Advertisement

3D Anisotropic Hybrid Network: Transferring Convolutional Features from 2D Images to 3D Anisotropic Volumes

  • Siqi Liu
  • Daguang Xu
  • S. Kevin Zhou
  • Olivier Pauly
  • Sasa Grbic
  • Thomas Mertelmeier
  • Julia Wicklein
  • Anna Jerebko
  • Weidong Cai
  • Dorin Comaniciu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11071)

Abstract

While deep convolutional neural networks (CNN) have been successfully applied to 2D image analysis, it is still challenging to apply them to 3D medical images, especially when the within-slice resolution is much higher than the between-slice resolution. We propose a 3D Anisotropic Hybrid Network (AH-Net) that transfers convolutional features learned from 2D images to 3D anisotropic volumes. Such a transfer inherits the desired strong generalization capability for within-slice information while naturally exploiting between-slice information for more effective modelling. We experiment with the proposed 3D AH-Net on two different medical image analysis tasks, namely lesion detection from a Digital Breast Tomosynthesis volume, and liver and liver tumor segmentation from a Computed Tomography volume and obtain state-of-the-art results.

References

  1. 1.
    Chen, J., Yang, L., Zhang, Y., Alber, M.S., Chen, D.Z.: Combining fully convolutional and recurrent neural networks for 3D biomedical image segmentation. In: NIPS (2016)Google Scholar
  2. 2.
    Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation. ArXiv eprints arXiv:1606.06650 (2016)
  3. 3.
    Ghesu, F.C., Georgescu, B., Grbic, S., Maier, A.K., Hornegger, J., Comaniciu, D.: Robust multi-scale anatomical landmark detection in incomplete 3D-CT data. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10433, pp. 194–202. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66182-7_23CrossRefGoogle Scholar
  4. 4.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of CVPR, pp. 770–778 (2016)Google Scholar
  5. 5.
    Huang, G., Liu, Z., Weinberger, K.Q., van der Maaten, L.: Densely Connected Convolutional Networks. ArXiv eprints arXiv:1608.06993 (2016)
  6. 6.
    Kingma, D.P., Ba, J.: Adam: A Method for Stochastic Optimization. ArXiv eprints arXiv:1412.6980 (2014)
  7. 7.
    Lee, K., Zung, J., Li, P., Jain, V., Seung, H.S.: Superhuman Accuracy on the SNEMI3D Connectomics Challenge. ArXiv e-prints arXiv:1706.00120 (2017)
  8. 8.
    Li, X., Chen, H., Qi, X., Dou, Q., Fu, C.W., Heng, P.A.: H-DenseUNet: Hybrid Densely Connected UNet for Liver and Liver Tumor Segmentation from CT Volumes. ArXiv e-prints arXiv:1709.07330 (2017)
  9. 9.
    Liu, F., Zhou, Z., Jang, H., Samsonov, A., Zhao, G., Kijowski, R.: Deep convolutional neural network and 3D deformable approach for tissue segmentation in musculoskeletal MR imaging. Magn. Reson. Med. (2017)Google Scholar
  10. 10.
    Peng, C., Zhang, X., Yu, G., Luo, G., Sun, J.: Large Kernel Matters - Improve Semantic Segmentation by Global Convolutional Network. ArXiv eprints arXiv:1703.02719 (2017)
  11. 11.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: Convolutional Networks for Biomedical Image Segmentation. ArXiv eprints arXiv:1505.04597 (2015)Google Scholar
  12. 12.
    Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. IJCV 115(3), 211–252 (2015)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid Scene Parsing Network. ArXiv eprints arXiv:1612.01105 (2016)

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Siqi Liu
    • 1
  • Daguang Xu
    • 1
  • S. Kevin Zhou
    • 1
  • Olivier Pauly
    • 2
  • Sasa Grbic
    • 1
  • Thomas Mertelmeier
    • 2
  • Julia Wicklein
    • 2
  • Anna Jerebko
    • 2
  • Weidong Cai
    • 3
  • Dorin Comaniciu
    • 1
  1. 1.Medical Imaging TechnologiesSiemens HealthineersPrincetonUSA
  2. 2.X-Ray ProductsSiemens HealthineersErlangenGermany
  3. 3.School of Information TechnologiesUniversity of SydneySydneyAustralia

Personalised recommendations