{"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}
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.