Nuclei instance segmentation and classification in histopathology images with StarDist

Instance segmentation and classification of nuclei is an important task in computational pathology. We show that StarDist, a deep learning based 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. At the end of the preliminary test phase of CoNIC, our approach ranked first on the leaderboard for the segmentation and classification task.