Nuclei instance segmentation and classification in histopathology images with StarDist

TL;DR

This paper demonstrates that StarDist, a deep learning method originally for microscopy, can be effectively adapted for nuclei segmentation and classification in histopathology images, achieving top results in a major challenge.

Contribution

The study extends StarDist to histopathology images and validates its effectiveness through experiments and a competitive challenge.

Findings

Achieved first place in the CoNIC challenge 2022 for segmentation and classification.

Successfully adapted a microscopy-based method to histopathology images.

Validated the approach on the Lizard dataset.

Abstract

Instance segmentation and classification of nuclei is an important task in computational pathology. We show that StarDist, a deep learning nuclei segmentation method originally developed for fluorescence microscopy, can be extended and successfully applied to histopathology images. This is substantiated by conducting experiments on the Lizard dataset, and through entering the Colon Nuclei Identification and Counting (CoNIC) challenge 2022, where our approach achieved the first spot on the leaderboard for the segmentation and classification task for both the preliminary and final test phase.