Classification of breast mass in 3D ultrasound images with annotations based on convolutional neural networks

Xiaohan Kong, T. Tan, L. Bao, Guangzhi Wang
{"title":"Classification of breast mass in 3D ultrasound images with annotations based on convolutional neural networks","authors":"Xiaohan Kong, T. Tan, L. Bao, Guangzhi Wang","doi":"10.3969/J.ISSN.0258-8021.2018.04.004","DOIUrl":null,"url":null,"abstract":"The automatic classification of breast tumor in ultrasound images is of great significance to improve doctors' efficiency and reduce the rate of misdiagnosis. The novel 3D breast ultrasound data contains more information for diagnosis, but images from different directions have their distinct performance as a result of this ultrasound imaging mechanism. For this breast ultrasound data, this paper designed three kinds of convolutional neural network model using its flexibility and characteristic of learning automatically, and the three models were able to accept transverse plane images, transverse plane and coronal plane images, images and annotations information. The effects of different information fusion on the accuracy of breast tumor classification were investigated. A dataset contains 880 images (i. e., 401 benign images, 479 malign images) and their annotations were employed, and we performed 5-fold cross validation to calculate the accuracy and AUC of each model. The experimental results indicated that the models designed in this paper can deal with the images and annotations simultaneously. Compared with the single-input model, the multi-information fusion model improved the accuracy of classification by 2.91%, and achieved the accuracy of 75.11% and AUC of 0.8294. The proposed models provided a reference for the classification application of convolutional neural networks with multi-information fusion.","PeriodicalId":35998,"journal":{"name":"中国生物医学工程学报","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2018-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"中国生物医学工程学报","FirstCategoryId":"1087","ListUrlMain":"https://doi.org/10.3969/J.ISSN.0258-8021.2018.04.004","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Medicine","Score":null,"Total":0}
引用次数: 5

Abstract

The automatic classification of breast tumor in ultrasound images is of great significance to improve doctors' efficiency and reduce the rate of misdiagnosis. The novel 3D breast ultrasound data contains more information for diagnosis, but images from different directions have their distinct performance as a result of this ultrasound imaging mechanism. For this breast ultrasound data, this paper designed three kinds of convolutional neural network model using its flexibility and characteristic of learning automatically, and the three models were able to accept transverse plane images, transverse plane and coronal plane images, images and annotations information. The effects of different information fusion on the accuracy of breast tumor classification were investigated. A dataset contains 880 images (i. e., 401 benign images, 479 malign images) and their annotations were employed, and we performed 5-fold cross validation to calculate the accuracy and AUC of each model. The experimental results indicated that the models designed in this paper can deal with the images and annotations simultaneously. Compared with the single-input model, the multi-information fusion model improved the accuracy of classification by 2.91%, and achieved the accuracy of 75.11% and AUC of 0.8294. The proposed models provided a reference for the classification application of convolutional neural networks with multi-information fusion.
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
基于卷积神经网络注释的三维超声图像乳腺肿块分类
乳腺肿瘤超声图像自动分类对提高医生工作效率、降低误诊率具有重要意义。新的乳腺三维超声数据包含了更多的诊断信息,但由于这种超声成像机制,不同方向的图像具有不同的性能。针对该乳腺超声数据,本文利用其灵活性和自动学习的特点,设计了三种卷积神经网络模型,三种模型均能接受横切面图像、横切面和冠状面图像、图像和注释信息。研究了不同信息融合对乳腺肿瘤分类准确率的影响。数据集包含880张图像(即401张良性图像,479张恶性图像),并使用它们的注释,我们进行了5倍交叉验证,以计算每个模型的准确率和AUC。实验结果表明,本文设计的模型可以同时处理图像和注释。与单输入模型相比,多信息融合模型的分类准确率提高了2.91%,准确率达到75.11%,AUC为0.8294。该模型为多信息融合卷积神经网络的分类应用提供了参考。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
中国生物医学工程学报
中国生物医学工程学报 Medicine-Medicine (miscellaneous)
CiteScore
0.40
自引率
0.00%
发文量
2798
期刊介绍: The mission of our journal: to be the bridge of the clinician, scientist and the industrial field, and to be the power of the development of biomedical engineering. The tenet of our journal: closely paying attention to and reporting the new theory, new means and new technology of biomedical engineering, tracking the newest applied achievement of biomedical engineering in clinic, serving vast clinicians, and promoting the developing of the subject of biomedical engineering. The feature of our journal: paying attention to the progress of science and technology, simultaneously, comprehensively weigh the relationship between the technology and one’s health in mind and body.
期刊最新文献
Classification of breast mass in 3D ultrasound images with annotations based on convolutional neural networks Multichannel EEG-EMG coupling analysis using a variable scale symbolic transfer entropy approach Applying visual perception information for detection analysis and automatic extraction of breast mass in mammograms Research on Medical Image Fusion Algorithms Based on Nonsubsampled Contourlet Common spatial spectral pattern for motor imagery tasks in small channel configuration
×
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