Cellular Segmentation and Composition in Routine Histology Images using Deep Learning

TL;DR

This paper presents deep learning pipelines for nuclei segmentation and cellular composition analysis in histology images, achieving competitive results in the CoNIC challenge for colorectal cancer tissue analysis.

Contribution

The study introduces novel deep learning methods, HoVer-Net and ALBRT, for nuclei segmentation and cellular composition prediction in histology images, advancing computational pathology tools.

Findings

HoVer-Net achieved a PQ of 0.58 on the test set.

ALBRT achieved an overall R^2 score of 0.53 for cellular composition.

Results demonstrate effective segmentation and cell type quantification in colorectal cancer images.

Abstract

Identification and quantification of nuclei in colorectal cancer haematoxylin \& eosin (H\&E) stained histology images is crucial to prognosis and patient management. In computational pathology these tasks are referred to as nuclear segmentation, classification and composition and are used to extract meaningful interpretable cytological and architectural features for downstream analysis. The CoNIC challenge poses the task of automated nuclei segmentation, classification and composition into six different types of nuclei from the largest publicly known nuclei dataset - Lizard. In this regard, we have developed pipelines for the prediction of nuclei segmentation using HoVer-Net and ALBRT for cellular composition. On testing on the preliminary test set, HoVer-Net achieved a PQ of 0.58, a PQ+ of 0.58 and finally a mPQ+ of 0.35. For the prediction of cellular composition with ALBRT on the preliminary test set, we achieved an overall $R^2$ score of 0.53, consisting of 0.84 for lymphocytes, 0.70 for epithelial cells, 0.70 for plasma and .060 for eosinophils.