Rank-Aware Contextual Reasoning on Whole Slide Images for Weakly Supervised Skin Cancer Grading

[Submitted on 29 Aug 2023]

Download a PDF of the paper titled RACR-MIL: Weakly Supervised Skin Cancer Grading using Rank-Aware Contextual Reasoning on Whole Slide Images, by Anirudh Choudhary and 13 other authors

Download PDF

Abstract: Cutaneous squamous cell cancer (cSCC) is the second most common skin cancer
in the US. It is diagnosed by manual multi-class tumor grading using a tissue
whole slide image (WSI), which is subjective and suffers from inter-pathologist
variability. We propose an automated weakly-supervised grading approach for
cSCC WSIs that is trained using WSI-level grade and does not require
fine-grained tumor annotations. The proposed model, RACR-MIL, transforms each
WSI into a bag of tiled patches and leverages attention-based multiple-instance
learning to assign a WSI-level grade. We propose three key innovations to
address general as well as cSCC-specific challenges in tumor grading. First, we
leverage spatial and semantic proximity to define a WSI graph that encodes both
local and non-local dependencies between tumor regions and leverage graph
attention convolution to derive contextual patch features. Second, we introduce
a novel ordinal ranking constraint on the patch attention network to ensure
that higher-grade tumor regions are assigned higher attention. Third, we use
tumor depth as an auxiliary task to improve grade classification in a multitask
learning framework. RACR-MIL achieves 2-9% improvement in grade classification
over existing weakly-supervised approaches on a dataset of 718 cSCC tissue
images and localizes the tumor better. The model achieves 5-20% higher accuracy
in difficult-to-classify high-risk grade classes and is robust to class
imbalance.