Separable-HoverNet and Instance-YOLO for Colon Nuclei Identification and Counting

TL;DR

This paper introduces a combined approach using Separable-HoverNet and Instance-YOLOv5 to improve colon nuclei identification and counting in histology images, addressing variability and class imbalance challenges.

Contribution

The novel integration of Separable-HoverNet and Instance-YOLOv5 effectively handles small and unbalanced nuclei detection in colon histology images.

Findings

Achieved mPQ+ 0.389 on segmentation and classification.

Achieved r2 0.599 on cellular composition.

Demonstrated effectiveness on ISBI 2022 CoNIC Challenge datasets.

Abstract

Nuclear segmentation, classification and quantification within Haematoxylin & Eosin stained histology images enables the extraction of interpretable cell-based features that can be used in downstream explainable models in computational pathology (CPath). However, automatic recognition of different nuclei is faced with a major challenge in that there are several different types of nuclei, some of them exhibiting large intraclass variability. In this work, we propose an approach that combine Separable-HoverNet and Instance-YOLOv5 to indentify colon nuclei small and unbalanced. Our approach can achieve mPQ+ 0.389 on the Segmentation and Classification-Preliminary Test Dataset and r2 0.599 on the Cellular Composition-Preliminary Test Dataset on ISBI 2022 CoNIC Challenge.