{"title":"RETRACTED: Lung cancer diagnosis of CT images using metaheuristics and deep learning.","authors":"Qiufang Ma, Giorgos Jimenez","doi":"10.1177/09544119221090725","DOIUrl":null,"url":null,"abstract":"","PeriodicalId":20666,"journal":{"name":"Proceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine","volume":"1 1","pages":"NP17-NP29"},"PeriodicalIF":1.7000,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1177/09544119221090725","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2022/4/21 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"ENGINEERING, BIOMEDICAL","Score":null,"Total":0}
癌症是由胸部的两个海绵状器官组成的肺部细胞不受控制的生长。这些细胞可能在一个称为转移的过程中渗透到肺外,并扩散到身体的组织和器官,增加死于这种疾病的风险。肺结节CT扫描是癌症早期诊断的方法之一。诊断肺结节的主要挑战之一是难以识别和区分肺结节和肺成分。在这项研究中,引入了一个计算机辅助检测系统来识别这些结节。在本研究中,经过图像预处理,提出了一种基于Otsu和数学形态学的图像分割方法。然后,基于一种新的元启发式方法来选择最优特征。因此,将这些特征注入到改进的基于卷积神经网络(CNN)的分类器中,以提供高精度的诊断系统。Otsu方法、特征选择和CNN分类器的优化是通过Red Fox Optimizer(RFO)算法的新修改版本建立的。然后将该方法应用于三个流行的癌症数据集,并将结果与三种最先进的方法进行比较,以显示所提出的方法的更高效率。
期刊介绍:
The Journal of Engineering in Medicine is an interdisciplinary journal encompassing all aspects of engineering in medicine. The Journal is a vital tool for maintaining an understanding of the newest techniques and research in medical engineering.