学习率在vgg16预测痴呆严重程度中的有效性

Farhad Abedinzadeh Torghabeh, Yeganeh Modaresnia, Mohammad Mahdi khalilzadeh
{"title":"学习率在vgg16预测痴呆严重程度中的有效性","authors":"Farhad Abedinzadeh Torghabeh, Yeganeh Modaresnia, Mohammad Mahdi khalilzadeh","doi":"10.4015/s1016237223500060","DOIUrl":null,"url":null,"abstract":"Alzheimer’s disease (AD) is the leading worldwide cause of dementia. It is a common brain disorder that significantly impacts daily life and slowly progresses from moderate to severe. Due to inaccuracy, lack of sensitivity, and imprecision, existing classification techniques are not yet a standard clinical approach. This paper proposes utilizing the Convolutional Neural Network (CNN) architecture to classify AD based on MRI images. Our primary objective is to use the capabilities of pre-trained CNNs to classify and predict dementia severity and to serve as an effective decision support system for physicians in predicting the severity of AD based on the degree of dementia. The standard Kaggle dataset is used to train and evaluate the classification model of dementia. Synthetic Minority Oversampling Technique (SMOTE) tackles the primary problem with the dataset, which is a disparity across classes. VGGNet16 with ReduceLROnPlateau is fine-tuned and assessed using testing data consisting of four stages of dementia and achieves an overall accuracy of 98.61% and a specificity of 99% for a multiclass classification, which is superior to current approaches. By selecting appropriate Initial Learning Rate (ILR) and scheduling it during the training phase, the proposed method has the benefit of causing the model to converge on local optimums with better performance.","PeriodicalId":8862,"journal":{"name":"Biomedical Engineering: Applications, Basis and Communications","volume":"34 1","pages":"0"},"PeriodicalIF":0.6000,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"EFFECTIVENESS OF LEARNING RATE IN DEMENTIA SEVERITY PREDICTION USING VGG16\",\"authors\":\"Farhad Abedinzadeh Torghabeh, Yeganeh Modaresnia, Mohammad Mahdi khalilzadeh\",\"doi\":\"10.4015/s1016237223500060\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Alzheimer’s disease (AD) is the leading worldwide cause of dementia. It is a common brain disorder that significantly impacts daily life and slowly progresses from moderate to severe. Due to inaccuracy, lack of sensitivity, and imprecision, existing classification techniques are not yet a standard clinical approach. This paper proposes utilizing the Convolutional Neural Network (CNN) architecture to classify AD based on MRI images. Our primary objective is to use the capabilities of pre-trained CNNs to classify and predict dementia severity and to serve as an effective decision support system for physicians in predicting the severity of AD based on the degree of dementia. The standard Kaggle dataset is used to train and evaluate the classification model of dementia. Synthetic Minority Oversampling Technique (SMOTE) tackles the primary problem with the dataset, which is a disparity across classes. VGGNet16 with ReduceLROnPlateau is fine-tuned and assessed using testing data consisting of four stages of dementia and achieves an overall accuracy of 98.61% and a specificity of 99% for a multiclass classification, which is superior to current approaches. By selecting appropriate Initial Learning Rate (ILR) and scheduling it during the training phase, the proposed method has the benefit of causing the model to converge on local optimums with better performance.\",\"PeriodicalId\":8862,\"journal\":{\"name\":\"Biomedical Engineering: Applications, Basis and Communications\",\"volume\":\"34 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.6000,\"publicationDate\":\"2023-05-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Biomedical Engineering: Applications, Basis and Communications\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.4015/s1016237223500060\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"ENGINEERING, BIOMEDICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biomedical Engineering: Applications, Basis and Communications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4015/s1016237223500060","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, BIOMEDICAL","Score":null,"Total":0}
引用次数: 0

摘要

阿尔茨海默病(AD)是全球痴呆症的主要原因。这是一种常见的脑部疾病,严重影响日常生活,从中度到重度进展缓慢。由于不准确、缺乏敏感性和不精确,现有的分类技术尚未成为标准的临床方法。本文提出利用卷积神经网络(CNN)架构对基于MRI图像的AD进行分类。我们的主要目标是利用预训练cnn的能力来分类和预测痴呆症的严重程度,并作为一个有效的决策支持系统,帮助医生根据痴呆症的程度来预测AD的严重程度。使用标准的Kaggle数据集来训练和评估痴呆症的分类模型。合成少数派过采样技术(SMOTE)解决了数据集的主要问题,即不同类别之间的差异。使用ReduceLROnPlateau的VGGNet16使用由痴呆四个阶段组成的测试数据进行微调和评估,总体准确率为98.61%,多类别分类特异性为99%,优于目前的方法。通过选择合适的初始学习率(ILR)并在训练阶段调度,该方法可以使模型收敛到局部最优并具有更好的性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
EFFECTIVENESS OF LEARNING RATE IN DEMENTIA SEVERITY PREDICTION USING VGG16
Alzheimer’s disease (AD) is the leading worldwide cause of dementia. It is a common brain disorder that significantly impacts daily life and slowly progresses from moderate to severe. Due to inaccuracy, lack of sensitivity, and imprecision, existing classification techniques are not yet a standard clinical approach. This paper proposes utilizing the Convolutional Neural Network (CNN) architecture to classify AD based on MRI images. Our primary objective is to use the capabilities of pre-trained CNNs to classify and predict dementia severity and to serve as an effective decision support system for physicians in predicting the severity of AD based on the degree of dementia. The standard Kaggle dataset is used to train and evaluate the classification model of dementia. Synthetic Minority Oversampling Technique (SMOTE) tackles the primary problem with the dataset, which is a disparity across classes. VGGNet16 with ReduceLROnPlateau is fine-tuned and assessed using testing data consisting of four stages of dementia and achieves an overall accuracy of 98.61% and a specificity of 99% for a multiclass classification, which is superior to current approaches. By selecting appropriate Initial Learning Rate (ILR) and scheduling it during the training phase, the proposed method has the benefit of causing the model to converge on local optimums with better performance.
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
Biomedical Engineering: Applications, Basis and Communications
Biomedical Engineering: Applications, Basis and Communications Biochemistry, Genetics and Molecular Biology-Biophysics
CiteScore
1.50
自引率
11.10%
发文量
36
审稿时长
4 months
期刊介绍: Biomedical Engineering: Applications, Basis and Communications is an international, interdisciplinary journal aiming at publishing up-to-date contributions on original clinical and basic research in the biomedical engineering. Research of biomedical engineering has grown tremendously in the past few decades. Meanwhile, several outstanding journals in the field have emerged, with different emphases and objectives. We hope this journal will serve as a new forum for both scientists and clinicians to share their ideas and the results of their studies. Biomedical Engineering: Applications, Basis and Communications explores all facets of biomedical engineering, with emphasis on both the clinical and scientific aspects of the study. It covers the fields of bioelectronics, biomaterials, biomechanics, bioinformatics, nano-biological sciences and clinical engineering. The journal fulfils this aim by publishing regular research / clinical articles, short communications, technical notes and review papers. Papers from both basic research and clinical investigations will be considered.
期刊最新文献
CORRELATION OF POINCARE PLOT DERIVED STRESS SCORE AND HEART RATE VARIABILITY PARAMETERS IN THE ASSESSMENT OF CORONARY ARTERY DISEASE HEURISTIC-ASSISTED ADAPTIVE HYBRID DEEP LEARNING MODEL WITH FEATURE SELECTION FOR EPILEPSY DETECTION USING EEG SIGNALS MAGNETIC RESONANCE IMAGE DENOIZING USING A DUAL-CHANNEL DISCRIMINATIVE DENOIZING NETWORK PREDICTION OF EPILEPSY BASED ON EEMD AND LSSVM DOUBLE CLASSIFICATION FILTER SELECTION FOR REMOVING NOISE FROM CT SCAN IMAGES USING DIGITAL IMAGE PROCESSING ALGORITHM
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1