Advertisement

Integrating Cross-modality Hallucinated MRI with CT to Aid Mediastinal Lung Tumor Segmentation

  • Jiang Jue
  • Hu Jason
  • Tyagi Neelam
  • Rimner Andreas
  • Berry L. Sean
  • Deasy O. Joseph
  • Veeraraghavan HariniEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11769)

Abstract

Lung tumors, especially those located close to or surrounded by soft tissues like the mediastinum, are difficult to segment due to the low soft tissue contrast on computed tomography images. Magnetic resonance images contain superior soft-tissue contrast information that can be leveraged if both modalities were available for training. Therefore, we developed a cross-modality educed learning approach where MR information that is educed from CT is used to hallucinate MRI and improve CT segmentation. Our approach, called cross-modality educed deep learning segmentation (CMEDL) combines CT and pseudo MR produced from CT by aligning their features to obtain segmentation on CT. Features computed in the last two layers of parallelly trained CT and MR segmentation networks are aligned. We implemented this approach on U-net and dense fully convolutional networks (dense-FCN). Our networks were trained on unrelated cohorts from open-source the Cancer Imaging Archive CT images (N = 377), an internal archive T2-weighted MR (N = 81), and evaluated using separate validation (N = 304) and testing (N = 333) CT-delineated tumors. Our approach using both networks were significantly more accurate (U-net \(P <0.001\); denseFCN \(P <0.001\)) than CT-only networks and achieved an accuracy (Dice similarity coefficient) of \(0.71\pm 0.15\) (U-net), \(0.74\pm 0.12\) (denseFCN) on validation and \(0.72\pm 0.14\) (U-net), \(0.73\pm 0.12\) (denseFCN) on the testing sets. Our novel approach demonstrated that educing cross-modality information through learned priors enhances CT segmentation performance.

Keywords

Hallucinating MRI from CT for segmentation Lung tumors Adversarial cross-domain deep learning 

Notes

Acknowledgements

This work was supported by the MSK Cancer Center support grant/core grant P30 CA008748, and NCI R01 CA198121-03.

References

  1. 1.
    Njeh, C.: Tumor delineation: the weakest link in the search for accuracy in radiotherapy. J. Med. Phys./Assoc. Med. Phys. India 33(4), 136 (2008)Google Scholar
  2. 2.
    Devic, S.: MRI simulation for radiotherapy treatment planning. Med. Phys. 39(11), 6701–6711 (2012)CrossRefGoogle Scholar
  3. 3.
    Nie, D., et al.: Medical image synthesis with context-aware generative adversarial networks. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10435, pp. 417–425. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66179-7_48CrossRefGoogle Scholar
  4. 4.
    Chartsias, A., Joyce, T., Dharmakumar, R., Tsaftaris, S.A.: Adversarial image synthesis for unpaired multi-modal cardiac data. In: Tsaftaris, S.A., Gooya, A., Frangi, A.F., Prince, J.L. (eds.) SASHIMI 2017. LNCS, vol. 10557, pp. 3–13. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-68127-6_1CrossRefGoogle Scholar
  5. 5.
    Jiang, J., et al.: Tumor-aware, adversarial domain adaptation from CT to MRI for lung cancer segmentation. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11071, pp. 777–785. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-00934-2_86CrossRefGoogle Scholar
  6. 6.
    Zhu, J.Y., Park, T., Isola, P., Efros, A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: International Conference Computer Vision (ICCV), pp. 2223–2232 (2017)Google Scholar
  7. 7.
    Long, M., Zhu, H., Wang, J., Jordan, M.I.: Deep transfer learning with joint adaptation networks. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 2208–2217. JMLR. org (2017)Google Scholar
  8. 8.
    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)CrossRefGoogle Scholar
  9. 9.
    Vanya, V.V., et al.: Multi-modal learning from unpaired images: application to multi-organ segmentation in CT and MRI. In: 2018 IEEE Winter Conference on Applications of Computer Vision, WACV 2018, Lake Tahoe, NV, USA, 12–15 March 2018, pp. 547–556 (2018)Google Scholar
  10. 10.
    Cai, J., Zhang, Z., Cui, L., Zheng, Y., Yang, L.: Towards cross-modal organ translation and segmentation: a cycle-and shape-consistent generative adversarial network. Med. Image Anal. 52, 174–184 (2019)CrossRefGoogle Scholar
  11. 11.
    Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems (NIPS), pp. 2672–2680 (2014)Google Scholar
  12. 12.
    Mechrez, R., Talmi, I., Zelnik-Manor, L.: The contextual loss for image transformation with non-aligned data. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision – ECCV 2018. LNCS, vol. 11218, pp. 800–815. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01264-9_47CrossRefGoogle Scholar
  13. 13.
    Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-24574-4_28CrossRefGoogle Scholar
  14. 14.
    Jégou, S., Drozdzal, M., Vazquez, D., Romero, A., Bengio, Y.: The one hundred layers tiramisu: fully convolutional densenets for semantic segmentation. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1175–1183. IEEE (2017)Google Scholar
  15. 15.
    Paszke, A., et al.: Automatic differentiation in pytorch (2017)Google Scholar
  16. 16.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the 3rd International Conference on Learning Representations (ICLR) (2014)Google Scholar
  17. 17.
    Clark, K., et al.: The cancer imaging archive (TCIA): maintaining and operating a public information repository. J. Digit. Imaging 26(6), 1045–1057 (2013)CrossRefGoogle Scholar
  18. 18.
    Aerts, H.J., et al.: Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat. Commun. 5, 4006 (2014)CrossRefGoogle Scholar
  19. 19.
    Menze, B.H., et al.: The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans. Med. Imaging 34(10), 1993 (2015)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Jiang Jue
    • 1
  • Hu Jason
    • 1
  • Tyagi Neelam
    • 1
  • Rimner Andreas
    • 2
  • Berry L. Sean
    • 1
  • Deasy O. Joseph
    • 1
  • Veeraraghavan Harini
    • 1
    Email author
  1. 1.Medical PhysicsMemorial Sloan Kettering Cancer CenterNew YorkUSA
  2. 2.Radiation OncologyMemorial Sloan Kettering Cancer CenterNew YorkUSA

Personalised recommendations