Deep asymmetric mixture model for unsupervised cell segmentation

TL;DR

This paper introduces a novel asymmetric mixture model that improves unsupervised cell segmentation accuracy, especially for asymmetrically distributed data, outperforming existing models with significant gains in dice coefficient.

Contribution

The paper proposes a new asymmetric mixture model that enhances unsupervised cell segmentation by addressing symmetry assumptions and outlier sensitivity of prior models.

Findings

Achieves 2-30% higher dice coefficient than state-of-the-art methods

Effectively handles asymmetrically distributed data in cell images

Demonstrates statistically significant improvements (p<0.05)

Abstract

Automated cell segmentation has become increasingly crucial for disease diagnosis and drug discovery, as manual delineation is excessively laborious and subjective. To address this issue with limited manual annotation, researchers have developed semi/unsupervised segmentation approaches. Among these approaches, the Deep Gaussian mixture model plays a vital role due to its capacity to facilitate complex data distributions. However, these models assume that the data follows symmetric normal distributions, which is inapplicable for data that is asymmetrically distributed. These models also obstacles weak generalization capacity and are sensitive to outliers. To address these issues, this paper presents a novel asymmetric mixture model for unsupervised cell segmentation. This asymmetric mixture model is built by aggregating certain multivariate Gaussian mixture models with log-likelihood and self-supervised-based optimization functions. The proposed asymmetric mixture model outperforms (nearly 2-30% gain in dice coefficient, p<0.05) the existing state-of-the-art unsupervised models on cell segmentation including the segment anything.