CVLGMay 10, 2020

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

arXiv:2005.08629v110 citations
Originality Synthesis-oriented
AI Analysis

This work addresses the need for efficient representation learning in pathology, where labeling large datasets is tedious, but it is incremental as it applies existing methods to a specific domain.

The study tackled the challenge of representation learning in histopathology by exploring deep neural networks with triplet loss across unsupervised, semi-supervised, and supervised setups, achieving high accuracy and generalization on two public datasets.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes