《计算机应用研究》|Application Research of Computers

基于有监督哈希的肺结节CT图像检索

Lung nodules CT image retrieval based on supervised hashing

免费全文下载 (已被下载 次)  
获取PDF全文
作者 潘玲,杜晓平,赵涓涓
机构 1.太原理工大学 计算机科学与技术学院,山西 晋中 030600;2.山西省煤炭中心医院 PETCT中心,太原 030006
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2017)09-2838-05
DOI 10.3969/j.issn.1001-3695.2017.09.061
摘要 针对传统方法在面对大量肺部数据时检索效率不高的问题,提出了一种基于有监督哈希的肺结节CT图像检索方法。通过图像预处理建立肺结节图像库,并从灰度、形态、纹理方面提取图像多特征;利用监督信息构造哈希函数,将多特征映射为低维哈希码;根据设计的自适应权重计算图像相似度,并返回相似的肺结节图像。实验结果表明,该方法能有效地实现肺结节CT图像的快速检索,对查询病灶的良恶性分类精度达到了89.45%。
关键词 肺结节;图像检索;多特征提取;有监督哈希;自适应权重;分类
基金项目 国家自然科学基金资助项目(61540007)
虚拟现实技术与系统国家重点实验室开放基金资助项目(61373100)
山西省回国留学人员科研资助项目(2016-038)
本文URL http://www.arocmag.com/article/01-2017-09-061.html
英文标题 Lung nodules CT image retrieval based on supervised hashing
作者英文名 Pan Ling, Du Xiaoping, Zhao Juanjuan
机构英文名 1.CollegeofComputerScience&Technology,TaiyuanUniversityofTechnology,JinzhongShanxi030600,China;2.PETCTCenter,ShanxiCoalCenterHospital,Taiyuan030006,China
英文摘要 In order to improve the retrieval efficiency when facing a large number of lung images, this paper presented a retrieval method for lung nodules CT image based on supervised hashing. The method firstly built lung nodules image database through image pre-procession and extracted the multi-features from gray, morphology and texture. Then, it utilized supervised information to construct hash functions and translated the multi-features into short hash codes. Finally, it retrieved the similar lung nodules CT images according to similarity calculation with adaptive weight. Experimental results show that the proposed method can effectively achieve the rapid retrieval of lung nodules CT image and the classification of benign and malignant tumor can reach 89.45%.
英文关键词 lung nodules; image retrieval; multi-feature extraction; supervised hashing; adaptive weight; classification
参考文献 查看稿件参考文献
  [1] Ng G, Song Yang, Cai Weidong, et al. Hierarchical and binary spatial descriptors for lung nodule image retrieval[C] //Proc ofInternational Conference of the IEEE Engineering in Medicine & Biology Society. 2014:6463-6466.
[2] 刘丛, 唐坚刚, 张丽红. 基于智能选择多维特征的肺部CT图像检索[J] . 计算机应用, 2010, 30(7):1867-1869.
[3] Wang Jingdong, Shen Hengtao, Songingkuan, et al. Hashing for similarity search:a survey[J] . Computer Science. 2014:arXiv:1408. 2927.
[4] Gionis A, Indyk P, Motwani R. Similarity search in high dimensions via hashing[C] //Proc of International Conference on Very Large Data Bases. 2000:518-529.
[5] Kulis B, Grauman K. Kernelized locality-sensitive hashing for scalable image search[C] //Proc of IEEE International Conference on Computer Vision. 2009:2130-2137.
[6] Weiss Y, Torralba A, Fergus R. Spectral hashing[C] //Advances in Neural Information Processing Systems. 2009:1753-1760.
[7] Gong Yunchao, Lazebnik S, Gordo A, et al. Iterative quantization:a procrustean approach to learning binary codes for large-scale image retrieval[J] . IEEE Trans on Pattern Analysis and Machine Intelligent, 2013, 35(2):2916-2929.
[8] Wang Jun, Kumar S, Chang S F. Semi-supervised hashing for scalable image retrieval[C] //Proc of IEEE Conference on Computer Vision & Pattern Recognition. Washington DC:IEEE Computer Society, 2010:3424-3431.
[9] Liu Wei, Wang Jun, Ji Rongrong, et al. Supervised hashing with kernels[C] //Proc of IEEE Conference on Computer Vision & Pattern Recognition. Washington DC:IEEE Computer Society, 2012:2074-2081.
[10] Kulis B, Darrell T. Learning to hash with binary reconstructive embeddings[C] //Advances in Neural Information Processing Systems. 2009:1042-1050.
[11] Zhang Xiaofan, Liu Wei, Zhang Shaoting. Mining histopathological images via hashing-based scalable image retrieval[C] //Proc of IEEE International Symposium on Biomedical Imaging. [S. l. ] :IEEE Press, 2014:1111-1114.
[12] Yu Xiang, Zhang Shaoting, Liu Bo, et al. Large scale medical image search via unsupervised PCA hashing[C] // Proc of Computer Vision and Pattern Recognition Workshops. 2013:393-398.
[13] Rd A S, Mclennan G, Bidaut L, et al. The lung image database consortium (LIDC) and image database resource initiative (IDRI):a completed reference database of lung nodules on CT scans[J] . Medical Physics, 2011, 38(2):915-31.
[14] 杨建峰, 赵涓涓, 强彦, 等. 结合区域生长的多尺度分水岭算法的肺分割[J] . 计算机工程与设计, 2014, 35(1):213-217.
[15] Qiang Yan, Zhang Xiaohui, Ji Guohua, et al. Automated lung nodule segmentation using an active contour model based on PET/CT images[J] . Journal of Computational & Theoretical Nanoscience, 2015, 12(8):1972-1976.
[16] Zhao Juanjuan, Ji Guohua, Qiang Yan, et al. A new method of detecting pulmonary nodules with PET/CT based on an improved watershed algorithm[J] . Plos One, 2015, 10(4):e0123694.
[17] Orozco H M, Villegas O O V, Sánchez V G C, et al. Automated system for lung nodules classification based on wavelet feature descriptor and support vector machine[J] . Biomedical Engineering Online, 2015, 14(1):1-20.
[18] Han Fangfang, Wang Huafeng, Zhang Guopeng, et al. Texture feature analysis for computer-aided diagnosis on pulmonary nodules[J] . Journal of Digital Imaging, 2015, 28(1):99-115.
[19] 付海燕. 基于图像哈希的大规模图像检索方法研究[D] . 大连:大连理工大学, 2014.
收稿日期 2016/6/27
修回日期 2016/8/15
页码 2838-2842
中图分类号 TP391.41
文献标志码 A