期刊文献+

基于PSVM的主动学习肿块检测方法 被引量:3

A PSVM-Based Active Learning Method for Mass Detection
下载PDF
导出
摘要 肿块区域通常形态各异、差异性较大,并且与正常组织相比没有明显的区别,严重影响了肿块自动检测系统的性能.为了能够有效地提高乳腺X线图像中肿块的检测灵敏度,通过引入包含了样本间相互制约关系的具有成对约束的SVM (PSVM)算法,提出了一种基于PSVM 的主动学习机制.其中,由系统根据样本的不确定性和相互之间的特征匹配距离,主动选择应该反馈给训练集的成对样本.实验结果表明,这种基于PSVM的主动学习方法,能够充分利用样本所包含的信息,使得检测方法具有更好的推广能力和检测性能. In mammograms,masses always vary widely in their shapes and densities,and yet share common appearances with the normal tissues.This point extremely increases the detection difficulty and also impacts the performance of the automatic mass detecting system.To improve the sensitivity of mass detection system,we propose an active learning scheme to detect various masses on mammograms.Firstly,the pairwise constraints are introduced,and the scheme conducts with pairwise support vector machine(PSVM) by involving the relationship among different samples into the classification procedure.Furthermore,according to the detection results,the missed samples with their uncertainty information are combined with the matched feature distance among different samples to provide for re-consideration.Then,with the representative information,the proposed PSVM-based method actively selects the pairwise samples that should be feed back to the training set.The experimental results show that the proposed active learning method with PSVM could make full use of the information of samples,and thus,it could get satisfactory detection rates and false positives during the detection procedure.The method can also get good compromise between the sensitivity and specificity,and the whole learning scheme has better generalization ability and detection performance in comparison with some existing detection methods.
出处 《计算机研究与发展》 EI CSCD 北大核心 2012年第3期572-578,共7页 Journal of Computer Research and Development
基金 国家杰出青年科学基金项目(61125204) 国家自然科学基金项目(61172146) 中央高校基本科研业务费专项资金(K50510020013) 陕西省自然科学基础研究计划资助项目(2011JQ8018)
关键词 计算机辅助检测 肿块检测 成对约束 成对约束支持向量机 主动学习 computer aided detection mass detection pairwise constraints pairwise support vector machine(PSVM) active learning
  • 相关文献

参考文献18

  • 1American Cancer Society. The statistics and figures of cancers in 2009 [EB/OL]. [ 2010-01-19 ]. http://www. cancer, org/downloads/STT/500809web, pdf.
  • 2Mudigonda N R, Rangayyan R M, Desautels J E Leo. Detection of breast masses in mammograms by density slicing and texture flow-field analysis [J]. IEEE Trans on Medical Imaging, 2001, 20(12): 1215-1227.
  • 3Timp S, Karssemeijer N. Interval change analysis to improve computer aided detection in mammography [J]. Medical Image Analysis, 2006, 10(1): 82-95.
  • 4Eltonsy N H, Tourassi G D, Elmaghraby A S. A concentric morphology model for the detection of masses in mammography [J]. IEEE Trans on Medical Imaging, 2007, 26(6) : 880-889.
  • 5王磊,朱淼良,邓丽萍,袁昕.一种基于二维粒子的自动检测乳腺钼靶片上微钙化点簇的方法[J].计算机研究与发展,2009,46(9):1438-1445. 被引量:5
  • 6EI-Naqa I, Yang Y, Werniek M N. A support vector machine approach for detection of microcalcifications [J]. IEEE Trans on Medical Imaging, 2002, 21(12): 1552-1563.
  • 7Campanini R, Dongiovanni E, Iampieri E. A novel featureless approach to mass detection in digital mammograms based on support vector machines[J].Physics Medicine Biology, 2002, 49(6): 961-975.
  • 8Mavroforakis M E, Georgiou H V, Dimitropoulos N, et al. Mammographic masses characterization based on localized texture and dataset fractal analysis using linear, neural and support vector machine classifiers [J]. Artificial Intelligence in Medicine, 2006, 37(2):145-162.
  • 9Mu T, Nandi A K, Rangayyan R M. Analysis of breast tumors in mammograms using the pairwise Rayleigh quotient classifier [J]. Journal Electronic Imaging, 2007, 16 (4) : 043004.
  • 10王颖,高新波.基于支持向量机和相关反馈技术的肿块检测算法[J].西安电子科技大学学报,2007,34(2):239-245. 被引量:2

二级参考文献42

共引文献6

同被引文献27

  • 1庄东,陈英.基于加权近似支持向量机的文本分类[J].清华大学学报(自然科学版),2005,45(S1):1787-1790. 被引量:16
  • 2吴宗亮,窦衡.一种广义最小二乘支持向量机算法及其应用[J].计算机应用,2009,29(3):877-879. 被引量:5
  • 3于湘涛,卢文秀,褚福磊.基于PSO算法的模糊PSVM及其在旋转机械故障诊断中的应用[J].振动与冲击,2009,28(11):183-186. 被引量:4
  • 4张猛,付丽华,王高峰.模糊临近支持向量机[J].计算机工程与应用,2005,41(5):37-39. 被引量:2
  • 5WHO Media Centre. WHO Cancer Fact Sheets [ DB ]. http:// www. who. int/mediacentre/factsheets/fs297/en/index, html, 2012-2.
  • 6Tang Jinshan, et al. Computer-Aided Detection and Diagnosis of Breast Cancer with Mammography : Recent Advances [ J ]. IEEE Transactions on Information Technology in Biomedicine, 2009,2 (13) : 236-251.
  • 7National Cancer Institute. NCI Cancer Fact Sheets[ DB ]. http:// www. cancer, gov/cancertopics/types/breast, 2012.
  • 8R Campanini, E Dongiovanni, E Iampieri. A novel featureless ap- proach to mass detection in digital mammograms based on support vector machines [ J ]. Physics Medicine Biology, 2002,49 ( 6 ) :961 -975.
  • 9M E Mavroforakis, et al. Mammographic masses characterization based on localized texture and dataset fractal analysis using linear, neural and support vector machine classifiers[J]. Artificial Intelli- gence, 2006,37(2) :145-162.
  • 10M E Tipping. Sparse Bayesian Learning and the Relevance Vector Machine [ J ]. Journal of Machine Learning Research, 2001,1:211 -244.

引证文献3

二级引证文献10

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部