Nuc2Vec: Learning Representations of Nuclei in Histopathology Images with Contrastive LossDownload PDF

Published: 31 Mar 2021, Last Modified: 16 May 2023MIDL 2021Readers: Everyone
Keywords: histopathology, tumor microenvironment, nuclei subtyping, constrastive learning, representation learning, unsupervised learning
TL;DR: We developed a method to learn useful vector embeddings for nuclei in histopathology images.
Abstract: The tumor microenvironment is an area of intense interest in cancer research and may be a clinically actionable aspect of cancer care. One way to study the tumor microenvironment is to characterize the spatial interactions between various types of nuclei in cancer tissue from H&E whole slide images, which require nucleus segmentation and classification. Current methods of nucleus classification rely on extensive labeling from pathologists and are limited by the number of categories a nucleus can be classified into. In this work, leveraging existing nucleus segmentation and contrastive representation learning methods, we developed a method that learns vector embeddings of nuclei based on their morphology in histopathology images. We show that the embeddings learned by this model capture distinctive morphological features of nuclei and can be used to group them into meaningful subtypes. These embeddings can provide a much richer characterization of the statistics of the spatial distribution of nuclei in cancer and open new possibilities in the quantitative study of the tumor microenvironment.
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
Source Code Url: https://github.com/chaosfengz/Nuc2Vec
Source Latex: zip
10 Replies

Loading