Digital holographic microscopy can provide quantitative phase images (QPIs) of 3D profile of red blood cell (RBC) with nanometer accuracy. In this paper we propose applying k-means clustering method to cluster RBCs into two groups of young and old RBCs by using a four-dimensional feature vector. The features are RBC thickness average, surface area-volume ratio, sphericity coefficient and RBC perimeter that can be obtained from QPIs. The proposed features are related to the morphology of RBC. The experimental result shows that by utilizing the proposed method two groups of sphero-echinocytes (old RBCs) and non-spheroechinocytes RBCs can be perfectly clustered.

© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.

K. Jaferzadeh, E. Ahmadzadeh, I. Moon, and S. Gholami, "Clustering of red blood cells using digital holographic microscopy," Proc. SPIE 10233, Holography: Advances and Modern Trends V, 102331E (Presented at SPIE Optics + Optoelectronics: April 27, 2017; Published: 15 May 2017); https://doi.org/10.1117/12.2264886.