Multiple Instance Learning (MIL) methods have become increasingly popular for classifying giga-pixel sized Whole-Slide Images (WSIs) in digital pathology. Most MIL methods operate at a single WSI magnification, by processing all the tissue patches. Such a formulation induces high computational requirements, and constrains the contextualization of the WSI-level representation to a single scale. A few MIL methods extend to multiple scales, but are computationally more demanding. In this paper, inspired by the pathological diagnostic process, we propose ZoomMIL, a method that learns to perform multi-level zooming in an end-to-end manner. ZoomMIL builds WSI representations by aggregating tissue-context information from multiple magnifications. The proposed method outperforms the state-of-the-art MIL methods in WSI classification on two large datasets, while significantly reducing the computational demands with regard to Floating-Point Operations (FLOPs) and processing time by up to 40x.
@article{arxiv.2204.12454,
title = {Differentiable Zooming for Multiple Instance Learning on Whole-Slide Images},
author = {Kevin Thandiackal and Boqi Chen and Pushpak Pati and Guillaume Jaume and Drew F. K. Williamson and Maria Gabrani and Orcun Goksel},
journal= {arXiv preprint arXiv:2204.12454},
year = {2022}
}
Comments
Typos corrected; Changed dataset name from INSEC to CRC upon dataset creators' request; Update affiliation and fix typos;