labels modelling pathology patient resolution spatial stat.me supervised learning tasks type