Fuzzy Statistical Matrices for Cell Classification

TL;DR

This paper introduces fuzzy versions of higher order statistical matrices for improved texture analysis, demonstrating enhanced cell classification performance in biological imaging tasks.

Contribution

It proposes new fuzzy statistical matrices (RLM and SZM), extending previous fuzzy COM, with algorithms that improve texture descriptor robustness and efficacy.

Findings

Fuzzy RLM and SZM outperform traditional matrices in cell classification.

Enhanced robustness to noise in biological image analysis.

Improved accuracy in classifying HEp-2 cells using fuzzy descriptors.

Abstract

In this paper, we generalize image (texture) statistical descriptors and propose algorithms that improve their efficacy. Recently, a new method showed how the popular Co-Occurrence Matrix (COM) can be modified into a fuzzy version (FCOM) which is more effective and robust to noise. Here, we introduce new fuzzy versions of two additional higher order statistical matrices: the Run Length Matrix (RLM) and the Size Zone Matrix (SZM). We define the fuzzy zones and propose an efficient algorithm to compute the descriptors. We demonstrate the advantage of the proposed improvements over several state-of-the-art methods on three tasks from quantitative cell biology: analyzing and classifying Human Epithelial type 2 (HEp-2) cells using Indirect Immunofluorescence protocol (IFF).