An improved overlapping k-means clustering method for medical applications

Khanmohammadi, Sina; Adibeig, Naiier; Shanehbandy, Samaneh

doi:10.1016/j.eswa.2016.09.025

Cited by 172 publications

(82 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the unsupervised method, the goal is to intrinsically group unlabeled data without predefined data groups. [20][21][22][23] In conventional two-dimensional (2-D) microscopic imaging techniques, it is difficult to detect the three-dimensional (3-D) shape of erythrocytes; thus, the overall performance is not acceptable. However, digital holographic microscopy (DHM) is capable of imaging semitransparent or transparent biological cells and provides quantitative detailed information about the cell structure and its contents at a single-RBC level.…”

Section: Introductionmentioning

confidence: 99%

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

et al. 2017

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%

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

et al. 2017

View full text Add to dashboard Cite

show abstract

“…They used the method of localization by reshaping the input image into vector and then the optimized k-means algorithm is applied twice to cluster the image pixels into one class. Sina Khanmohammadi et al [13] proposed a new and improved k-means clustering algorithm knows as overlapping k-means (OKM). They also introduced hybrid method of the k-harmonic means and overlapping k-means algorithm (KHM-OKM).…”

Section: A K-means Algorithmmentioning

confidence: 99%

A Survey on Image Segmentation Methods using Clustering Techniques

Dhanachandra¹,

Chanu²

2017

EJERS

View full text Add to dashboard Cite

Image segmentation has been considered as the first step in the image processing. An efficient segmentation result would make it easier for further analysis of image processing. However, there exits many algorithms and approaches for image segmentation. Clustering is one of the commonly used image segmentation techniques. In this paper, we have briefly describe some of the clustering techniques and discuss some of the recent works by researchers on these techniques.

show abstract

“…In their research [17] proposed a hybrid model K Harmonic Means and Overlapping KMeans (KHM-OKM) for clustering medical data whereby the output of KHM is used as input to initialize the cluster centers for OKM. These researchers identified that medical datasets usually have overlapping information which required an improved overlapping k means algorithm for handling the unique nature.…”

Section: Literature Reviewmentioning

confidence: 99%