Morphological, Texture, and Color Feature Analysis for Erythrocyte Classification in Thalassemia Cases

Dyah Aruming Tyas,Tri Ratnaningsih,Sri Hartati,Agus Harjoko

doi:10.1109/access.2020.2983155

Abstract

Abnormal erythrocytes have diverse shapes. The appearance of specific erythrocyte shapes in a person's blood can indicate certain diseases, including thalassemia. We used thalassemia peripheral blood smear images and applied a segmentation process to produce single erythrocyte sub-images. Each erythrocyte has a unique shape. The selection of appropriate features to represent erythrocytes is critical for classification accuracy. We used morphological features such as moment invariants, geometry parameters of the cell and central pallor, and distance angle signature (DAS) morphological features of the cell and central pallor. We combined morphological features with texture and color features to increase the accuracy of erythrocyte classification. In this study, the multi-layer perceptron is used to classify nine shapes of erythrocytes present in thalassemia cases. The experimental results of 7108 erythrocytes indicated an accuracy of 98.11% based on the combination of features. The experimental results also show that the combination of features we proposed produced higher classification accuracy than previous work, which yielded an accuracy of 93.77%.

Highlights

The abnormal form of erythrocytes can indicate certain diseases, including thalassemia
Tyas et al.: Morphological, Texture, and Color Feature Analysis for Erythrocyte Classification in Thalassemia Cases separation in sickle cell disease was published by GonzálezHidalgo [8]
This study aims to classify nine types of erythrocytes that often appear in thalassemia cases using the combination of morphological features, texture features and color features

Summary

INTRODUCTION

The abnormal form of erythrocytes can indicate certain diseases, including thalassemia. In the thalassemia screening process, a laboratory assistant must observe and count the number of abnormal red blood cells from visual microscopic observations in peripheral blood smear preparations to assess erythrocytes. The research usually aims to count and recognize blood cells to identify diseases or abnormalities. In 2014, Tomari et al [5] classified red blood cells (RBC) in blood smear images into normal and abnormal types. Tyas et al.: Morphological, Texture, and Color Feature Analysis for Erythrocyte Classification in Thalassemia Cases separation in sickle cell disease was published by GonzálezHidalgo [8]. This study aims to classify nine types of erythrocytes that often appear in thalassemia cases using the combination of morphological features, texture features and color features. The main contribution of this paper is to identify features that can be used to distinguish nine types of erythrocytes

RELATED WORKS

SEGMENTATION

FEATURE EXTRACTION

AND DISCUSSION

Findings

CONCLUSION