Artifact-Robust Graph-Based Learning in Digital Pathology

Abstract

Whole slide images (WSIs) are digitized images of tissues placed on glass slides using advanced scanners. The digital processing of WSIs is challenging as they are gigapixel images and stored in multiresolution format. A common challenge with WSIs is that perturbations/artifacts are inevitable during the storage of the glass slides and digitizing them. These perturbations include motion, which often arises from slide movement during placement, and changes in hue and brightness due to variations in staining chemicals and the quality of digitizing scanners. In this work, a novel robust learning approach is presented to account for these artifacts. Due to the size and resolution of WSIs and to account for neighborhood information, graph-based methods are called for. We use graph convolutional network (GCN) to extract features from the graph that represents the WSI. Using a denoiser and pooling layer, perturbations in WSIs are effectively managed. Subsequently, the output is processed by a transformer that classifies two different datasets: one for various grades of prostate cancer and another for lung cancer classification. To compare the efficacy of the proposed approach, the model without denoiser is trained and tested with WSIs without any perturbation and then different perturbations are introduced in WSIs and passed through the network with the denoiser. The accuracy and kappa scores of the proposed model with both datasets compared with non-robust algorithms show significant improvement in cancer diagnosis.