用于乳腺癌检测的定制卷积神经网络

Thyagaraj T, Keshava Prasanna, Hariprasad S A
{"title":"用于乳腺癌检测的定制卷积神经网络","authors":"Thyagaraj T, Keshava Prasanna, Hariprasad S A","doi":"10.35940/ijeat.b4334.1213223","DOIUrl":null,"url":null,"abstract":"Breast cancer remains a serious global health issue. Leveraging the use of deep learning techniques, this study presents a custom Convolutional Neural Network (CNN) framework for the detection of breast cancer. With the specific objective of accurate classification of breast cancer, a framework is made to analyze high-dimensional medical image information. The CNN's architecture, which consists of specifically developed layers and activation components tailored for the categorization of breast cancer, is described in detail. Utilizing the BreakHis dataset, which comprises biopsy slide images of patients in a range of cancer stages, the model is trained and verified. Comparing our findings to conventional techniques, we find notable gains in sensitivity, specificity, and accuracy. Gray-Level Co-Occurrence Matrix (GLCM) features extracted from the BreakHis dataset was used to analyze the performance on sequential neural network, transfer learning and machine learning models. After analysis, we have proposed hybrid models of CNN-SVM, CNN-KNN, CNN-Logistic regression and achieved accuracy of about 95.2%.","PeriodicalId":13981,"journal":{"name":"International Journal of Engineering and Advanced Technology","volume":" 36","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2023-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Custom Convolution Neural Network for Breast Cancer Detection\",\"authors\":\"Thyagaraj T, Keshava Prasanna, Hariprasad S A\",\"doi\":\"10.35940/ijeat.b4334.1213223\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Breast cancer remains a serious global health issue. Leveraging the use of deep learning techniques, this study presents a custom Convolutional Neural Network (CNN) framework for the detection of breast cancer. With the specific objective of accurate classification of breast cancer, a framework is made to analyze high-dimensional medical image information. The CNN's architecture, which consists of specifically developed layers and activation components tailored for the categorization of breast cancer, is described in detail. Utilizing the BreakHis dataset, which comprises biopsy slide images of patients in a range of cancer stages, the model is trained and verified. Comparing our findings to conventional techniques, we find notable gains in sensitivity, specificity, and accuracy. Gray-Level Co-Occurrence Matrix (GLCM) features extracted from the BreakHis dataset was used to analyze the performance on sequential neural network, transfer learning and machine learning models. After analysis, we have proposed hybrid models of CNN-SVM, CNN-KNN, CNN-Logistic regression and achieved accuracy of about 95.2%.\",\"PeriodicalId\":13981,\"journal\":{\"name\":\"International Journal of Engineering and Advanced Technology\",\"volume\":\" 36\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-12-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Engineering and Advanced Technology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.35940/ijeat.b4334.1213223\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Engineering and Advanced Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.35940/ijeat.b4334.1213223","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

乳腺癌仍然是一个严重的全球健康问题。本研究利用深度学习技术,提出了一种用于检测乳腺癌的定制卷积神经网络(CNN)框架。该框架以准确分类乳腺癌为具体目标,用于分析高维医学图像信息。CNN 的架构由专门为乳腺癌分类开发的层和激活组件组成,本文将对其进行详细介绍。利用 BreakHis 数据集对该模型进行了训练和验证,该数据集由处于不同癌症阶段的患者的活检切片图像组成。将我们的研究结果与传统技术相比较,我们发现在灵敏度、特异性和准确性方面都有显著提高。从 BreakHis 数据集中提取的灰度共生矩阵 (GLCM) 特征被用来分析顺序神经网络、迁移学习和机器学习模型的性能。经过分析,我们提出了 CNN-SVM、CNN-KNN、CNN-逻辑回归的混合模型,并取得了约 95.2% 的准确率。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Custom Convolution Neural Network for Breast Cancer Detection
Breast cancer remains a serious global health issue. Leveraging the use of deep learning techniques, this study presents a custom Convolutional Neural Network (CNN) framework for the detection of breast cancer. With the specific objective of accurate classification of breast cancer, a framework is made to analyze high-dimensional medical image information. The CNN's architecture, which consists of specifically developed layers and activation components tailored for the categorization of breast cancer, is described in detail. Utilizing the BreakHis dataset, which comprises biopsy slide images of patients in a range of cancer stages, the model is trained and verified. Comparing our findings to conventional techniques, we find notable gains in sensitivity, specificity, and accuracy. Gray-Level Co-Occurrence Matrix (GLCM) features extracted from the BreakHis dataset was used to analyze the performance on sequential neural network, transfer learning and machine learning models. After analysis, we have proposed hybrid models of CNN-SVM, CNN-KNN, CNN-Logistic regression and achieved accuracy of about 95.2%.
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
×
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