A Paradigm Shift in Nuclear Chromatin Interpretation: From Qualitative Intuitive Recognition to Quantitative Texture Analysis of Breast Cancer Cell Nuclei

Abstract

Assessing the pattern of nuclear chromatin is essential for pathological investigations. However, the interpretation of nuclear pattern is subjective. In this study, we performed the texture analysis of nuclear chromatin in breast cancer samples to determine the nuclear pleomorphism score thereof. We used three different algorithms for extracting high‐level texture features: the gray‐level co‐occurrence matrix (GLCM), gray‐level run length matrix (GLRLM), and gray‐level size zone matrix (GLSZM). Using these algorithms, 12 GLCM, 11 GLRLM, and 16 GLSZM features were extracted from three scores of breast carcinoma (Scores 1–3). Classification accuracy was assessed using the support vector machine (SVM) and k‐nearest neighbor (KNN) classification models. Three features of GLCM, 11 of GLRLM, and 12 of GLSZM were consistent across the three nuclear pleomorphism scores of breast cancer. Comparing Scores 1 and 3, the GLSZM feature large zone high gray‐level emphasis showed the largest difference among breast cancer nuclear scores among all features of the three algorithms. The SVM and KNN classifiers showed favorable results for all three algorithms. A multiclass classification was performed to compare and distinguish between the scores of breast cancer. Texture features of nuclear chromatin can provide useful information for nuclear scoring. However, further validation of the correlations of histopathologic features, and standardization of the texture analysis process, are required to achieve better classification results. © 2021 The Authors. Cytometry Part A published by Wiley Periodicals LLC on behalf of International Society for Advancement of Cytometry.

Gray-Level Co-occurrence Matrix Analysis for the Detection of Discrete, Ethanol-Induced, Structural Changes in Cell Nuclei: An Artificial Intelligence Approach

“…Another possible medical application of GLCM is for the detection of pathologically changed cells and nuclei during cancer development. For example, in the recent study, Lee et al (2021) used this method for the evaluation of chromatin patterns and nuclear pleomorphism in breast cancer cells. Apart from GLCM, gray-level run-length matrix and gray-level size zone matrix were also implemented, and the authors concluded that textural features of chromatin are potentially valuable in nuclear scoring (Lee et al, 2021).…”

“…Data obtained from GLCM analysis can be used as inputs in various supervised and unsupervised ML models in order to increase the accuracy of prediction of physiological and pathological phenomena (Davidovic et al, 2021; Lee et al, 2021). Some of these models are based on a simple binominal logistic regression, while other models use more complex decision trees or Bayesian networks.…”

Effects of Iron Oxide Nanoparticles on Structural Organization of Hepatocyte Chromatin: Gray Level Co-occurrence Matrix Analysis

“…As mentioned before, GLCM as a method has several potentially important advantages over other techniques in microscopy. This is an objective method since it does not depend on the pathologist/histologist personal opinion and previous experience (Paunovic et al, 2019; Lee et al, 2020). The computational algorithm is designed in a way to assign a specific value (that can later be statistically analyzed) to a textural feature such as uniformity and homogeneity.…”

“…Later, we focused on the potential applications of GLCM as a sensing system for differentiating tissue and cell changes in the central nervous system, as well as for detection of chromatin damage induced by various toxins (Pantic et al, 2016 a , 2020). Other authors focused their research on the potential usefulness of GLCM in identification of cancer cells, as well as in clinical prognosis of outcomes of certain malignant diseases (Dincic et al, 2020; Lee et al, 2020). Despite numerous publications referring to the GLCM value in microscopy and pathology, it should be noted that most of these results are still preliminary, and we estimate that several years of additional research will be needed before we can make the definite conclusion and recommendations on whether GLCM can be successfully introduced in conventional pathology protocols.…”

“…In recent years, GLCM was shown to be able to identify discrete variations in cell and nuclear structure that are otherwise undetectable during conventional microscopy analysis (Pantic et al, 2016 a , 2020). This method was also successfully applied for the quantification of changes in nuclear chromatin organization and distribution during the processes of physiological aging, programmed cell death, as well as carcinogenesis (Pantic et al, 2017; Kanai et al, 2020; Lee et al, 2020). Today, various supplementary techniques to GLCM are also occasionally used in medicine, the most important probably being the discrete wavelet transform as a form of textural analysis (Vidya et al, 2015; AlKubeyyer et al, 2020).…”