[1]王兵锐,张新刚,杨晓非.基于精简卷积神经网络的低分辨率乳腺癌识别[J].计算机技术与发展,2020,30(09):200-204.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 036]
　WANG Bing-rui,ZHANG Xin-gang,YANG Xiao-fei.Low Resolution Breast Cancer Recognition Based on Simplified Convolutional Neural Network[J].,2020,30(09):200-204.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 036]
点击复制

基于精简卷积神经网络的低分辨率乳腺癌识别()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
30
期数:
2020年09期
页码:
200-204
栏目:
应用开发研究
出版日期:
2020-09-10

文章信息/Info

Title:
Low Resolution Breast Cancer Recognition Based on Simplified Convolutional Neural Network
文章编号:
1673-629X(2020)09-0200-05
作者:
王兵锐1; 2; 张新刚1; 杨晓非2
1. 南阳师范学院 河南省智能应急研究中心,河南 南阳 473007; 2. 华中科技大学 光学与电子信息学院,湖北 武汉 430074
Author(s):
WANG Bing-rui1; 2; ZHANG Xin-gang1; YANG Xiao-fei2
1. Henan Intelligent Emergency Research Center,Nanyang Normal University,Nanyang 473007,China; 2. School of Optics and Electronics,Huazhong University of Science and Technology,Wuhan 430074,China
关键词:
卷积神经网络; 乳腺癌; 低分辨率; 精度损失; 不平衡
Keywords:
convolutional neural network; breast cancer; low resolution; accuracy loss; imbalance
分类号:
TP18
DOI:
10. 3969 / j. issn. 1673-629X. 2020. 09. 036
摘要:
乳腺癌严重威胁女性健康,应用人工智能进行及时诊断是应对乳腺癌的重要方法。 卷积神经网络(convolutional neural network,CNN)是人工智能中最经典的处理方法之一。 通常健康人数量(称作多数类数据)远大于癌症患者数量(称作少数类数据),学习后的网络模型严重倾向于多数类导致失败。 针对这种数据集不平衡问题,对多数类健康数据集采用随机下采样减少数据,对少数类癌症数据采用数据增强扩充处理,控制网络模型的权重比例,同时融合这三种方法应对数据不平衡。 针对采用的 50×50 像素癌症数据集分辨率过低的问题,调整到 100×100 像素以便提取更多细节。 提出一种 4 卷积层 CNN 网络,分别针对两种像素进行训练测试,并与经典的 16 层 VGG16 网络进行对比。 精度损失曲线和混淆矩阵的实验结果表明,提出的 CNN 的乳腺癌识别精度优于 VGG16 多达 4 个百分点。
Abstract:
Breast cancer is a serious threat to women’s health. It is an important method to diagnose breast cancer in time by using artificial intelli-gence. Convolutional neural network (CNN) is one of the most classical processing methods in artificial intelligence. Generally,the number of healthy people (called as majority data) is far greater than that of cancer patients (called as minority data),and the learned network model tends to fail in most cases. For this kind of data set imbalance,the healthy data are sub-sampled randomly. A few kinds of cancer data are augmented, and the weight proportion of network model is controlled. At the same time,these three methods are combined to deal with the imbalance of data. In order to solve the problem of low resolu-tion of 50×50 pixel cancer data set,we adjust the data set to 100×100 pixel to extract more details. A 4-convolution layer CNN network is proposed and compared with the classical 16-layer VGG16 network. Two kinds of pixels are trained and tested. The experimental results of accuracy loss curve and confusion matrix show that the recognition accuracy of breast cancer based on the proposed CNN is better than VGG16 by up to 4 percentage points.

相似文献/References:

[1]崔凤焦.表情识别算法研究进展与性能比较[J].计算机技术与发展,2018,28(02):145.[doi:10．3969/j．issn．1673－629X．2018．02．031]
　CUI Feng-jiao.Ｒesearch and Performance Comparison of Facial Expression Ｒecognition Algorithm[J].,2018,28(09):145.[doi:10．3969/j．issn．1673－629X．2018．02．031]
[2]张丹丹,李雷. 基于PCANet-RF的人脸检测系统[J].计算机技术与发展,2016,26(02):31.
　ZHANG Dan-dan,LI Lei. Face Detection System Based on PCANet-RF[J].,2016,26(09):31.
[3]陈强锐,谢世朋.基于深度学习的肺部肿瘤检测方法[J].计算机技术与发展,2018,28(04):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
　CHEN Qiang-rui,XIE Shi-peng.Lung Cancer Detection Method Based on Deep Learning[J].,2018,28(09):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
[4]郭子琰,舒心,刘常燕,等.基于ReLU 函数的卷积神经网络的花卉识别算法[J].计算机技术与发展,2018,28(05):154.[doi:10．3969/j．issn．1673－629X．2018．05．035]
　GUO Ziyan,SHU Xin,LIU Changyan,et al.A Recognition Algorithm of Flower Based on Convolution Neural Network with ReLU Function[J].,2018,28(09):154.[doi:10．3969/j．issn．1673－629X．2018．05．035]
[5]缪宇杰,吴智钧,宫 婧.基于3D 卷积的视频错帧筛选方法[J].计算机技术与发展,2018,28(05):179.[doi:10.3969/ j. issn.1673-629X.2018.05.040]
　MIAO Yu-jie,WU Zhi-jun,GONG Jing.A Wrong Temporal-order Frames Identification Method Based on 3D Convolution[J].,2018,28(09):179.[doi:10.3969/ j. issn.1673-629X.2018.05.040]
[6]吴玉枝,吴志红,熊运余.基于卷积神经网络的小样本车辆检测与识别[J].计算机技术与发展,2018,28(06):1.[doi:10.3969/ j. issn.1673-629X.2018.06.001]
　WU Yu-zhi,WU Zhi-hong,XIONG Yun-yu.Vehicle Detection and Recognition of a Few Samples Based on Convolutional Neural Network[J].,2018,28(09):1.[doi:10.3969/ j. issn.1673-629X.2018.06.001]
[7]李相桥,李晨,田丽华,等.卷积神经网络并行训练的优化研究[J].计算机技术与发展,2018,28(08):12.[doi:10.3969/ j. issn.1673-629X.2018.08.003]
　LI Xiang-qiao,LI Chen,TIAN Li-hua,et al.Research on Optimization of Parallel Training for Convolution Neural Network[J].,2018,28(09):12.[doi:10.3969/ j. issn.1673-629X.2018.08.003]
[8]邓宗平,赵启军,陈虎. 基于深度学习的人脸姿态分类方法[J].计算机技术与发展,2016,26(07):11.
　DEND Zong-ping,ZHAO Qi-jun,CHEN Hu. Face Pose Classification Method Based on Deep Learning[J].,2016,26(09):11.
[9]河海大学 计算机与信息学院,江苏 南京 0098.卷积网络的无监督特征提取对人脸识别的研究[J].计算机技术与发展,2018,28(06):17.[doi:10.3969/ j. issn.1673-629X.2018.06.004]
　DU Bai-sheng.Research on Unsupervised Feature Extraction Based on Convolutional Neural Network for Face Recognition[J].,2018,28(09):17.[doi:10.3969/ j. issn.1673-629X.2018.06.004]
[10]高翔,陈志,岳文静,等.基于视频场景深度学习的人物语义识别模型[J].计算机技术与发展,2018,28(06):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
　GAO Xiang,CHEN Zhi,YUE Wen-jing,et al.Human Semantic Recognition Model Based on Video Scene Deep Learning[J].,2018,28(09):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
[11]郝 堃,胡 磊,丁晓明.加权 Fisher 卷积神经网络乳腺癌检测模型[J].计算机技术与发展,2022,32(06):179.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 030]
　HAO Kun,HU Lei,DING Xiao-ming.A Model Based on Weighted Fisher LetNet-5 Criterion Convolutional Neural Network for Breast Cancer Detection[J].,2022,32(09):179.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 030]

更新日期/Last Update: 2020-09-10