Self-Supervised Nuclei Segmentation in Histopathological Images Using Attention

TL;DR

This paper introduces a self-supervised method for nuclei segmentation in histopathological images, leveraging magnification identification as a proxy task to generate segmentation maps without manual annotations.

Contribution

The study proposes a novel self-supervised approach that uses magnification level prediction to guide nuclei segmentation, reducing reliance on manual annotations and outperforming other unsupervised methods.

Findings

Outperforms other unsupervised nuclei segmentation methods.

Achieves comparable performance to supervised approaches on MoNuSeg dataset.

Provides open-source code and models for further research.

Abstract

Segmentation and accurate localization of nuclei in histopathological images is a very challenging problem, with most existing approaches adopting a supervised strategy. These methods usually rely on manual annotations that require a lot of time and effort from medical experts. In this study, we present a self-supervised approach for segmentation of nuclei for whole slide histopathology images. Our method works on the assumption that the size and texture of nuclei can determine the magnification at which a patch is extracted. We show that the identification of the magnification level for tiles can generate a preliminary self-supervision signal to locate nuclei. We further show that by appropriately constraining our model it is possible to retrieve meaningful segmentation maps as an auxiliary output to the primary magnification identification task. Our experiments show that with standard post-processing, our method can outperform other unsupervised nuclei segmentation approaches and report similar performance with supervised ones on the publicly available MoNuSeg dataset. Our code and models are available online to facilitate further research.