Automated three-dimensional morphology-based clustering of human erythrocytes with regular shapes: stomatocytes, discocytes, and echinocytes

Abstract

Inkyu Moon, "Automated three-dimensional morphologybased clustering of human erythrocytes with regular shapes: stomatocytes, discocytes, and echinocytes," J. Biomed. Opt. 22(7), 076015 (2017), doi: 10.1117/1.JBO.22.7.076015. Abstract. We present unsupervised clustering methods for automatic grouping of human red blood cells (RBCs) extracted from RBC quantitative phase images obtained by digital holographic microscopy into three RBC clusters with regular shapes, including biconcave, stomatocyte, and sphero-echinocyte. We select some good features related to the RBC profile and morphology, such as RBC average thickness, sphericity coefficient, and mean corpuscular volume, and clustering methods, including density-based spatial clustering applications with noise, k-medoids, and k -means, are applied to the set of morphological features. The clustering results of RBCs using a set of three-dimensional features are compared against a set of two-dimensional features. Our experimental results indicate that by utilizing the introduced set of features, two groups of biconcave RBCs and old RBCs (suffering from the sphero-echinocyte process) can be perfectly clustered. In addition, by increasing the number of clusters, the three RBC types can be effectively clustered in an automated unsupervised manner with high accuracy. The performance evaluation of the clustering techniques reveals that they can assist hematologists in further diagnosis. © The Authors. Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

Quantitative phase imaging of erythrocyte in epilepsy patients

“…It is possible to observe samples at different magnifications. However, as a result of surface imaging, SEM gives a two-dimensional image with scale information (Ahmadzadeh et al, 2017). In this respect, SEM has disadvantage compared to the surface profilometers or quantitative phase imaging techniques.…”

“…Red blood cells (RBC), or erythrocytes, representing discoid cells with thick rim and thin sunken center, are the most abundant among blood cells. Different blood abnormalities at different stages alter the original biconcave shape of erythrocytes into different morphologies (Ahmadzadeh, Jaferzadeh, Lee, & Moon, 2017; Jaferzadeh & Moon, 2016; Moon et al, 2013; Singh, Srivastava, & Mehta, 2020). Apart from studies on clustering irregular shapes of erythrocytes at different duration of storage from the sample collected from healthy person (Ficarra et al, 2013; Piety, Reinhart, Pourreau, Abidi, & Shevkoplyas, 2016; Suwalsky et al, 2004; Suwalsky, Mennickent, Norris, Villena, & Sotomayor, 2006), there are various other articles investigating the erythrocyte morphologies from the sample collected from patients (Buys et al, 2013; Kurantsin‐Mills, Samji, Moscarello, & Boggs, 1982; Oprisan, Stoica, & Avadanei, 2017).…”

“…The widely used two‐dimensional microscopic imaging techniques performance is not acceptable according to the quantitative phase imaging in terms of noninvasive and without sample preparation. Quantitative phase imaging techniques are capable of providing quantitatively detailed information about the cell structure at a single‐cell level (Ahmadzadeh et al, 2017). From the three‐dimensional (3D) profile, retrieved by quantitative phase imaging methods, structural parameters such as diameter of cell rim, height of the upper view area, surface area, and volume can be obtained (Jaferzadeh & Moon, 2016).…”

Automated quantitative analysis of multiple cardiomyocytes at the single‐cell level with three‐dimensional holographic imaging informatics

“…Intensity-based imaging systems cannot accurately capture cell structures. Threedimensional (3D) digital holographic in microscopic configuration (DH) imaging techniques in combination with information processing provide quantitative phase information about live cells in vitro [1][2][3][4][5][6][7][8][9][10][11][12]. In cell analysis at the single-cell level, standard image segmentation techniques suffer from inherent noise, degradation and low contrast in medical images.…”

Automated single cardiomyocyte characterization by nucleus extraction from dynamic holographic images using a fully convolutional neural network

“…Digital holographic microscopy (DHM) providing quantitative phase images (QPIs), is a promising tool in the field of label-free and computer-aided assessments [1][2][3]. The benefits of numerical reconstruction of digitally recorded holograms made it possible to study micrometer-sized living cells [4][5][6].…”