基于AlexNet模型和自适应对比度增强的乳腺结节超声图像分类

计算机科学 ›› 2019, Vol. 46 ›› Issue (6A): 146-152.

基于AlexNet模型和自适应对比度增强的乳腺结节超声图像分类

陈思文^1,2, 刘玉江³, 刘冬³, 苏晨³, 赵地¹, 钱林学³, 张佩珩¹

中国科学院计算技术研究所北京100190¹;
北京邮电大学国际学院北京100089²;
首都医科大学重点实验室北京100069³

出版日期:2019-06-14 发布日期:2019-07-02
通讯作者: 赵地(1978－),男,博士,副研究员,主要研究方向为深度学习、类脑计算、脑科学,E-mail:zhaodi@escience.cn
作者简介:陈思文(1996－),女,主要研究方向为深度学习;刘玉江(1984－),男,博士,副研究员,主要研究方向为超声医学、医学人工智能;刘冬(1984－),男,博士,副研究员,主要研究方向为超声医学、医学人工智能;苏晨(1993－),女,博士,副研究员,主要研究方向为超声医学、医学人工智能;钱林学(1965－),男,博士,主要研究方向为超声医学、医学人工智能;张佩珩(1960－),男,博士,教授,主要研究方向为深度学习、类脑计算、脑科学。
基金资助:
本文受北京市自然科学基金重点项目(4161004),北京市科技计划项目(Z171100000117001,Z161100000216143),国家重点研发计划项目(2018ZX10723203)资助。

AlexNet Model and Adaptive Contrast Enhancement Based UltrasoundImaging Classification

CHEN Si-wen^1,2, LIU Yu-jiang³, LIU Dong³, SU Chen³, ZHAO Di¹, QIAN Lin-xue³, ZHANG Pei-heng¹

Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China¹;
International School,Beijing University of Posts and Telecommunications,Beijing 100089,China²;
Key Laboratory,Capital Medical University,Beijing 100069,China³

Online:2019-06-14 Published:2019-07-02

摘要/Abstract

摘要： 乳腺癌是女性是最常见的恶性肿瘤之一,其发病率有逐年增高的趋势,严重威胁着患者健康。如何取代传统活体穿刺,快速准确地对乳腺结节进行良恶性判断,近年越来越受到关注。医学研究表明,良恶性结节在边缘处呈现较为显著的差异,因此对边界加强处理的算法为判断乳腺结节良恶性的深度学习提供了新思路。文中实验数据库的构建基础得到首都医科大学附属北京友谊医院的支持。在比较5种边界增强算法后对图像进行扩增,并采用在图像分类方面十分出色的AlexNet网络模型。将分别经过线性、非线性对比度拉伸、直方图均衡化、直方图阈值化以及自适应对比度增强算法处理后的数据用于AlexNet模型,比较5种算法对AlexNet模型准确度的影响,得出更适用于乳腺结节超声图像的预处理算法。扩增后的数据集图像总数量超过一万张,其中训练集占80%,验证集与测试集各占10%。最终,通过绘制ROC曲线计算敏感度、特异度、精确度参数,对测试结果进行评估,并得到了较好的测试结果。

关键词: AlexNet模型, 卷积神经网络, 乳腺癌, 乳腺结节, 深度学习, 图像预处理, 自适应增强对比度算法

Abstract: Breast cancer is one of the most common malignant tumors of women.The incidence of breast cancer is increasing year by year,which seriously threatens the health of the patients.In recent years,more and more attention has been paid to how to replace the traditional needle biopsy in the diagnosis of benign and malignant breast nodules.Medical research shows that significant differences exist on the edge of benign and malignant nodules.So the algorithm of boundary enhancement treatment provides a new way for the study of judgment of benign and malignant breast cancer.The database was constructed with the support of Beijing Friendship Hospital which is affiliated to Capital Medical University.The images are expanded based on the comparison of 5 kinds of boundary enhancement (ACE) algorithm.AlexNet network model is used which is excellent in image classification.The data processed by linear,nonlinear contrast stretching,histogram equalization,histogram thresholding and adaptive contrast enhancement algorithm are applied to the AlexNet model.The influence of the five algorithms on the accuracy of AlexNet model is compared,and a preprocessing algorithm,which is more suitable for ultrasonic images of breast nodules,is obtained.The total number of images in the expanded data set is more than ten thousand,of which the training set is 80%,and the verification set and the test set account for 10% each.Finally,the sensitivity,specificity and accuracy parameters are calculated by plotting the ROC curve,and the test results are evaluated.The better test results are obtained.

Key words: AlexNet model, Automatic contrast enhancement algorithm, Breast cancer, Breast nodules, Convolutional neutral network, Deep learning, Image preprocessing

中图分类号:

TP391.5

陈思文, 刘玉江, 刘冬, 苏晨, 赵地, 钱林学, 张佩珩. 基于AlexNet模型和自适应对比度增强的乳腺结节超声图像分类[J]. 计算机科学, 2019, 46(6A): 146-152. https://doi.org/

CHEN Si-wen, LIU Yu-jiang, LIU Dong, SU Chen, ZHAO Di, QIAN Lin-xue, ZHANG Pei-heng. AlexNet Model and Adaptive Contrast Enhancement Based UltrasoundImaging Classification[J]. Computer Science, 2019, 46(6A): 146-152. https://doi.org/

参考文献

[1]DOI K.Computer-aided diagnosis in medical imaging:history review,current status and future potential [J].Computerized Medical Imaging and Graphics.2007,31:198-211.
[2]GUPTA A,AYHAN M,MAIDA A.Natural image bases to represent neuroimaging data[C]∥Proceedings of the 30th International Conference on Machine Learning(ICML-13).Atlanta,USA,2013:987-994.
[3]CHEN W J,MU W.Value texture feature analysis of MRI dynamic contrast enhancement in diagnosis of benign and malignant breast nodules [J].Chin. J. Med. Imaging Technol.,2017,33(5):647-651.
[4]MEHDY M M,NG P Y,SHAIR E F,et al.Artificial Neural Networks in Image Processing for Early Detection of Breast Cancer [J].Computational and Mathematical Methods in Medicine,2017:1-15.
[5]HIZUKURI A,NAKAYAMA R,ASHIBA H.Segmentation Method of Breast Masses on Ultrasonographic Images Using Level Set Method Based on Statistical Model [J].Journal of Biomedical Science and Engineering,2017,10(4):149-162.
[6]SU Y N.Automatic Detection and Classification of Breast Tumors in Ultrasonic Images Using Texture and Morphological Features [J].The Open Medical Informatics Journal,2017,11:26-37.
[7]GUO Y H,CHENG H D,ZHANG Y T.Breast Ultrasound Image Segmentation Based on Particles Swarm Optimization And The Characteristics of Breast Tissue [J].Natural Computation,2011,7(1):135-154.
[8]MINAVATHI M,MURALI S,DINESH M S.Classification of Mass in Breast Ultrasound Images using Image Processing Techniques [J].International Journal of Computer Applications,2012,42(10):29-36.
[9]BANDYOPADHYAY S K.Pre-processing of Mammogram Images [J].International Journal of Engineering Science and Technology,2010,2(11):6753-6758.
[10]ZHANG J,WANG C,CHENG Y.Comparison of despeckle filters for breast ultra- sound images [J].Circuits Syst.Signal Process,2015,34(1),185-208.
[11]QUAN L,ZHANG D,YANG Y,et al.Segmentation of tumor ultrasound image via region-based ncut method [J].Wuhan Univ.J.Nat.Sci.,2013,18(4):313-318.
[12]ZHOU Z,WU W,WU S,et al.Semiautomatic breast ultrasound image segmentation based on mean shift and graph cuts [J].Ultrason.Imaging,2014,36(4):256-276.
[13]PONS G,MART J,MART R,et al.Evaluating lesion segmentation on breast sonography as related to lesion type[J].J.Ultrasound Med.,2013,32(9):1659-1670.
[14]DEODHARE D,SURI N R,AMIT R.Preprocessing and Image Enhancement Algorithms for a Form-based Intelligent Character Recognition System [J].International Journal of Computer Scie-nce & Applications,2005,2(2):131-144.
[15]SAHINER B,CHAN H P,PETRICK N,et al.Classification of mass and normal breast tissue:a convolution neural network classifier with spatial domain and texture images [J].IEEE Trans. Med. Imaging,1996,15:598-610.
[16]GARRA B S,KRASNER B H,HORII S C,et al.Improving the distinction between benign and malignant breast lesions:the va-lue of sonographic texture analysis [J].Ultrasound Imaging 1993,15:267-285.
[17]GONZALEZ R C,WOODS R E.Image Compression in Digital Image Processing Reading,Mass [M].Wesley,1992:312-315.
[18]KARIMI B,KRZYZ·AK A.A novel technique for detecting suspicious lesions in breast ultrasoundimages.Concurrency and Computation [J].Practice and Experience,2016,28(7):2237-2260.
[19]LECUN Y,BENGIOY.Convolutional networks for images, speech,and time series[M].The Handbook of Brain Theory & Neural,1995.
[20]CHENG J Z,et al.Computer-Aided diagnosis with deep learning architecture:applications to breast lesions in us images and pulmonary nodules in CT scans.[R] Scientific Reports 6,2016.
[21]WENG S.Automating Breast Cancer Detection with Deep Learning [D].Houston,USA.Rice University,2017.

相关文章 15

[1]	周乐员, 张剑华, 袁甜甜, 陈胜勇. 多层注意力机制融合的序列到序列中国连续手语识别和翻译 Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion 计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026
[2]	徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺. 时序知识图谱表示学习 Temporal Knowledge Graph Representation Learning 计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204
[3]	饶志双, 贾真, 张凡, 李天瑞. 基于Key-Value关联记忆网络的知识图谱问答方法 Key-Value Relational Memory Networks for Question Answering over Knowledge Graph 计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277
[4]	汤凌韬, 王迪, 张鲁飞, 刘盛云. 基于安全多方计算和差分隐私的联邦学习方案 Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy 计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108
[5]	李宗民, 张玉鹏, 刘玉杰, 李华. 基于可变形图卷积的点云表征学习 Deformable Graph Convolutional Networks Based Point Cloud Representation Learning 计算机科学, 2022, 49(8): 273-278. https://doi.org/10.11896/jsjkx.210900023
[6]	王剑, 彭雨琦, 赵宇斐, 杨健. 基于深度学习的社交网络舆情信息抽取方法综述 Survey of Social Network Public Opinion Information Extraction Based on Deep Learning 计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099
[7]	郝志荣, 陈龙, 黄嘉成. 面向文本分类的类别区分式通用对抗攻击方法 Class Discriminative Universal Adversarial Attack for Text Classification 计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077
[8]	姜梦函, 李邵梅, 郑洪浩, 张建朋. 基于改进位置编码的谣言检测模型 Rumor Detection Model Based on Improved Position Embedding 计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046
[9]	陈泳全, 姜瑛. 基于卷积神经网络的APP用户行为分析方法 Analysis Method of APP User Behavior Based on Convolutional Neural Network 计算机科学, 2022, 49(8): 78-85. https://doi.org/10.11896/jsjkx.210700121
[10]	朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥. 基于注意力机制的医学影像深度哈希检索算法 Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism 计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153
[11]	孙奇, 吉根林, 张杰. 基于非局部注意力生成对抗网络的视频异常事件检测方法 Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection 计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[12]	檀莹莹, 王俊丽, 张超波. 基于图卷积神经网络的文本分类方法研究综述 Review of Text Classification Methods Based on Graph Convolutional Network 计算机科学, 2022, 49(8): 205-216. https://doi.org/10.11896/jsjkx.210800064
[13]	胡艳羽, 赵龙, 董祥军. 一种用于癌症分类的两阶段深度特征选择提取算法 Two-stage Deep Feature Selection Extraction Algorithm for Cancer Classification 计算机科学, 2022, 49(7): 73-78. https://doi.org/10.11896/jsjkx.210500092
[14]	张颖涛, 张杰, 张睿, 张文强. 全局信息引导的真实图像风格迁移 Photorealistic Style Transfer Guided by Global Information 计算机科学, 2022, 49(7): 100-105. https://doi.org/10.11896/jsjkx.210600036
[15]	戴朝霞, 李锦欣, 张向东, 徐旭, 梅林, 张亮. 基于DNGAN的磁共振图像超分辨率重建算法 Super-resolution Reconstruction of MRI Based on DNGAN 计算机科学, 2022, 49(7): 113-119. https://doi.org/10.11896/jsjkx.210600105

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed