MF-Hovernet: An Extension of Hovernet for Colon Nuclei Identification and Counting (CoNiC) Challenge

TL;DR

This paper introduces MF-Hovernet, an enhanced version of Hovernet with multiple filter blocks, to improve nuclei identification and counting in colon cancer histology images, demonstrating increased performance.

Contribution

The paper presents a novel extension of Hovernet incorporating multiple filter blocks, which enhances nuclei detection and counting accuracy in colon cancer histology analysis.

Findings

Improved nuclei identification accuracy.

Enhanced counting performance over baseline Hovernet.

Demonstrated effectiveness on colon histology images.

Abstract

Nuclei Identification and Counting is the most important morphological feature of cancers, especially in the colon. Many deep learning-based methods have been proposed to deal with this problem. In this work, we construct an extension of Hovernet for nuclei identification and counting to address the problem named MF-Hovernet. Our proposed model is the combination of multiple filer block to Hovernet architecture. The current result shows the efficiency of multiple filter block to improve the performance of the original Hovernet model.