Deep asymmetric mixture model for unsupervised cell segmentation
This work addresses automated cell segmentation for disease diagnosis and drug discovery, offering an incremental improvement over existing unsupervised models.
The paper tackled the problem of unsupervised cell segmentation by addressing limitations of symmetric distribution assumptions in existing models, resulting in a novel asymmetric mixture model that achieved gains of nearly 2-30% in dice coefficient compared to state-of-the-art methods.
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.