Elephant herding optimized features-based fast RCNN for classifying leukemia stages.

IF 1.4 4区医学 Q4 ENGINEERING, BIOMEDICAL

Technology and Health Care Pub Date : 2025-01-01 DOI:10.3233/THC-240750

Della Reasa Valiaveetil, Kanimozhi T

{"title":"Elephant herding optimized features-based fast RCNN for classifying leukemia stages.","authors":"Della Reasa Valiaveetil, Kanimozhi T","doi":"10.3233/THC-240750","DOIUrl":null,"url":null,"abstract":"Background: Leukemia is a cancer that develops in the bone marrow and blood that is brought on by an excessive generation of abnormal white blood cells. This disease damages deoxyribonucleic acid (DNA), which is associated with immature cells, particularly white blood cells. It is time-consuming and requires enhanced accuracy for radiologists to diagnose acute leukemia cells.Objective: To overcome this issue, we have studied the use of a novel proposed LEU-EHO NET.Methods: LEU-EHO NET has been proposed for classifying blood smear images based on leukemia-free and leukemia-infected images. Initially, the input blood smear images are pre-processed using two techniques: normalization and cropping black edges in images. The pre-processed images are then subjected to MobileNet for feature extraction. After that, Elephant Herding Optimization (EHO) is used to select the relevant feature from the retrieved characteristics. Finally, Faster RCNN is trained with the selected features to perform the classification task and discriminate between Normal and Abnormal.Results: The total accuracy of the proposed LEU-EHO NET is 99.30%. The proposed LEU-EHO NET model enhances the overall accuracy by 0.69%, 16.21%, 1.10%, 1.71%, and 1.38% better than Inception v3 XGBoost, VGGNet, DNN, SVM and MobilenetV2 respectively.Conclusion: The approach needs to be improved so that overlapped cells can be segmented more accurately. Additionally, future work might improve classification accuracy by utilizing different deep learning models.","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":" ","pages":"167-183"},"PeriodicalIF":1.4000,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Technology and Health Care","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.3233/THC-240750","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, BIOMEDICAL","Score":null,"Total":0}

引用次数: 0

Abstract

Background: Leukemia is a cancer that develops in the bone marrow and blood that is brought on by an excessive generation of abnormal white blood cells. This disease damages deoxyribonucleic acid (DNA), which is associated with immature cells, particularly white blood cells. It is time-consuming and requires enhanced accuracy for radiologists to diagnose acute leukemia cells.

Objective: To overcome this issue, we have studied the use of a novel proposed LEU-EHO NET.

Methods: LEU-EHO NET has been proposed for classifying blood smear images based on leukemia-free and leukemia-infected images. Initially, the input blood smear images are pre-processed using two techniques: normalization and cropping black edges in images. The pre-processed images are then subjected to MobileNet for feature extraction. After that, Elephant Herding Optimization (EHO) is used to select the relevant feature from the retrieved characteristics. Finally, Faster RCNN is trained with the selected features to perform the classification task and discriminate between Normal and Abnormal.

Results: The total accuracy of the proposed LEU-EHO NET is 99.30%. The proposed LEU-EHO NET model enhances the overall accuracy by 0.69%, 16.21%, 1.10%, 1.71%, and 1.38% better than Inception v3 XGBoost, VGGNet, DNN, SVM and MobilenetV2 respectively.

Conclusion: The approach needs to be improved so that overlapped cells can be segmented more accurately. Additionally, future work might improve classification accuracy by utilizing different deep learning models.

查看原文本刊更多论文

基于大象放牧优化特征的快速 RCNN 用于白血病分期分类

背景介绍白血病是一种发生在骨髓和血液中的癌症，由异常白细胞的过度生成引起。这种疾病会破坏脱氧核糖核酸（DNA），而脱氧核糖核酸与未成熟细胞尤其是白细胞有关。放射科医生诊断急性白血病细胞既费时又需要更高的准确性：为了解决这一问题，我们研究了一种新型 LEU-EHO NET 的使用方法：方法：LEU-EHO NET 是一种基于无白血病和白血病感染图像的血涂片图像分类方法。首先，使用两种技术对输入的血涂片图像进行预处理：归一化和裁剪图像中的黑边。然后，将预处理后的图像交由 MobileNet 进行特征提取。然后，使用大象放牧优化（EHO）从检索到的特征中选择相关特征。最后，利用选定的特征训练 Faster RCNN，以执行分类任务并区分正常和异常：结果：提议的 LEU-EHO NET 的总准确率为 99.30%。与 Inception v3 XGBoost、VGGNet、DNN、SVM 和 MobilenetV2 相比，拟议的 LEU-EHO NET 模型分别提高了 0.69%、16.21%、1.10%、1.71% 和 1.38%：该方法有待改进，以便更准确地分割重叠的细胞。此外，未来的工作可能会利用不同的深度学习模型来提高分类的准确性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Technology and Health Care HEALTH CARE SCIENCES & SERVICES-ENGINEERING, BIOMEDICAL

CiteScore

2.10

自引率

6.20%

发文量

282

审稿时长

>12 weeks

期刊介绍： Technology and Health Care is intended to serve as a forum for the presentation of original articles and technical notes, observing rigorous scientific standards. Furthermore, upon invitation, reviews, tutorials, discussion papers and minisymposia are featured. The main focus of THC is related to the overlapping areas of engineering and medicine. The following types of contributions are considered: 1.Original articles: New concepts, procedures and devices associated with the use of technology in medical research and clinical practice are presented to a readership with a widespread background in engineering and/or medicine. In particular, the clinical benefit deriving from the application of engineering methods and devices in clinical medicine should be demonstrated. Typically, full length original contributions have a length of 4000 words, thereby taking duly into account figures and tables. 2.Technical Notes and Short Communications: Technical Notes relate to novel technical developments with relevance for clinical medicine. In Short Communications, clinical applications are shortly described. 3.Both Technical Notes and Short Communications typically have a length of 1500 words. Reviews and Tutorials (upon invitation only): Tutorial and educational articles for persons with a primarily medical background on principles of engineering with particular significance for biomedical applications and vice versa are presented. The Editorial Board is responsible for the selection of topics. 4.Minisymposia (upon invitation only): Under the leadership of a Special Editor, controversial or important issues relating to health care are highlighted and discussed by various authors. 5.Letters to the Editors: Discussions or short statements (not indexed).