ciscNet -- A Single-Branch Cell Instance Segmentation and Classification Network

TL;DR

ciscNet is a novel single-branch neural network designed for simultaneous segmentation, classification, and counting of cell nuclei in histopathological images, aiding pathologists in diagnosis.

Contribution

This work introduces ciscNet, a new method for cell nuclei segmentation and classification that performs all tasks within a single-branch architecture, advancing automated pathology analysis.

Findings

Preliminary evaluation shows promising segmentation accuracy.

The method effectively classifies different cell nuclei types.

Code availability facilitates reproducibility and further research.

Abstract

Automated cell nucleus segmentation and classification are required to assist pathologists in their decision making. The Colon Nuclei Identification and Counting Challenge 2022 (CoNIC Challenge 2022) supports the development and comparability of segmentation and classification methods for histopathological images. In this contribution, we describe our CoNIC Challenge 2022 method ciscNet to segment, classify and count cell nuclei, and report preliminary evaluation results. Our code is available at https://git.scc.kit.edu/ciscnet/ciscnet-conic-2022.