基于SVM的脑肿瘤3D-DWT特征分类

Mücahid Barstuğan
{"title":"基于SVM的脑肿瘤3D-DWT特征分类","authors":"Mücahid Barstuğan","doi":"10.56038/oprd.v2i1.239","DOIUrl":null,"url":null,"abstract":"Brain tumours are one of the most challenging medical conditions to diagnose and treat. Accurate and timely classification of brain tumours is critical for effective treatment planning and patient management. Machine learning algorithms have shown great promise in improving the accuracy of brain tumour classification. This study implemented high-grade glioma (HGG) and low-grade glioma (LGG) classification on four different 3D-MRI (magnetic resonance imaging) scans (FLAIR, T1, T1c, T2). By using four different scans, 15 different combinations were created for classification process. 3D Discrete Wavelet Transform was used to transform tumour images for feature extraction stage. 36 different wavelet types were used for image transformation. First Order Statistics (mean, variance, kurtosis, skewness, entropy, energy) were extracted from transformed images of 36 wavelet types. Support Vector Machines (SVM) algorithm classified the FOS features that were obtained on BraTS 2017 dataset. The 2-fold, 5-fold, and 10-fold cross-validations are implemented and six metrics (sensitivity, specificity, accuracy, precision, F1-score, AUC) evaluated the performance of proposed method. Consequently, proposed method achieved remarkable scores of 95.23% (sensitivity), 78.81% (specificity), 90.89% (accuracy), 92.59% (precision), 93.89% (F1-score), and 87.02% (AUC) for HGG/LGG classification of 3D brain MRI data on T1+T1c+T2 combination by 2-fold cross validation.","PeriodicalId":117452,"journal":{"name":"Orclever Proceedings of Research and Development","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Classification of 3D-DWT Features of Brain Tumours with SVM\",\"authors\":\"Mücahid Barstuğan\",\"doi\":\"10.56038/oprd.v2i1.239\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Brain tumours are one of the most challenging medical conditions to diagnose and treat. Accurate and timely classification of brain tumours is critical for effective treatment planning and patient management. Machine learning algorithms have shown great promise in improving the accuracy of brain tumour classification. This study implemented high-grade glioma (HGG) and low-grade glioma (LGG) classification on four different 3D-MRI (magnetic resonance imaging) scans (FLAIR, T1, T1c, T2). By using four different scans, 15 different combinations were created for classification process. 3D Discrete Wavelet Transform was used to transform tumour images for feature extraction stage. 36 different wavelet types were used for image transformation. First Order Statistics (mean, variance, kurtosis, skewness, entropy, energy) were extracted from transformed images of 36 wavelet types. Support Vector Machines (SVM) algorithm classified the FOS features that were obtained on BraTS 2017 dataset. The 2-fold, 5-fold, and 10-fold cross-validations are implemented and six metrics (sensitivity, specificity, accuracy, precision, F1-score, AUC) evaluated the performance of proposed method. Consequently, proposed method achieved remarkable scores of 95.23% (sensitivity), 78.81% (specificity), 90.89% (accuracy), 92.59% (precision), 93.89% (F1-score), and 87.02% (AUC) for HGG/LGG classification of 3D brain MRI data on T1+T1c+T2 combination by 2-fold cross validation.\",\"PeriodicalId\":117452,\"journal\":{\"name\":\"Orclever Proceedings of Research and Development\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-03-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Orclever Proceedings of Research and Development\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.56038/oprd.v2i1.239\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Orclever Proceedings of Research and Development","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.56038/oprd.v2i1.239","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

脑肿瘤是诊断和治疗最具挑战性的疾病之一。准确和及时的脑肿瘤分类对于有效的治疗计划和患者管理至关重要。机器学习算法在提高脑肿瘤分类的准确性方面显示出巨大的希望。本研究通过四种不同的3D-MRI(磁共振成像)扫描(FLAIR, T1, T1c, T2)对高级别胶质瘤(HGG)和低级别胶质瘤(LGG)进行分类。通过使用四种不同的扫描,创建了15种不同的组合用于分类过程。采用三维离散小波变换对肿瘤图像进行特征提取。图像变换采用了36种不同的小波变换类型。从36种小波变换后的图像中提取一阶统计量(均值、方差、峰度、偏度、熵、能量)。支持向量机(SVM)算法对BraTS 2017数据集上获得的FOS特征进行分类。进行了2倍、5倍和10倍交叉验证,并使用6个指标(灵敏度、特异性、准确性、精密度、f1评分、AUC)评估了所提方法的性能。因此,该方法经2倍交叉验证,对T1+T1c+T2组合的3D脑MRI数据进行HGG/LGG分类,获得了95.23%(敏感性)、78.81%(特异性)、90.89%(准确性)、92.59%(精密度)、93.89% (f1评分)和87.02% (AUC)的显著评分。
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
Classification of 3D-DWT Features of Brain Tumours with SVM
Brain tumours are one of the most challenging medical conditions to diagnose and treat. Accurate and timely classification of brain tumours is critical for effective treatment planning and patient management. Machine learning algorithms have shown great promise in improving the accuracy of brain tumour classification. This study implemented high-grade glioma (HGG) and low-grade glioma (LGG) classification on four different 3D-MRI (magnetic resonance imaging) scans (FLAIR, T1, T1c, T2). By using four different scans, 15 different combinations were created for classification process. 3D Discrete Wavelet Transform was used to transform tumour images for feature extraction stage. 36 different wavelet types were used for image transformation. First Order Statistics (mean, variance, kurtosis, skewness, entropy, energy) were extracted from transformed images of 36 wavelet types. Support Vector Machines (SVM) algorithm classified the FOS features that were obtained on BraTS 2017 dataset. The 2-fold, 5-fold, and 10-fold cross-validations are implemented and six metrics (sensitivity, specificity, accuracy, precision, F1-score, AUC) evaluated the performance of proposed method. Consequently, proposed method achieved remarkable scores of 95.23% (sensitivity), 78.81% (specificity), 90.89% (accuracy), 92.59% (precision), 93.89% (F1-score), and 87.02% (AUC) for HGG/LGG classification of 3D brain MRI data on T1+T1c+T2 combination by 2-fold cross validation.
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
0
期刊最新文献
Endemic Plant Classification Using Deep Neural Networks Investigation of Cooling Systems Faults, Control and Management Models The Scientometric Analysis of Material Recycling in Sustainable Construction Hybrid Beamforming for Multi User Massive MIMO Systems Development of Oil Purification Process in Metal Sheet Products
×
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