A self-supervised contrastive learning approach for whole slide image representation in digital pathology

Parsa Ashrafi Fashi, Sobhan Hemati, Morteza Babaie, Ricardo Gonzalez, H. R. Tizhoosh

Research output: Contribution to journalArticlepeer-review


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 may improve the generalizations of downstream tasks. Previous self-supervised representation methods rely on patch selection and classification such that the effect of SSL on end-to-end WSI representation is not investigated. In contrast to existing augmentation-based SSL methods, this paper proposes a novel self-supervised learning scheme based on the available primary site information. We also design 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 6000 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.

Original languageEnglish (US)
Article number100133
JournalJournal of Pathology Informatics
StatePublished - Jan 2022


  • Computational pathology
  • Digital pathology
  • Image search
  • Multiple instance learning
  • Representation learning
  • Self-supervised learning
  • Supervised contrastive learning

ASJC Scopus subject areas

  • Pathology and Forensic Medicine
  • Health Informatics
  • Computer Science Applications


Dive into the research topics of 'A self-supervised contrastive learning approach for whole slide image representation in digital pathology'. Together they form a unique fingerprint.

Cite this