Automatic analysis system for abnormal red blood cells in peripheral blood smears. Issue 11 (2nd August 2022)

• Record Type: Journal Article
• Authors: Gil, Taeyeon; Moon, Cho‐I; Lee, Sukjun; Lee, Onseok
• Is Part Of: Microscopy research and technique. Volume 85:Issue 11(2022)
• Page Start: 3623
• Page End: 3632
• Publication Date: 2022-08-02
• Subjects: abnormal red blood cells -- automatic classification system -- geometric features -- multiple classifiers -- peripheral blood smear; Electron microscopy -- Technique -- Periodicals; Microscopy -- Periodicals; Microscopy -- Technique -- Periodicals; 502.825
• DOI: 10.1002/jemt.24215
• Languages: English
• ISSNs: 1059-910X

Abstract

Abstract: The type and ratio of abnormal red blood cells (RBCs) in blood can be identified through peripheral blood smear test. Accurate classification is important because the accompanying diseases indicated by abnormal RBCs vary. In clinical practice, this task is time‐consuming because the RBCs are manually classified. In addition, because the classification depends on the subjective criteria of pathologists, objective classification is difficult to achieve. In this paper, an automatic classification method that is solely based on images of RBCs captured under a microscope and processed using machine learning (ML) is proposed. The size and hemoglobin abnormalities of RBCs were classified by optimizing the criteria used in clinical practice. For morphologically abnormal RBCs classification, used seven geometric features information (major axis, minor axis, ratio of major and minor axis, perimeter, circularity, number of convex hulls, difference between area and convex area) and five types of multiple classifiers (Support Vector Machine, Decision Tree, K‐Nearest Neighbor, Random Forest, and Adaboost models). Among was categorized using SVM, highly accurate results (99.9%) were obtained. The classification is performed simultaneously, and results are provided to the user through a graphical user interface (GUI). Abstract : It is the result of abnormal RBCs classification using GUI. In the left section, the image ID and the whole image are displayed. In the right section, there is a part that shows the magnified crop image and the number of each type of the analysis results of RBC, and there is a part that shows the amount of RBC usage, utilization, and number of each type for the whole image, and finally, there are buttons for use GUI. RBC: red blood cell; GUI: graphical user interface; ID: identification.