Litcius/Paper detail

HistoSSL: Self-Supervised Representation Learning for Classifying Histopathology Images

Xu Jin, Teng Huang, Ke Wen, Mengxian Chi, Hong An

2022Mathematics18 citationsDOIOpen Access PDF

Abstract

The success of image classification depends on copious annotated images for training. Annotating histopathology images is costly and laborious. Although several successful self-supervised representation learning approaches have been introduced, they are still insufficient to consider the unique characteristics of histopathology images. In this work, we propose the novel histopathology-oriented self-supervised representation learning framework (HistoSSL) to efficiently extract representations from unlabeled histopathology images at three levels: global, cell, and stain. The model transfers remarkably to downstream tasks: colorectal tissue phenotyping on the NCTCRC dataset and breast cancer metastasis recognition on the CAMELYON16 dataset. HistoSSL achieved higher accuracies than state-of-the-art self-supervised learning approaches, which proved the robustness of the learned representations.

Topics & Concepts

HistopathologyArtificial intelligenceRobustness (evolution)Computer sciencePattern recognition (psychology)Representation (politics)Machine learningPathologyMedicineBiologyBiochemistryPoliticsLawPolitical scienceGeneAI in cancer detectionDigital Imaging for Blood DiseasesCOVID-19 diagnosis using AI