Advertisement

A Novel Domain Adaptation Framework for Medical Image Segmentation

  • Amir GholamiEmail author
  • Shashank Subramanian
  • Varun Shenoy
  • Naveen Himthani
  • Xiangyu Yue
  • Sicheng Zhao
  • Peter Jin
  • George Biros
  • Kurt Keutzer
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11384)

Abstract

We propose a segmentation framework that uses deep neural networks and introduce two innovations. First, we describe a biophysics-based domain adaptation method. Second, we propose an automatic method to segment white matter, gray matter, glial matter and cerebrospinal fluid, in addition to tumorous tissue. Regarding our first innovation, we use a domain adaptation framework that combines a novel multispecies biophysical tumor growth model with a generative adversarial model to create realistic looking synthetic multimodal MR images with known segmentation. These images are used for the purpose of training time data augmentation. Regarding our second innovation, we propose an automatic approach to enrich available segmentation data by computing the segmentation for healthy tissues. This segmentation, which is done using diffeomorphic image registration between the BraTS training data and a set of pre-labeled atlases, provides more information for training and reduces the class imbalance problem. Our overall approach is not specific to any particular neural network and can be used in conjunction with existing solutions. We demonstrate the performance improvement using a 2D U-Net for the BraTS’18 segmentation challenge. Our biophysics based domain adaptation achieves better results, as compared to the existing state-of-the-art GAN model used to create synthetic data for training.

Keywords

Segmentation Neural network Machine learning Glioblastoma multiforme Tumor growth models Image registration 

References

  1. 1.
    Bakas, S., et al.: Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features. Nat. Sci. Data 4, 170117 (2017)CrossRefGoogle Scholar
  2. 2.
    Bakas, S., et al.: Segmentation Labels for the Pre-operative Scans of the TCGA-GBM Collection (2017). http://doi.org/10.7937/k9/tcia.2017.klxwjj1q
  3. 3.
    Bakas, S., et al.: Segmentation Labels for the Pre-operative Scans of the TCGA-LGG Collection (2017). http://doi.org/10.7937/k9/tcia.2017.gjq7r0ef
  4. 4.
    Bakas, S., et al.: Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the brats challenge. arXiv preprint arXiv:1811.02629 (2018)
  5. 5.
    Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 248–255. IEEE (2009)Google Scholar
  6. 6.
    Gholami, A.: Fast algorithms for biophysically-constrained inverse problems in medical imaging. Ph.D. thesis, The University of Texas at Austin (2017)Google Scholar
  7. 7.
    Hawkins-Daarud, A., Rockne, R.C., Anderson, A.R.A., Swanson, K.R.: Modeling tumor-associated edema in gliomas during anti-angiogenic therapy and its imapct on imageable tumor. Front. Oncol. 3, 66 (2013)CrossRefGoogle Scholar
  8. 8.
    Hawkins-Daarud, A., van der Zee, K.G., Tinsley Oden, J.: Numerical simulation of a thermodynamically consistent four-species tumor growth model. Int. J. Numer. Methods Biomed. Eng. 28(1), 3–24 (2012)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Isensee, F., Kickingereder, P., Wick, W., Bendszus, M., Maier-Hein, K.H.: Brain tumor segmentation and radiomics survival prediction: contribution to the BRATS 2017 challenge. CoRR abs/1802.10508 (2018). http://arxiv.org/abs/1802.10508
  10. 10.
    Ivkovic, S., et al.: Direct inhibition of myosin II effectively blocks glioma invasion in the presence of multiple motogens. Mol. Biol. Cell 23(4), 533–542 (2012)CrossRefGoogle Scholar
  11. 11.
    Kamnitsas, K., et al.: Ensembles of multiple models and architectures for robust brain tumour segmentation. CoRR abs/1711.01468 (2017). http://arxiv.org/abs/1711.01468
  12. 12.
    Kamnitsas, K., et al.: Efficient multi-scale 3d CNN with fully connected CRF for accurate brain lesion segmentation. Med. Image Anal. 36, 61–78 (2017). http://www.sciencedirect.com/science/article/pii/S1361841516301839CrossRefGoogle Scholar
  13. 13.
    Lima, E., Oden, J., Hormuth, D., Yankeelov, T., Almeida, R.: Selection, calibration, and validation of models of tumor growth. Math. Models Methods Appl. Sci. 26(12), 2341–2368 (2016)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. CoRR abs/1411.4038 (2014). http://arxiv.org/abs/1411.4038
  15. 15.
    Maier, O., et al.: ISLES 2015 - a public evaluation benchmark for ischemic stroke lesion segmentation from multispectral MRI. Med. Image Anal. 35, 250–269 (2017)CrossRefGoogle Scholar
  16. 16.
    Mang, A., Biros, G.: A semi-Lagrangian two-level preconditioned Newton-Krylov solver for constrained diffeomorphic image registration. SIAM J. Sci. Comput. 39(6), B1064–B1101 (2017)MathSciNetCrossRefGoogle Scholar
  17. 17.
    Mang, A., Gholami, A., Biros, G.: Distributed-memory large deformation diffeomorphic 3d image registration. In: SC16: International Conference for High Performance Computing, Networking, Storage and Analysis (2016)Google Scholar
  18. 18.
    Mang, A., Gholami, A., Davatzikos, C., Biros, G.: CLAIRE: a distributed-memory solver for constrained large deformation diffeomorphic image registration. arXiv preprint arXiv:1808.04487 (2018)
  19. 19.
    Oden, J.T., et al.: Toward predictive multiscale modeling of vascular tumor growth. Arch. Comput. Methods Eng. 23(4), 735–779 (2016)MathSciNetCrossRefGoogle Scholar
  20. 20.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. CoRR abs/1505.04597 (2015). http://arxiv.org/abs/1505.04597Google Scholar
  21. 21.
    Shin, H.-C., et al.: Medical image synthesis for data augmentation and anonymization using generative adversarial networks. In: Gooya, A., Goksel, O., Oguz, I., Burgos, N. (eds.) SASHIMI 2018. LNCS, vol. 11037, pp. 1–11. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-00536-8_1CrossRefGoogle Scholar
  22. 22.
    Subramanian, S., Gholami, A., Biros, G.: Simulation of glioblastoma growth using a 3d multispecies tumor model with mass effect. arXiv preprint arXiv:1810.05370
  23. 23.
    Wang, G., Li, W., Ourselin, S., Vercauteren, T.: Automatic brain tumor segmentation using cascaded anisotropic convolutional neural networks. CoRR abs/1709.00382 (2017). http://arxiv.org/abs/1709.00382
  24. 24.
    Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: 2017 IEEE International Conference on Computer Vision (ICCV) (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Amir Gholami
    • 1
    Email author
  • Shashank Subramanian
    • 2
  • Varun Shenoy
    • 1
  • Naveen Himthani
    • 2
  • Xiangyu Yue
    • 1
  • Sicheng Zhao
    • 1
  • Peter Jin
    • 1
  • George Biros
    • 2
  • Kurt Keutzer
    • 1
  1. 1.University of California BerkeleyBerkeleyUSA
  2. 2.The University of Texas at AustinAustinUSA

Personalised recommendations