A Self-Supervised Contrastive Learning Approach for Whole Slide Image Representation in Digital Pathology

Parsa Ashrafi Fashi, Sobhan Hemati, Morteza Babaie, Ricardo Gonzalez, Hamid Tizhoosh

Keywords: Digital Pathology, Representation Learning, Self-Supervised Learning, Supervised Contrastive Learning, Multiple Instance Learning, Attention

TL;DR: This paper conducts self-supervision based on primary site information of pathology slides and exploits contrastive learning and attention-based pooling for Representation Learning.

Abstract: Image analysis in digital pathology has proven to be one of the most challenging fields in medical imaging for AI-driven classification and search tasks. Due to their gigapixel dimensions, whole slide images (WSIs) are difficult to represent for computational pathology. Self-supervised learning (SSL) has recently demonstrated excellent performance in learning effective representations on pretext objectives, which improves the generalizations of downstream tasks. Previous self-supervised representation methods rely on patch (i.e., sub-image) selection and classification such that the effect of SSL on end-to-end WSI representation is not investigated. In this paper, we propose a novel self-supervised learning scheme based on the available primary site information, in contrast to existing augmentation-based SSL methods. We also exploit a fully supervised contrastive learning setup to increase the robustness of the representations for WSI classification and search for both pretext and downstream tasks. We trained and evaluated the model on more than 6,000 WSIs from The Cancer Genome Atlas (TCGA) repository provided by the National Cancer Institute. The proposed architecture achieved excellent results on most primary sites and cancer subtypes. We also achieved the best result on validation on a lung cancer classification task.

Registration: I acknowledge that publication of this at MIDL and in the proceedings requires at least one of the authors to register and present the work during the conference.

Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.

Paper Type: both

Primary Subject Area: Unsupervised Learning and Representation Learning

Secondary Subject Area: Application: Histopathology

Confidentiality And Author Instructions: I read the call for papers and author instructions. I acknowledge that exceeding the page limit and/or altering the latex template can result in desk rejection.