一种新的混合胶囊网络和优化的学习框架,用于改进肺肿瘤分类

IF 0.1 4区 医学
M. Manimegalai, P. Suresh Kumar
{"title":"一种新的混合胶囊网络和优化的学习框架,用于改进肺肿瘤分类","authors":"M. Manimegalai, P. Suresh Kumar","doi":"10.1166/jbt.2023.3297","DOIUrl":null,"url":null,"abstract":"The development of the intelligent expert system is required mandatorily today for the clinical analysis and to make the accurate diagnosis for disease treatment. Lung cancer diagnosis requires more thorough investigation than other disease processes since it impacts equally men and\n women with a higher fatality rate. Images from a computer tomography (CT) scan can give more useful information about a lung cancer’s diagnosis. Using CT scan input images, numerous machine learning as well as deep learning techniques are developed for the improvement of the medical\n treatment process. But when it comes to developing a precise and intelligent system, research still has a dark side. This research suggests a brand-new classification model that operates on the principles of optimal learning networks and capsules. Capsule network theory is used into the suggested\n framework to enhance classification maps and consequently lower the likelihood of overfitting issues. Additionally, Whale Optimized Feed Forward Layers (WO FFL) have been used in place of the traditional neural network in the suggested study to get the best classification of malignancies in\n lung CT scan. The suggested framework’s simulation results demonstrate improved F 1-score (99.98%), specificity (99.96%), sensitivity (99.95%), and accuracy (99.99%). Additionally, the suggested framework’s performance was compared to that of other traditional system, and\n several performance metrics indicated that the suggested paradigm outperformed the alternatives.","PeriodicalId":15300,"journal":{"name":"Journal of Biomaterials and Tissue Engineering","volume":" ","pages":""},"PeriodicalIF":0.1000,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"LUNGCAPS-A Novel Hybrid Capsule Networks and Optimized Learning Framework for the Improved Classification of Lung Tumours\",\"authors\":\"M. Manimegalai, P. Suresh Kumar\",\"doi\":\"10.1166/jbt.2023.3297\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The development of the intelligent expert system is required mandatorily today for the clinical analysis and to make the accurate diagnosis for disease treatment. Lung cancer diagnosis requires more thorough investigation than other disease processes since it impacts equally men and\\n women with a higher fatality rate. Images from a computer tomography (CT) scan can give more useful information about a lung cancer’s diagnosis. Using CT scan input images, numerous machine learning as well as deep learning techniques are developed for the improvement of the medical\\n treatment process. But when it comes to developing a precise and intelligent system, research still has a dark side. This research suggests a brand-new classification model that operates on the principles of optimal learning networks and capsules. Capsule network theory is used into the suggested\\n framework to enhance classification maps and consequently lower the likelihood of overfitting issues. Additionally, Whale Optimized Feed Forward Layers (WO FFL) have been used in place of the traditional neural network in the suggested study to get the best classification of malignancies in\\n lung CT scan. The suggested framework’s simulation results demonstrate improved F 1-score (99.98%), specificity (99.96%), sensitivity (99.95%), and accuracy (99.99%). Additionally, the suggested framework’s performance was compared to that of other traditional system, and\\n several performance metrics indicated that the suggested paradigm outperformed the alternatives.\",\"PeriodicalId\":15300,\"journal\":{\"name\":\"Journal of Biomaterials and Tissue Engineering\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":0.1000,\"publicationDate\":\"2023-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Biomaterials and Tissue Engineering\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1166/jbt.2023.3297\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Biomaterials and Tissue Engineering","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1166/jbt.2023.3297","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

智能专家系统的发展是当今临床分析和准确诊断疾病治疗的必然要求。肺癌的诊断需要比其他疾病过程更彻底的调查,因为它对男性和女性的影响相同,死亡率更高。计算机断层扫描(CT)的图像可以提供更多关于肺癌诊断的有用信息。利用CT扫描输入图像,开发了许多机器学习和深度学习技术来改进医疗过程。但是,当涉及到开发一个精确和智能的系统时,研究仍然有黑暗的一面。本研究提出了一种基于最优学习网络和胶囊原理的全新分类模型。胶囊网络理论被用于建议的框架,以增强分类图,从而降低过拟合问题的可能性。此外,在本研究中,鲸鱼优化前馈层(WO FFL)已取代传统的神经网络,以获得肺部CT扫描中恶性肿瘤的最佳分类。该框架的仿真结果表明,该框架提高了f1评分(99.98%)、特异性(99.96%)、灵敏度(99.95%)和准确性(99.99%)。此外,将建议的框架的性能与其他传统系统的性能进行了比较,几个性能指标表明建议的范式优于替代方案。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
LUNGCAPS-A Novel Hybrid Capsule Networks and Optimized Learning Framework for the Improved Classification of Lung Tumours
The development of the intelligent expert system is required mandatorily today for the clinical analysis and to make the accurate diagnosis for disease treatment. Lung cancer diagnosis requires more thorough investigation than other disease processes since it impacts equally men and women with a higher fatality rate. Images from a computer tomography (CT) scan can give more useful information about a lung cancer’s diagnosis. Using CT scan input images, numerous machine learning as well as deep learning techniques are developed for the improvement of the medical treatment process. But when it comes to developing a precise and intelligent system, research still has a dark side. This research suggests a brand-new classification model that operates on the principles of optimal learning networks and capsules. Capsule network theory is used into the suggested framework to enhance classification maps and consequently lower the likelihood of overfitting issues. Additionally, Whale Optimized Feed Forward Layers (WO FFL) have been used in place of the traditional neural network in the suggested study to get the best classification of malignancies in lung CT scan. The suggested framework’s simulation results demonstrate improved F 1-score (99.98%), specificity (99.96%), sensitivity (99.95%), and accuracy (99.99%). Additionally, the suggested framework’s performance was compared to that of other traditional system, and several performance metrics indicated that the suggested paradigm outperformed the alternatives.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
332
审稿时长
>12 weeks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信