9 September 2015 Automated counting of morphologically normal red blood cells by using digital holographic microscopy and statistical methods
Author Affiliations +
Abstract
In this paper we overview a method to automatically count morphologically normal red blood cells (RBCs) by using off-axis digital holographic microscopy and statistical methods. Three kinds of RBC are used as training and testing data. All of the RBC phase images are obtained with digital holographic microscopy (DHM) that is robust to transparent or semitransparent biological cells. For the determination of morphologically normal RBCs, the RBC’s phase images are first segmented with marker-controlled watershed transform algorithm. Multiple features are extracted from the segmented cells. Moreover, the statistical method of Hotelling’s T-square test is conducted to show that the 3D features from 3D imaging method can improve the discrimination performance for counting of normal shapes of RBCs. Finally, the classifier is designed by using statistical Bayesian algorithm and the misclassification rates are measured with leave-one-out technique. Experimental results show the feasibility of the classification method for calculating the percentage of each typical normal RBC shape.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Inkyu Moon, Inkyu Moon, Faliu Yi, Faliu Yi, } "Automated counting of morphologically normal red blood cells by using digital holographic microscopy and statistical methods", Proc. SPIE 9598, Optics and Photonics for Information Processing IX, 95980G (9 September 2015); doi: 10.1117/12.2185576; https://doi.org/10.1117/12.2185576
PROCEEDINGS
5 PAGES


SHARE
Back to Top