A Deep Learning Framework for Nuclear Segmentation and Classification in Histopathological Images

TL;DR

This paper introduces a deep learning framework that simultaneously segments and classifies nuclei in histopathological images, addressing heterogeneity and variation challenges in digital pathology.

Contribution

It presents a unified neural network with three branches for nuclear segmentation, HoVer mapping, and classification, improving accuracy and efficiency.

Findings

Effective in segmenting nuclei with high heterogeneity

Accurate classification of nuclear types

Outperforms existing methods in digital pathology tasks

Abstract

Nucleus segmentation and classification are the prerequisites in the workflow of digital pathology processing. However, it is very challenging due to its high-level heterogeneity and wide variations. This work proposes a deep neural network to simultaneously achieve nuclear classification and segmentation, which is designed using a unified framework with three different branches, including segmentation, HoVer mapping, and classification. The segmentation branch aims to generate the boundaries of each nucleus. The HoVer branch calculates the horizontal and vertical distances of nuclear pixels to their centres of mass. The nuclear classification branch is used to distinguish the class of pixels inside the nucleus obtained from segmentation.