Supervision and Source Domain Impact on Representation Learning: A Histopathology Case Study

TL;DR

This study investigates how supervision levels and source domain differences affect deep neural network representation learning in histopathology, demonstrating high accuracy and generalization across datasets.

Contribution

It compares supervised, semi-supervised, and unsupervised methods for pathology image representation learning, highlighting the impact of supervision and domain variation.

Findings

High accuracy achieved with learned representations

Effective generalization across different pathology datasets

Comparison of various learning setups in histopathology

Abstract

As many algorithms depend on a suitable representation of data, learning unique features is considered a crucial task. Although supervised techniques using deep neural networks have boosted the performance of representation learning, the need for a large set of labeled data limits the application of such methods. As an example, high-quality delineations of regions of interest in the field of pathology is a tedious and time-consuming task due to the large image dimensions. In this work, we explored the performance of a deep neural network and triplet loss in the area of representation learning. We investigated the notion of similarity and dissimilarity in pathology whole-slide images and compared different setups from unsupervised and semi-supervised to supervised learning in our experiments. Additionally, different approaches were tested, applying few-shot learning on two publicly available pathology image datasets. We achieved high accuracy and generalization when the learned representations were applied to two different pathology datasets.