NucleiMix: Realistic Data Augmentation for Nuclei Instance Segmentation

TL;DR

NucleiMix is a novel data augmentation technique that balances nuclei type distribution in pathology images by inserting and seamlessly blending rare-type nuclei, significantly improving segmentation accuracy.

Contribution

This paper introduces NucleiMix, a two-phase augmentation method using candidate placement and diffusion-based inpainting to enhance nuclei dataset diversity and segmentation performance.

Findings

NucleiMix improves segmentation accuracy on public datasets.

It effectively synthesizes realistic rare-type nuclei.

The method enhances nuclei classification robustness.

Abstract

Nuclei instance segmentation is an essential task in pathology image analysis, serving as the foundation for many downstream applications. The release of several public datasets has significantly advanced research in this area, yet many existing methods struggle with data imbalance issues. To address this challenge, this study introduces a data augmentation method, called NucleiMix, which is designed to balance the distribution of nuclei types by increasing the number of rare-type nuclei within datasets. NucleiMix operates in two phases. In the first phase, it identifies candidate locations similar to the surroundings of rare-type nuclei and inserts rare-type nuclei into the candidate locations. In the second phase, it employs a progressive inpainting strategy using a pre-trained diffusion model to seamlessly integrate rare-type nuclei into their new environments in replacement of major-type nuclei or background locations. We systematically evaluate the effectiveness of NucleiMix on three public datasets using two popular nuclei instance segmentation models. The results demonstrate the superior ability of NucleiMix to synthesize realistic rare-type nuclei and to enhance the quality of nuclei segmentation and classification in an accurate and robust manner.