Advertisement

Efficient 3D Depthwise and Separable Convolutions with Dilation for Brain Tumor Segmentation

  • Donghao Zhang
  • Yang SongEmail author
  • Dongnan Liu
  • Chaoyi Zhang
  • Yicheng Wu
  • Heng Wang
  • Fan Zhang
  • Yong Xia
  • Lauren J. O’Donnell
  • Weidong Cai
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11919)

Abstract

In this paper, we propose a 3D convolutional neural network targeting at the segmentation of brain tumor. There are different types of brain tumors and our focus is one common type named glioma. The proposed network is efficient and balances the tradeoff between the number of parameters and accuracy of segmentation. It consists of Anisotropic Block, Dilated Parallel Residual Block, and Feature Refinement Module. The Anisotropic Block applies anisotropic convolutional kernels on different branches. In addition, the Dilated Parallel Residual Block incorporates 3D depthwise and separable convolutions to reduce the amount of required parameters dramatically, while multiscale dilated convolutions enlarge the receptive field. The Feature Refinement Module prevents global contextual information loss. Our method is evaluated on the BRATS 2017 dataset. The results show that our method achieved competitive performance among all compared methods, with a reduced number of parameters. The ablation study also proves that each individual block or module is effective.

Keywords

Brain tumor segmentation Magnetic resonance imaging 3D deep neural network 

References

  1. 1.
    Bakas, S., et al.: Advancing the Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features. Sci. Data 4, 170117 (2017)CrossRefGoogle Scholar
  2. 2.
    Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834–848 (2018)CrossRefGoogle Scholar
  3. 3.
    Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 424–432. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46723-8_49CrossRefGoogle Scholar
  4. 4.
    Havaei, M., et al.: Brain tumor segmentation with deep neural networks. Med. Image Anal. 35, 18–31 (2017) CrossRefGoogle Scholar
  5. 5.
    Jia, H., et al.: 3D APA-Net: 3D adversarial pyramid anisotropic convolutional network for prostate segmentation in mr images. IEEE Trans. Med. Imag. (2019)Google Scholar
  6. 6.
    Li, W., Wang, G., Fidon, L., Ourselin, S., Cardoso, M.J., Vercauteren, T.: On the compactness, efficiency, and representation of 3D convolutional networks: brain parcellation as a pretext task. In: Niethammer, M., et al. (eds.) IPMI 2017. LNCS, vol. 10265, pp. 348–360. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-59050-9_28CrossRefGoogle Scholar
  7. 7.
    Liu, D., et al.: Densely connected large kernel convolutional network for semantic membrane segmentation in microscopy images. In: 2018 25th IEEE International Conference on Image Processing (ICIP), pp. 2461–2465. IEEE (2018)Google Scholar
  8. 8.
    Liu, D., Zhang, D., Song, Y., Zhang, F., O’Donnell, L.J., Cai, W.: 3D large kernel anisotropic network for brain tumor segmentation. In: Cheng, L., Leung, A.C.S., Ozawa, S. (eds.) ICONIP 2018. LNCS, vol. 11307, pp. 444–454. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-04239-4_40CrossRefGoogle Scholar
  9. 9.
    Ma, J., Yang, X.: Automatic brain tumor segmentation by exploring the multi-modality complementary information and cascaded 3D lightweight CNNs. In: Crimi, A., Bakas, S., Kuijf, H., Keyvan, F., Reyes, M., van Walsum, T. (eds.) BrainLes 2018. LNCS, vol. 11384, pp. 25–36. Springer, Cham (2019).  https://doi.org/10.1007/978-3-030-11726-9_3CrossRefGoogle Scholar
  10. 10.
    Menze, B.H., et al.: The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans. Med. Imag. 34(10), 1993–2024 (2015)CrossRefGoogle Scholar
  11. 11.
    Milletari, F., Navab, N., Ahmadi, S.A.: V-Net: fully convolutional neural networks for volumetric medical image segmentation. In: 3D Vision, pp. 565–571 (2016)Google Scholar
  12. 12.
    Pereira, S., Pinto, A., Alves, V., Silva, C.A.: Brain tumor segmentation using convolutional neural networks in MRI images. IEEE Trans. Med. Imag. 35(5), 1240–1251 (2016)CrossRefGoogle Scholar
  13. 13.
    Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: CVPR (2018)Google Scholar
  14. 14.
    Subbanna, N.K., Precup, D., Collins, D.L., Arbel, T.: Hierarchical probabilistic gabor and MRF segmentation of brain tumours in MRI volumes. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013. LNCS, vol. 8149, pp. 751–758. Springer, Heidelberg (2013).  https://doi.org/10.1007/978-3-642-40811-3_94CrossRefGoogle Scholar
  15. 15.
    Wang, H., et al.: Segmenting neuronal structure in 3D optical microscope images via knowledge distillation with teacher-student network. In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), pp. 228–231. IEEE (2019)Google Scholar
  16. 16.
    Wen, P.Y., et al.: Updated response assessment criteria for high-grade gliomas: response assessment in neuro-oncology working group. J. Clin. Oncol. 28(11), 1963–1972 (2010)CrossRefGoogle Scholar
  17. 17.
    Wu, Y., et al.: Vessel-Net: retinal vessel segmentation under multi-path supervision. In: Shen, D., et al. (eds.) MICCAI 2019. Lecture Notes in Computer Science, vol. 11764, pp. 264–272. Springer, Cham (2019).  https://doi.org/10.1007/978-3-030-32239-7_30CrossRefGoogle Scholar
  18. 18.
    Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: BiSeNet: bilateral segmentation network for real-time semantic segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 334–349. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01261-8_20CrossRefGoogle Scholar
  19. 19.
    Zhang, C., et al.: MS-GAN: GAN-based semantic segmentation of multiple sclerosis lesions in brain magnetic resonance imaging. In: 2018 Digital Image Computing: Techniques and Applications (DICTA), pp. 1–8. IEEE (2018)Google Scholar
  20. 20.
    Zhang, D., et al.: Panoptic segmentation with an end-to-end cell R-CNN for pathology image analysis. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11071, pp. 237–244. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-00934-2_27CrossRefGoogle Scholar
  21. 21.
    Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: CVPR, pp. 6230–6239 (2017)Google Scholar
  22. 22.
    Zhao, X., et al.: A deep learning model integrating FCNNs and CRFs for brain tumor segmentation. Med. Image Anal. 43, 98–111 (2018)CrossRefGoogle Scholar
  23. 23.
    Zhou, C., Ding, C., Lu, Z., Wang, X., Tao, D.: One-pass multi-task convolutional neural networks for efficient brain tumor segmentation. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11072, pp. 637–645. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-00931-1_73CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Donghao Zhang
    • 1
  • Yang Song
    • 2
    Email author
  • Dongnan Liu
    • 1
  • Chaoyi Zhang
    • 1
  • Yicheng Wu
    • 3
  • Heng Wang
    • 1
  • Fan Zhang
    • 4
  • Yong Xia
    • 3
  • Lauren J. O’Donnell
    • 4
  • Weidong Cai
    • 1
  1. 1.School of Computer ScienceUniversity of SydneySydneyAustralia
  2. 2.School of Computer Science and EngineeringUniversity of New South WalesKensingtonAustralia
  3. 3.School of Computer Science and EngineeringNorthwestern Polytechnical UniversityXi’anChina
  4. 4.Brigham and Women’s Hospital, Harvard Medical SchoolBostonUSA

Personalised recommendations