Advertisement

Abstract

Automatic lesion segmentation in dermoscopy images is an essential step for computer-aided diagnosis of melanoma. The dermoscopy images exhibits rotational and reflectional symmetry, however, this geometric property has not been encoded in the state-of-the-art convolutional neural networks based skin lesion segmentation methods. In this paper, we present a deeply supervised rotation equivariant network for skin lesion segmentation by extending the recent group rotation equivariant network. Specifically, we propose the G-upsampling and G-projection operations to adapt the rotation equivariant classification network for our skin lesion segmentation problem. To further increase the performance, we integrate the deep supervision scheme into our proposed rotation equivariant segmentation architecture. The whole framework is equivariant to input transformations, including rotation and reflection, which improves the network efficiency and thus contributes to the segmentation performance. We extensively evaluate our method on the ISIC 2017 skin lesion challenge dataset. The experimental results show that our rotation equivariant networks consistently excel the regular counterparts with the same model complexity under different experimental settings. Our best model also outperforms the state-of-the-art challenging methods, which further demonstrate the effectiveness of our proposed deeply supervised rotation equivariant segmentation network.

Notes

Acknowledgments

The work described in this paper was supported by a grant from the Research Grants Council of the Hong Kong Special Administrative Region (Project no. GRF 14225616) and a grant from Hong Kong Innovation and Technology Commission (Project no. ITS/426/17FP). We special thank Dr. Taco Cohen for fruitful discussions, kindly help and encouragement in our exploration.

References

  1. 1.
    Bekkers, E.J., Lafarge, M.W., Veta, M., Eppenhof, K.A., Pluim, J.P.: Roto-translation covariant convolutional networks for medical image analysis. arXiv preprint arXiv:1804.03393 (2018)
  2. 2.
    Berseth, M.: ISIC 2017-skin lesion analysis towards melanoma detection. arXiv preprint arXiv:1703.00523 (2017)
  3. 3.
    Bi, L., Kim, J., Ahn, E., Feng, D.: Automatic skin lesion analysis using large-scale dermoscopy images and deep residual networks. arXiv preprint arXiv:1703.04197 (2017)
  4. 4.
    Chen, H., Qi, X., Yu, L., Heng, P.A.: DCAN: deep contour-aware networks for accurate gland segmentation. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 2487–2496 (2016)Google Scholar
  5. 5.
    Codella, N.C., Gutman, D., Celebi, M.E., et al.: Skin lesion analysis toward melanoma detection: a challenge at the 2017 international symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC). arXiv preprint arXiv:1710.05006 (2017)
  6. 6.
    Cohen, T., Welling, M.: Group equivariant convolutional networks. In: International Conference on Machine Learning, pp. 2990–2999 (2016)Google Scholar
  7. 7.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
  8. 8.
    Kimball, A.B., Resneck, J.S.: The us dermatology workforce: a specialty remains in shortage. J. Am. Acad. Dermatol. 59(5), 741–745 (2008)CrossRefGoogle Scholar
  9. 9.
    Lee, C.Y., Xie, S., Gallagher, P., Zhang, Z., Tu, Z.: Deeply-supervised nets. In: Artificial Intelligence and Statistics, pp. 562–570 (2015)Google Scholar
  10. 10.
    Marcos, D., Volpi, M., Komodakis, N., Tuia, D.: Rotation equivariant vector field networks. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 5058–5067. IEEE (2017)Google Scholar
  11. 11.
    Paszke, A., et al.: Automatic differentiation in PyTorch (2017)Google Scholar
  12. 12.
    Rogers, H.W., Weinstock, M.A., Feldman, S.R., Coldiron, B.M.: Incidence estimate of nonmelanoma skin cancer (keratinocyte carcinomas) in the us population, 2012. JAMA Dermatol. 151(10), 1081–1086 (2015)CrossRefGoogle Scholar
  13. 13.
    Siegel, R.L., Miller, K.D., Jemal, A.: Cancer statistics, 2017. CA Cancer J. Clin. 67(1), 7–30 (2017).  https://doi.org/10.3322/caac.21387CrossRefGoogle Scholar
  14. 14.
    Veeling, B.S., Linmans, J., Winkens, J., Cohen, T., Welling, M.: Rotation equivariant CNNs for digital pathology. arXiv preprint arXiv:1806.03962 (2018)
  15. 15.
    Winkens, J., Linmans, J., Veeling, B.S., Cohen, T.S., Welling, M.: Improved semantic segmentation for histopathology using rotation equivariant convolutional networks. Med. Imaging Deep Learn. 330–341 (2018)Google Scholar
  16. 16.
    Yu, L., Chen, H., Dou, Q., Qin, J., Heng, P.A.: Automated melanoma recognition in dermoscopy images via very deep residual networks. IEEE Trans. Med. Imaging 36(4), 994–1004 (2017)CrossRefGoogle Scholar
  17. 17.
    Yuan, Y., Lo, Y.C.: Improving dermoscopic image segmentation with enhanced convolutional-deconvolutional networks. IEEE J. Biomed. Health Inform. (2017).  https://doi.org/10.1109/JBHI.2017.2787487

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Xiaomeng Li
    • 1
    Email author
  • Lequan Yu
    • 1
  • Chi-Wing Fu
    • 1
  • Pheng-Ann Heng
    • 1
  1. 1.Department of Computer Science and EngineeringThe Chinese University of Hong KongShatinHong Kong

Personalised recommendations