Automatic analysis system for abnormal red blood cells in peripheral blood smears,Microscopy Research and Technique

当前位置： X-MOL 学术 › Microsc. Res. Tech. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Automatic analysis system for abnormal red blood cells in peripheral blood smears
Microscopy Research and Technique ( IF 2.0 ) Pub Date : 2022-08-02 , DOI: 10.1002/jemt.24215
Taeyeon Gil ₁ , Cho-I Moon ₁ , Sukjun Lee ₂ , Onseok Lee _{1,

3}

Affiliation

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).

中文翻译：

外周血涂片异常红细胞自动分析系统

血液中异常红细胞（RBCs）的类型和比例可以通过外周血涂片检查来确定。准确分类很重要，因为异常红细胞指示的伴随疾病各不相同。在临床实践中，这项任务非常耗时，因为红细胞是手动分类的。此外，由于分类依赖于病理学家的主观标准，客观分类难以实现。在本文中，提出了一种仅基于在显微镜下捕获并使用机器学习 (ML) 处理的红细胞图像的自动分类方法。通过优化临床实践中使用的标准对红细胞的大小和血红蛋白异常进行分类。对于形态异常的红细胞分类，使用了七种几何特征信息（长轴、短轴、长短轴比、周长、圆度、凸包数、面积与凸面积差）和五种类型的多分类器（支持向量机、决策树、K-最近邻、随机森林和 Adaboost 模型）。其中使用 SVM 进行分类，获得了高度准确的结果 (99.9%)。分类同时进行，结果通过图形用户界面 (GUI) 提供给用户。

更新日期：2022-08-02

点击分享查看原文

点击收藏

阅读更多本刊最新论文本刊介绍/投稿指南11