NOVEL MULTIPLE INSTANCE LEARNING MODELS FOR DIGITAL HISTOPATHOLOGY

Abstract

Histopathology is the gold standard in cancer diagnosis. Slide scanners have transformed histopathology into digital, where glass slides are digitized and stored as whole-slide-images (WSIs). WSIs provide us with precious data that powerful deep learning models can exploit. However, a WSI is a gigapixel image that traditional deep learning models cannot process. Besides, deep learning models require a lot of labeled data. Nevertheless, most WSIs are either unannotated or annotated with some weak labels indicating slide-level properties, like a tumor slide or a normal slide. This thesis develops novel multiple instance learning (MIL) models to tackle huge WSIs and utilize weak labels. We treat a WSI as a bag of small patches from the WSI and use the WSI’s weak label as the bag label. We test our models’ usefulness on real-world tasks at the intersection of digital histopathology and genomics.