Department of Software Convergence, Graduate School, Soonchunhyang University, Asan City, Chungnam-do, Republic of Korea.
Department of Biomedical Laboratory Science, College of Health and Medical Sciences, Cheongju University, Cheongju City, Chungbuk, Republic of Korea.
Microsc Res Tech. 2022 Nov;85(11):3623-3632. doi: 10.1002/jemt.24215. Epub 2022 Aug 2.
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).
通过外周血涂片检查可以识别血液中异常红细胞（RBC）的类型和比例。由于异常 RBC 所伴随的疾病各不相同，因此准确分类非常重要。在临床实践中，由于需要手动对 RBC 进行分类，因此这项任务非常耗时。此外，由于分类依赖于病理学家的主观标准，因此客观分类具有一定难度。本文提出了一种仅基于显微镜下拍摄的 RBC 图像并使用机器学习（ML）进行处理的自动分类方法。通过优化临床实践中使用的标准，对 RBC 的大小和血红蛋白异常进行了分类。对于形态异常 RBC 的分类，使用了七个几何特征信息（长轴、短轴、长轴与短轴的比例、周长、圆形度、凸壳数量、面积与凸面积之差）和五种多分类器（支持向量机、决策树、K-最近邻、随机森林和 Adaboost 模型）。其中 SVM 分类效果最好，获得了 99.9%的高精度结果。该分类可同步进行，并通过图形用户界面（GUI）向用户提供结果。
