Automatic analysis system for abnormal red blood cells in peripheral blood smears
- Authors
- Gil, Taeyeon; Moon, Cho-, I; Lee, Sukjun; Lee, Onseok
- Issue Date
- Nov-2022
- Publisher
- John Wiley & Sons Inc.
- Keywords
- abnormal red blood cells; automatic classification system; geometric features; multiple classifiers; peripheral blood smear
- Citation
- Microscopy Research and Technique, v.85, no.11, pp 3623 - 3632
- Pages
- 10
- Journal Title
- Microscopy Research and Technique
- Volume
- 85
- Number
- 11
- Start Page
- 3623
- End Page
- 3632
- URI
- https://scholarworks.bwise.kr/sch/handle/2021.sw.sch/21680
- DOI
- 10.1002/jemt.24215
- ISSN
- 1059-910X
1097-0029
- 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).
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Medical Sciences > Department of Medical IT Engineering > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/sch/handle/2021.sw.sch/21680)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.