Advertisement

Breast Lesion Discrimination Using Saliency Features from MRI Sequences and MKL-Based Classification

  • Henry Jhoán Areiza-Laverde
  • Carlos Andrés Duarte-Salazar
  • Liliana Hernández
  • Andrés Eduardo Castro-OspinaEmail author
  • Gloria M. Díaz
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11896)

Abstract

Breast MRI interpretation requires that radiologists examine several images, depending on the acquisition protocol that is managed in the health institution, a very subjective and time-consuming process that reports large variability, which affects the final diagnosis and prognosis of the patient. In this paper, we present a computational method for classifying lesions detected in breast MRI studies, which aims to reduce physician subjectivity. The proposed approach take advantage of the ability of the Multiple Kernel Learning (MKL) strategy for optimally fusing the features extracted from the different image sequences that compose a breast MRI Study, which describe the grey level distribution of the original image and its saliency map, computed using the Graph-based Visual Saliency (GBVS) algorithm. Breast lesions were classified as positive and negative findings with an accuracy of \(85.5\%\) and \(84.8\%\) when nine and five sequences were used, respectively.

Keywords

Breast MRI GBVS Machine learning MKL Visual saliency 

References

  1. 1.
    Aggarwal, N., Agrawal, R.K.: First and second order statistics features for classification of magnetic resonance brain images. J. Signal Inf. Process. 03(02), 146–153 (2012).  https://doi.org/10.4236/jsip.2012.32019CrossRefGoogle Scholar
  2. 2.
    Alpert, S., Kisilev, P.: Unsupervised detection of abnormalities in medical images using salient features. In: Medical Imaging 2014: Image Processing, vol. 9034, p. 903416. International Society for Optics and Photonics (2014)Google Scholar
  3. 3.
    Amit, G., et al.: Hybrid mass detection in breast MRI combining unsupervised saliency analysis and deep learning. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10435, pp. 594–602. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66179-7_68CrossRefGoogle Scholar
  4. 4.
    Areiza-Laverde, H.J., Díaz, G.M., Castro-Ospina, A.E.: Feature group selection using MKL penalized with \(\ell _1\)-norm and SVM as base learner. In: Figueroa-García, J.C., López-Santana, E.R., Rodriguez-Molano, J.I. (eds.) WEA 2018. CCIS, vol. 915, pp. 136–147. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-00350-0_12CrossRefGoogle Scholar
  5. 5.
    Banerjee, S., Mitra, S., Shankar, B.U., Hayashi, Y.: A novel GBM saliency detection model using multi-channel MRI. PLoS ONE 11(1), 1–16 (2016).  https://doi.org/10.1371/journal.pone.0146388CrossRefGoogle Scholar
  6. 6.
    Bickelhaupt, S., et al.: Fast and noninvasive characterization of suspicious lesions detected at breast cancer X-Ray screening: capability of diffusion-weighted MR imaging with MIPs. Radiology 278(3), 689–697 (2016).  https://doi.org/10.1148/radiol.2015150425CrossRefGoogle Scholar
  7. 7.
    Borji, A., Itti, L.: State-of-the-art in visual attention modeling. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 35(1), 185–207 (2013).  https://doi.org/10.1109/TPAMI.2012.89CrossRefGoogle Scholar
  8. 8.
    Clerc, M.: Standard particle swarm optimisation (2012)Google Scholar
  9. 9.
    Cristianini, N., Shawe-Taylor, J.: An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods. Cambridge University Press, Cambridge (2000)CrossRefGoogle Scholar
  10. 10.
    Culache, O., Obadă, D.R.: Multimodality as a premise for inducing online flow on a brand website: a social semiotic approach. Procedia - Soc. Behav. Sci. 149, 261–268 (2014).  https://doi.org/10.1016/j.sbspro.2014.08.227CrossRefGoogle Scholar
  11. 11.
    Erihov, M., Alpert, S., Kisilev, P., Hashoul, S.: A cross saliency approach to asymmetry-based tumor detection. In: MICCAI 2015: 18th International Conference on Medical Image Computing and Computer Assisted Intervention, vol. 9351, pp. 636–643 (2015).  https://doi.org/10.1007/978-3-319-24574-4Google Scholar
  12. 12.
    Gönen, M., Alpaydın, E.: Multiple kernel learning algorithms. J. Mach. Learn. Res. 12(8), 2211–2268 (2011)MathSciNetzbMATHGoogle Scholar
  13. 13.
    Harel, J., Koch, C., Perona, P.: Graph-based visual saliency. In: Advances in Neural Information Processing Systems, pp. 545–552 (2007)Google Scholar
  14. 14.
    Heller, S.L., Moy, L.: Breast MRI screening: benefits and limitations. Current Breast Cancer Rep. 8(4), 248–257 (2016).  https://doi.org/10.1007/s12609-016-0230-7CrossRefGoogle Scholar
  15. 15.
    Itti, L., Dhavale, N., Pighin, F.: Realistic avatar eye and head animation using a neurobiological model of visual attention. In: Applications and Science of Neural Networks, Fuzzy Systems, and Evolutionary Computation VI, vol. 5200, pp. 64–79. International Society for Optics and Photonics (2003)Google Scholar
  16. 16.
    Jampani, V., Sivaswamy, J., Vaidya, V.: Assessment of computational visual attention models on medical images. In: Proceedings of the Eighth Indian Conference on Computer Vision, Graphics and Image Processing - ICVGIP 2012, pp. 1–8 (2012).  https://doi.org/10.1145/2425333.2425413
  17. 17.
    Kloft, M., Brefeld, U., Sonnenburg, S., Zien, A.: Non-sparse regularization and efficient training with multiple kernels. arXiv preprint arXiv:1003.0079, vol. 186, pp. 189–190 (2010)
  18. 18.
    Mitra, S., Banerjee, S., Hayashi, Y.: Volumetric brain tumour detection from MRI using visual saliency. PLoS ONE 12(11), 1–14 (2017).  https://doi.org/10.1371/journal.pone.0187209CrossRefGoogle Scholar
  19. 19.
    Mitra, S., Banerjee, S., Hayashi, Y.: Volumetric brain tumour detection from MRI using visual saliency. PloS ONE 12(11), e0187209 (2017)CrossRefGoogle Scholar
  20. 20.
    Narváez, F., Díaz, G., Poveda, C., Romero, E.: An automatic BI-RADS description of mammographic masses by fusing multiresolution features. Expert Syst. Appl. 74, 82–95 (2017)CrossRefGoogle Scholar
  21. 21.
    Papadimitriou, C.H., Steiglitz, K.: Combinatorial Optimization: Algorithms and Complexity. Courier Corporation, North Chelmsford (1998)zbMATHGoogle Scholar
  22. 22.
    Strahle, D.A., Pathak, D.R., Sierra, A., Saha, S., Strahle, C., Devisetty, K.: Systematic development of an abbreviated protocol for screening breast magnetic resonance imaging. Breast Cancer Res. Treat. 162(2), 283–295 (2017).  https://doi.org/10.1007/s10549-017-4112-0CrossRefGoogle Scholar
  23. 23.
    Xu, Z., Jin, R., Yang, H., King, I., Lyu, M.R.: Simple and efficient multiple kernel learning by group lasso. In: Proceedings of the 27th International Conference on Machine Learning (ICML 2010), pp. 1175–1182. Citeseer (2010)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Henry Jhoán Areiza-Laverde
    • 1
  • Carlos Andrés Duarte-Salazar
    • 1
  • Liliana Hernández
    • 2
  • Andrés Eduardo Castro-Ospina
    • 1
    Email author
  • Gloria M. Díaz
    • 1
  1. 1.Instituto Tecnológico MetropolitanoMedellínColombia
  2. 2.Instituto de Alta Tecnología MédicaMedellínColombia

Personalised recommendations