Classification of Red Blood Cells From a Geometric Morphometric Study

Abstract

Sickle cell disease causes the deformation of erythrocytes into sickle cells. The study of this process using digital images of peripheral blood smears can help specialists to quantify the number of deformed cells in order to gauge the severity of the illness. A new method for classifying red blood cells into three categories: healthy, sickle cell disease, and other deformations is proposed. This method does not require obtaining the contour of each cell but instead utilizes information obtained from a small number of points, obtained through appropriate geometric sampling and the use of stereological formulas. The parameters utilized for classification are the bending energy times length (E) and the circular shape factor (F). In normal cells, which exhibit an almost circular shape, these parameters typically have values close to (1,1). To assess the effectiveness of classification using the parameters (E,F), a synthetic curve dataset and a dataset of red blood cells are employed, applying various supervised and unsupervised classification methods.