GradMix for nuclei segmentation and classification in imbalanced pathology image datasets

TL;DR

GradMix is a novel data augmentation method that improves nuclei segmentation and classification in imbalanced pathology datasets by generating realistic rare-class nuclei through customized mixing of major and rare nuclei.

Contribution

This paper introduces GradMix, a new augmentation technique specifically designed for nuclei in pathology images, addressing class imbalance issues.

Findings

GradMix improves segmentation accuracy on imbalanced datasets.

It enhances classification performance for rare nuclei types.

Experimental results confirm the effectiveness of GradMix.

Abstract

An automated segmentation and classification of nuclei is an essential task in digital pathology. The current deep learning-based approaches require a vast amount of annotated datasets by pathologists. However, the existing datasets are imbalanced among different types of nuclei in general, leading to a substantial performance degradation. In this paper, we propose a simple but effective data augmentation technique, termed GradMix, that is specifically designed for nuclei segmentation and classification. GradMix takes a pair of a major-class nucleus and a rare-class nucleus, creates a customized mixing mask, and combines them using the mask to generate a new rare-class nucleus. As it combines two nuclei, GradMix considers both nuclei and the neighboring environment by using the customized mixing mask. This allows us to generate realistic rare-class nuclei with varying environments. We employed two datasets to evaluate the effectiveness of GradMix. The experimental results suggest that GradMix is able to improve the performance of nuclei segmentation and classification in imbalanced pathology image datasets.