In this article, the optimization of the modified U-Net neural network model extended with fuzzy layers has been studied with the usage of Grid search and Keras tuner. The article is a continuation of previous work where the model is suggested and explored. From one point of view, the research is focused on the optimization of Fuzzy Layers embedded in the U-Net model in order to find the better neural network architecture for nuclei segmentation in the research work in BioMed Varna R&D ecosystem for the segmentation of cellular nuclei. At the same time from a global perspective, this experiment is a part of the bigger one for the searching of new neural network architecture design techniques.

No abstract

This paper presents a proof of concept for the usefulness of second-order texture features for the qualitative analysis and classification of chromogenic in-situ hybridization whole slide images in high-throughput imaging experiments. The challenge is that currently, the gold standard for gene expression grading in such images is expert assessment. The idea of the research team is to use different approaches in the analysis of these images that will be used for structural segmentation and functional analysis in gene expression. The article presents such perspective idea to select a number of textural features that are going to be used for classification. In our experiment, natural grouping of image samples (tiles) depending on their local texture properties was explored in an unsupervised classification procedure. The features are reduced to two dimensions with fuzzy c-means clustering. The overall conclusion of this experiment is that Haralick features are a viable choice for classification and analysis of chromogenic insitu hybridization image data. The principal component analysis approach produced slightly more "understandable" from an annotator's point of view classes.

No abstract

No abstract