Focal Liver Lesion Classification Based on Tensor Sparse Representations of Multi-phase CT Images

  • Jian Wang
  • Xian-Hua Han
  • Jiande Sun
  • Lanfen Lin
  • Hongjie Hu
  • Yingying Xu
  • Qingqing Chen
  • Yen-Wei ChenEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11165)


The bag-of-visual-words (BoVW) method has been proved to be an effective method for classification tasks in both natural imaging and medical imaging. In this paper, we propose a multilinear extension of the traditional BoVW method for classification of focal liver lesions using multi-phase CT images. In our approach, we form new volumes from the corresponding slices of multi-phase CT images and extract cubes from the volumes as local structures. Regard the high dimensional local structures as tensors, we propose a K-CP (CANDECOMP/PARAFAC) algorithm to learn a tensor dictionary in an iterative way. With the learned tensor dictionary, we can calculate sparse representations of each group of multi-phase CT images. The proposed tensor was evaluated in classification of focal liver lesions and achieved better results than conventional BoVW method.


Multi-phase CT Tensor analysis Sparse coding Image classification Focal liver lesion 



This research was supported in part by the Grant-in Aid for Scientific Research from the Japanese Ministry for Education, Science, Culture and Sports (MEXT) under the Grant No. 18H03267, and No. 18H04747, in part by the Key Science and Technology Innovation Support Program of Hangzhou under the Grant No.20172011A038, and in part by the National Key Basic Research Program of China under the Grant No. 2015CB352400.


  1. 1.
    Mir, A.H., Hanmandlu, M., Tandon, S.N.: Texture analysis of CT-images. IEEE Eng. Med. Biol. 5, 781–786 (1995)CrossRefGoogle Scholar
  2. 2.
    Yu, M., Lu, Z., Feng, Q., Chen, W.: Liver CT image retrieval based on non-tensor product wavelet. In: International Conference on Medical Image Analysis and Clinical Applications (MIACA), pp. 67–70 (2010)Google Scholar
  3. 3.
    Duda, D., Kretowski, M., Bezy-Wendling, J.: Texture characterization for hepatic tumor recognition in multiphase CT. Biocybern. Biomed. Eng. 26(4), 15–24 (2006)Google Scholar
  4. 4.
    Roy, S., Chi, Y., Liu, J., Venkatesh, S.K., Brown, M.S.: Three-dimensional spatiotemporal features for fast content-based retrieval of focal liver lesions. IEEE Trans. Biomed. Eng. 61(11), 2768–2778 (2014)CrossRefGoogle Scholar
  5. 5.
    Xu, Y., et al.: Combined density, texture and shape features of multi-phase contrast-enhanced CT images for CBIR of focal liver lesions: a preliminary study. In: Chen, Y.-W., Toro, C., Tanaka, S., Howlett, R.J., Jain, L.C. (eds.) Innovation in Medicine and Healthcare 2015. SIST, vol. 45, pp. 215–224. Springer, Cham (2016). Scholar
  6. 6.
    Yu, M., Feng, Q., Yang, W., Gao, Y., Chen, W.: Extraction of lesion- partitioned features and retrieval of contrast-enhanced liver images. In: Computational and Mathematical Methods in Medicine (2012)CrossRefGoogle Scholar
  7. 7.
    Yang, W., Lu, Z., Yu, M., Huang, M., Feng, Q., Chen, W.: Content-based retrieval of focal liver lesions using bag-of-visual- words representations of single- and multi-phase contrast-enhanced CT images. J. Digit Imaging 25, 708–719 (2012)CrossRefGoogle Scholar
  8. 8.
    Diamant, I., et al.: Improved patch based automated liver lesion classification by separate analysis of the interior and boundary regions. IEEE J. Biomed. Health Inform. 20(6), 1585–1594 (2016)CrossRefGoogle Scholar
  9. 9.
    Xu, Y., et al.: Bag of temporal co-occurrence words for retrieval of focal liver lesions using 3D multiphase contrast-enhanced CT images. In: 2016 23rd International Conference on Pattern Recognition (ICPR 2016) (2016)Google Scholar
  10. 10.
    Xu, Y., et al.: Texture-specific bag of visual words model and spatial cone matching-based method for the retrieval of focal liver lesions using multiphase contrast-enhanced CT images. Int. J. Comput. Assist. Radiol. Surg. 13(1), 151–164 (2018)CrossRefGoogle Scholar
  11. 11.
    Diamant, I., Klang, E., Amitai, M., Konen, E., Goldberger, J., Greenspan, H.: Task-driven dictionary learning based on mutual information for medical image classification. IEEE Trans. Biomed. Eng. 64(6), 1380–1392 (2017)CrossRefGoogle Scholar
  12. 12.
    Wang, J., et al.: Sparse codebook model of local structures for retrieval of focal liver lesions using multi-phase medical images. Int. J. Biomed. Imaging. vol. 2017, Article ID 1413297, 13 pages (2017)Google Scholar
  13. 13.
    Litjens, G.: A survey on deep learning in medical image analysis. Med. Image Anal. 42(9), 60–88 (2017)CrossRefGoogle Scholar
  14. 14.
    Kolda, T.G., Bader, B.W.: Tensor decompositions and applications. SIAM Rev. 51(3), 455–500 (2009)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Foruzan, A.H., Chen, Y.-W.: Improved segmentation of low-contrast lesions using sigmoid edge model. Int. J. CARS 11(7), 1267–1283 (2016)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Jian Wang
    • 1
    • 2
  • Xian-Hua Han
    • 3
  • Jiande Sun
    • 1
  • Lanfen Lin
    • 4
  • Hongjie Hu
    • 5
  • Yingying Xu
    • 4
  • Qingqing Chen
    • 5
  • Yen-Wei Chen
    • 2
    • 4
    Email author
  1. 1.School of Information Science and EngineeringShandong Normal UniversityJinanChina
  2. 2.College of Information Science and EngineeringRitsumeikan UniversityKyotoJapan
  3. 3.Faculty of ScienceYamaguchi UniversityYamaguchiJapan
  4. 4.College of Computer Science and TechnologyZhejiang UniversityHangzhouChina
  5. 5.Department of RadiologySir Run Run Shaw HospitalHangzhouChina

Personalised recommendations