机器学习在乳腺肿瘤分类检测中的应用研究

摘要/Abstract

摘要：

机器学习算法在医学检测与诊断，尤其是乳腺肿瘤分类检测与诊断中扮演愈发重要的角色。分析比较了

几种经典机器学习分类器在乳腺肿瘤分类检测中的性能，并从准确率、灵敏度、特异性及执行效率等方

面对各分类器的性能进行了评估比较，根据在不同数据库上的实验结果，总结了各机器学习分类器在乳

腺肿瘤分类中的性能特点：线性判别分析和极限学习机两种分类器性能优良且训练效率很高；支持向量

机性能较为平均且非常稳定，但训练耗时较长；而人工神经网络分类器虽然可以给出良好的特异性指标

，但灵敏度指标不够理想。

关键词: 乳腺肿瘤, 机器学习, 性能比较

Abstract:

Machine learning algorithms are playing an increasingly important role in medical detection

and diagnosis, especially for breast tumor classification, detection and diagnosis. We

evaluate these machine learning methods based on criterions including accuracy,

sensitivity, specificity and efficiency. We then summarize the characteristics of different

classifiers according to the experimental results of different breast tumor databases: all

of the classifiers can achieve relatively ideal performance in terms of testing efficiency.

The linear discriminant analysis and the extreme learning machine have excellent

classification performance and high training efficiency while the support vector machine

has average classification performance and a long training time, and the artificial neural

network has relatively low sensitivity but an extremely high specificity.

Key words: breast tumor, machine learning, performance comparison

李喆，吕卫，闵行，褚晶辉. 机器学习在乳腺肿瘤分类检测中的应用研究[J]. 计算机工程与科学.

LI Zhe,L Wei,MIN Hang,CHU Jinghui.

Application of machine learning

algorithms in breast tumor detection

[J]. Computer Engineering & Science.

参考文献

［1］Mitchell T. Machine learning［M］. Beijing: China Machine Press,2003.

［2］Ganesan K,Acharya U R,Chua C K,et al.Computeraided breast cancer detection using

mammograms:A review［J］.IEEE Reviews in Biomedical Engineering,2013,6(77):98.

［3］Orozco H M,Villegas O V,Maynez L O,et al.Lung nodule classification in frequency

domain using support vector machines［C］∥
Proc of 2012 11th International Conference on Information Science,Signal Processing and

their Applications （ISSPA）,2012:870875.

［4］Pinheiro F M R,Kuo M H.Poster:Applying data mining algorithms to early detection of

liver cancer［C］∥
Proc of 2012 IEEE 2nd International Conference on Computational Advances in Bio and Medical

Sciences (ICCABS),2012:1.

［5］Pei Chengdan,Xu Shengzhou.Segmentation of mammography images based on the label

controlling watershed algorithm［J］.Science Technology and Engineering，2013，13（5）:1210

1214.(in Chinese)

［6］Wang Zhiqiong,Kang Yan,Yu Ge,et al.Breast tumor detection algorithm based on feature

selection ELM［J］.Journal of Northeastern University（Natural Science），2013，34（6）:792

796.(in Chinese)

［7］Japkowicz N.Learning from imbalanced data sets:A comparison of various strategies［C］

∥Proc of AAAI’2000 Workshop on Learning from Imbalanced Data Sets,2000:1015.

［8］Tan P N,Steinbach M,Kumar V.Introduction to data mining［M］.Beijing:Posts & Telecom

Press,2006:426.

［9］Duda R O.Pattern recognition［M］.2nd edition.Beijing:China Machine Press,2004.

［10］Liu X M,Tang J S.Mass classification in mammograms using selected geometry and

texture features,and a new SVMbased feature selection method［J］.IEEE Systems

Journal,2014,8(3):910920.

［11］Li Zhenxiang,Wang Wenjian,Guo Husheng, et al.SVM classification algorithm for

solving multiclass imbalance data［J］.Computer Engineering and Design，2014，35

（7）:24992503.(in Chinese)

［12］Zhang Zheng,Wang Yanping,Xue Guixiang.Digital image processing and machine

vision:Implemented by Visual C++ and Matlab［M］.Beijing:Posts & Telecom Press,2010.(in

Chinese)

［13］Harrington P.Machine learning in action［M］.Beijing:Posts and Telecom Press，2013.

［14］Wang Zhihui.Research on BP neural networks and ELM algorithms［D］.Hangzhou:China

Jiliang University,2012.(in Chinese)

［15］Haykin S.Neural networks and learning machines［M］.third Edition. Beijing:China

Machine Press,2009.

［16］Yang Xiaofan,Chen Tinghuai.Advantages and disadvantages of artificial neural

networks［J］.Computer Science,1994,21（2）:2326.(in Chinese)

［17］Huang G B,Zhou H M,Ding X J,et al.Extreme learning machine for regression and

multiclass classification［J］.IEEE Transactions on Systems,Man,and Cybernetics,Part

B:Cybernetics,
2012,42(2):513529.

［18］Huang G B,Zhu Q Y,Siew C K.Extreme learning machine:A new learning scheme of

feedforward neural networks［C］∥

Proc of 2004 IEEE International Joint Conference on Neural Networks,
2004:2529.

［19］Menaka K,Karpagavalli S.Mammogram classification using extreme learning machine and

genetic programming［C］∥Proc of 2014 International Conference on Computer Communication

and Informatics （ICCCI）,2014:17.

［20］Heath M,Bowyer K,Kopans D,et al.The digital databasefor screening mammography［C］∥

Proc of the 5th International Workshop on Digital Mammography,2000:212218.

［21］Cascio D,Fauci F,Magro R，et al.Mammogram segmentation by contour searching and mass

lesions classification with neural network ［J］.IEEE Transactions on Nuclear Science,
2006,53(5):28272833.

［22］Pradeep N,Girisha H,Sreepathi B,et al.Feature extraction of mammograms

［J］.International Journal of Bioinformatics Research,
2012，4(1):241244.

［23］Lichman M. UCI machine learning repository ［DB/OL］.［201507

01］.http://archive.ics.uci.edu/ml.Irvine.

［24］Chang C C,Lin C J.LIBSVM:A library for support vector machines［J］.ACM Transactions

on Intelligent Systems and Technology,
2011,2(23):127.

附中文参考文献:

［5］裴承丹，徐胜舟.基于标记控制分水岭算法的乳腺X线摄片分割［J］.科学技术与工程，2013，13（

5）:12101214．

［6］王之琼，康雁，于戈,等.基于特征选择ELM的乳腺肿块检测算法［J］.东北大学学报（自然科学版

），2013，34（6）:792796．

［11］李珍香，王文剑，郭虎升,等.处理多类不平衡数据的SVM分类算法［J］.计算机工程与设计，2014

，35（7）:24992503.

［12］张铮，王艳平，薛桂香.数字图像处理与机器视觉：Visual C++与Matlab处理［M］.北京：人民邮

电出版社，2010.

［14］王智慧.BP神经网络和ELM算法研究［D］.杭州：中国计量学院,2012.

［16］杨晓帆，陈廷槐.人工神经网络固有的优点和缺点［J］.计算机科学，1994，21（2）:2326.

[1]	赵振宇, 杨天豪, 蒋汶乘, 张书政. 基于机器学习的多压多温多参标准单元延迟快速计算方法[J]. 计算机工程与科学, 2023, 45(08): 1331-1338.
[2]	李小玲, 方建滨, 马俊, 谭霜, 谭郁松. 基于监督学习的稀疏矩阵自动任务分配[J]. 计算机工程与科学, 2023, 45(05): 782-789.
[3]	胡艳芳, 熊文, 高炜. 基于 Spark 平台的网络游戏用户流失预测方法[J]. 计算机工程与科学, 2022, 44(10): 1730-1737.
[4]	唐阳坤, 鲜港, 杨文祥, 喻杰, 张晓蓉, 王耀彬. 基于用户行为的超级计算机作业失败预测方法[J]. 计算机工程与科学, 2022, 44(10): 1753-1761.
[5]	楚阳, 徐文龙. 基于计算机辅助诊断技术的阿尔兹海默症早期分类研究综述[J]. 计算机工程与科学, 2022, 44(05): 879-893.
[6]	崔弘, 赵双, 张广胜, 苏金树. 基于机器学习的移动代理应用流量识别方法[J]. 计算机工程与科学, 2022, 44(04): 654-664.
[7]	刘国强, 赵振宇, 赵晨煜, 韩奥, 杨天豪. 基于机器学习的PCB布线电阻计算方法[J]. 计算机工程与科学, 2022, 44(03): 396-402.
[8]	李文丽. 基于朴素贝叶斯分类的网络谣言识别研究[J]. 计算机工程与科学, 2022, 44(03): 495-501.
[9]	曹良林, 贲可荣, 张献. 基于代理辅助多目标萤火虫算法的软件缺陷预测方法研究[J]. 计算机工程与科学, 2022, 44(02): 257-265.
[10]	张家灏, 邓科峰, 聂腾飞, 任开军, 宋君强. 基于机器学习的海洋中尺度涡检测识别研究综述[J]. 计算机工程与科学, 2021, 43(12): 2115-2125.
[11]	欧琦媛, 祝恩. 基于压缩子空间对齐的多核聚类算法[J]. 计算机工程与科学, 2021, 43(10): 1730-1735.
[12]	何静, 李晋文, 杨安毅. 基于机器学习方法的高速信道建模研究[J]. 计算机工程与科学, 2021, 43(06): 984-988.
[13]	曾杰, 贲可荣, 张献, 徐永士. 融合文本分布式表示的重复缺陷报告检测[J]. 计算机工程与科学, 2021, 43(04): 670-680.
[14]	王思齐, 胡婧韬, 余广, 祝恩, 蔡志平. 智能视频异常事件检测方法综述[J]. 计算机工程与科学, 2020, 42(08): 1393-1405.
[15]	余华鸿, 周凤艳, 陈毛毛. 基于机器学习的KDD-CUP99网络入侵检测数据集的分析[J]. 计算机工程与科学, 2019, 41(增刊S1): 91-97.