Skip to main content
Springer Nature Link
Log in

Better Fibre Orientation Estimation with Single-Shell Diffusion MRI Using Spherical U-Net

  • Conference paper
  • First Online:
Data Science (ICPCSEE 2023)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1880))

  • 535 Accesses

Abstract

Diffusion MRI is an important technology for detecting human brain nerve pathways, aiding in neuroscience and clinical diagnosis. However, the Multi-Shell Multi-Tissue Constrained Spherical Deconvolution (M-CSD) method, which is a significant technique for reconstructing the fibre orientation distribution function (fODF), requires multishell data with a considerable number of gradient directions to achieve high accuracy. As multishell data are not easy to acquire, the Single-Shell Single-Tissue CSD (S-CSD) suffers from the Partial Volume Effect (PVE). It would be more convenient if we could use single-shell data to reconstruct better fODFs.

We propose a novel method that utilizes the spatial structure and anisotropy of dMRI data through a spherical convolution network. We reduce the need for high-quality data by utilizing b = 1000 s/mm2 with 60 gradient directions or even less. Our results show that our method outperforms the traditional S-CSD when compared to the M-CSD results as our gold standard.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

References

  1. Le Bihan, D.: Looking into the functional architecture of the brain with diffusion mri. Nat. Rev. Neurosci. 4(6), 469–480 (2003)

    Article  Google Scholar 

  2. Garyfallidis, E.: Towards an accurate brain tractography. PhD thesis, University of Cambridge (2013)

    Google Scholar 

  3. Basser, P.J., Mattiello, J., LeBihan, D.: Mr diffusion tensor spectroscopy and imaging. Biophys. J . 66(1), 259–267 (1994)

    Article  Google Scholar 

  4. Jeurissen, B., Tournier, J.-D., Dhollander, T., Connelly, A., Sijbers, J.: Multitissue constrained spherical deconvolution for improved analysis of multishell diffusion mri data. Neuroimage 103, 411–426 (2014)

    Article  Google Scholar 

  5. Tournier, J.-D., Calamante, F., Connelly, A.: Robust determination of the fibre orientation distribution in diffusion mri: nonnegativity constrained superresolved spherical deconvolution. Neuroimage 35(4), 1459–1472 (2007)

    Article  Google Scholar 

  6. Litjens, G., et al.: A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60–88 (2017)

    Article  Google Scholar 

  7. Zhao, F., et al.: Spherical u-net on cortical surfaces: methods and applications. In: Information Processing in Medical Imaging: 26th International Conference, IPMI 2019, Hong Kong, China, 2–7 June  2019, Proceedings 26, pp. 855–866. Springer (2019). https://doi.org/10.1007/978-3-030-20351-1_67

  8. Zhao, F., et al.: Spherical deformable u-net: Application to cortical surface parcellation and development prediction. IEEE Trans. Med. Imaging 40(4), 1217–1228 (2021)

    Article  Google Scholar 

  9. Koppers, S., Merhof, D.: Direct estimation of fibre orientations using deep learning in diffusion imaging. In: Machine Learning in Medical Imaging: 7th International Workshop, MLMI 2016, Held in Conjunction with MICCAI 2016, Athens, Greece, 17 October 2016, Proceedings 7, pp. 53–60. Springer (2016). https://doi.org/10.1007/978-3-319-47157-0_7

  10. Schultz, T.: Learning a reliable estimate of the number of fibre directions in diffusion mri. In: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2012: 15th International Conference, Nice, France, October 1–5, 2012, Proceedings, Part III 15, pp. 493–500. Springer (2012). https://doi.org/10.1007/978-3-642-33454-2_61

  11. Koppers, S., Friedrichs, M., Merhof, D.: Reconstruction of diffusion anisotropies using 3d deep convolutional neural networks in diffusion imaging. In: Modelling, Analysis, and Visualization of Anisotropy, pp. 393–404. Springer (2017). https://doi.org/10.1007/978-3-319-61358-1_17

  12. Lin, Z., et al.: Fast learning of fibre orientation distribution function for mr tractography using convolutional neural network. Med. Phys. 46(7), 3101–3116 (2019)

    Google Scholar 

  13. Zeng, R., et al.: Fod-net: A deep learning method for fibre orientation distribution angular super resolution. Med. Image Anal. 79, 102431 (2022)

    Google Scholar 

  14. Patel, K., Groeschel, S., Schultz, T.: Better Fiber ODFs from suboptimal data with autoencoder based regularization. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11072, pp. 55–62. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00931-1_7

    Chapter  Google Scholar 

  15. Nath, V., Pathak, S.K., Schilling, K.G., Schneider, W., Landman, B.A.: Deep learning estimation of multitissue constrained spherical deconvolution with limited single shell dw-mri. In: Medical Imaging 2020: Image Processing, vol. 11313, pp. 162–171. SPIE (2020)

    Google Scholar 

  16. Lucena, O., Vos, S.B., Vakharia, V., Duncan, J., Ourselin, S., Sparks, R.: Convolutional neural networks for fibre orientation distribution enhancement to improve single-shell diffusion mri tractography. In: Computational Diffusion MRI: MICCAI Workshop, Shenzhen, China, October 2019, pp. 101–112. Springer (2020). https://doi.org/10.1007/978-3-030-52893-5_9

  17. Tuch, D.S., Reese, T.G., Wiegell, M.R., Makris, N., Belliveau, J.W., Wedeen, V.J.: High angular resolution diffusion imaging reveals intravoxel white matter fibre heterogeneity. Magn. Reson. Med. Official J. Internat. Soc. Magn. Reson. Med. 48(4), 577–582 (2002)

    Article  Google Scholar 

  18. Jha, R.R., Nigam, A., Bhavsar, A., Pathak, S.K., Schneider, W., Rathish, K.: Multishell d-mri reconstruction via residual learning utilizing encoder-decoder network with attention (msr-net). In: 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), pp. 1709–1713 (2020). IEEE

    Google Scholar 

  19. Sedlar, S., Papadopoulo, T., Deriche, R., Deslauriers-Gauthier, S.: Diffusion mri fibre orientation distribution function estimation using voxelwise spherical u-net. In: Computational Diffusion MRI: International MICCAI Workshop, Lima, Peru, October 2020, pp. 95–106. Springer (2021). https://doi.org/10.1007/978-3-030-73018-5_8

  20. Lucena, O., et al.: Enhancing the estimation of fibre orientation distributions using convolutional neural networks. Comput. Biol. Med. 135, 104643 (2021)

    Article  Google Scholar 

  21. Karimi, D., Vasung, L., Jaimes, C., Machado-Rivas, F., Warfield, S.K., Gholipour, A.: Learning to estimate the fibre orientation distribution function from diffusion-weighted mri. Neuroimage 239, 118316 (2021)

    Article  Google Scholar 

  22. Karimi, D., et al.: A machine learning-based method for estimating the number and orientations of major fascicles in diffusion-weighted magnetic resonance imaging. Med. Image Anal. 72, 102129 (2021)

    Article  Google Scholar 

  23. Canales-Rodríguez, E.J., et al.: Sparse wars: a survey and comparative study of spherical deconvolution algorithms for diffusion mri. Neuroimage 184, 140–160 (2019)

    Google Scholar 

  24. Descoteaux, M., Angelino, E., Fitzgibbons, S., Deriche, R.: Apparent diffusion coefficients from high angular resolution diffusion imaging: estimation and applications. Magn. Reson. Med. Official J. Inter. Soc. Magn. Reson. Med. 56(2), 395–410 (2006)

    Article  Google Scholar 

  25. Wilkins, B., Lee, N., Gajawelli, N., Law, M., Leporé, N.: Fibre estimation and tractography in diffusion mri: development of simulated brain images and comparison of multifibre analysis methods at clinical b-values. Neuroimage 109, 341–356 (2015)

    Article  Google Scholar 

  26. Puttashamachar, N., Bagci, U.: End to end brain fibre orientation estimation using deep learning. arXiv preprint arXiv:1806.03969 (2018)

  27. Ye, C., Prince, J.L.: Fibre orientation estimation guided by a deep network. In: Medical Image Computing and Computer Assisted Intervention-MICCAI 2017: 20th International Conference, Quebec City, QC, Canada, 11–13 September  2017, Proceedings, Part I, pp. 575–583. Springer (2017). https://doi.org/10.1007/978-3-319-66182-7_66

  28. Golkov, V., et al.: Q-space deep learning: twelve-fold shorter and model-free diffusion mri scans. IEEE Trans. Med. Imaging 35(5), 1344–1351 (2016)

    Article  Google Scholar 

  29. Hagmann, P., Jonasson, L., Maeder, P., Thiran, J.-P., Wedeen, V.J., Meuli, R.: Understanding diffusion mr imaging techniques: from scalar diffusion-weighted imaging to diffusion tensor imaging and beyond. Radiographics 26(suppl_1), 205–223 (2006)

    Google Scholar 

  30. Dell’Acqua, F., Tournier, J.-D.: Modelling white matter with spherical deconvolution: How and why? NMR Biomed. 32(4), 3945 (2019)

    Google Scholar 

  31. Glasser, M.F., et al.: The minimal preprocessing pipelines for the human connectome project. Neuroimage 80, 105–124 (2013)

    Google Scholar 

  32. Tournier, J.-D., et al.: Mrtrix3: A fast, flexible and open software framework for medical image processing and visualization. Neuroimage 202, 116137 (2019)

    Article  Google Scholar 

  33. Anderson, A.W.: Measurement of fibre orientation distributions using high angular resolution diffusion imaging. Magn. Reson. Med. Official J. Inter. Soc. Magn. Reson Med. 54(5), 1194–1206 (2005)

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by the Natural Science Foundation of Heilongjiang Province (LH2021F046).

Author information

Authors and Affiliations

  1. Department of Computer Science and Technology, Heilongjiang University, Harbin, China

    Hang Zhao, Chengdong Deng, Yu Wang & Jiquan Ma

Authors
  1. Hang Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chengdong Deng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yu Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jiquan Ma
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jiquan Ma .

Editor information

Editors and Affiliations

  1. Harbin Engineering University, Harbin, China

    Zhiwen Yu

  2. Harbin Engineering University, Harbin, China

    Qilong Han

  3. Harbin Institute of Technology, Harbin, Heilongjiang, China

    Hongzhi Wang

  4. Northwestern Polytechnical University, Xi'an, China

    Bin Guo

  5. Shiga University, Shiga, Japan

    Xiaokang Zhou

  6. Harbin University of Science and Technology, Harbin, China

    Xianhua Song

  7. National Academy of Guo Ding Institute of Data Science, Beijing, China

    Zeguang Lu

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Zhao, H., Deng, C., Wang, Y., Ma, J. (2023). Better Fibre Orientation Estimation with Single-Shell Diffusion MRI Using Spherical U-Net. In: Yu, Z., et al. Data Science. ICPCSEE 2023. Communications in Computer and Information Science, vol 1880. Springer, Singapore. https://doi.org/10.1007/978-981-99-5971-6_1

Download citation

  • DOI: https://doi.org/10.1007/978-981-99-5971-6_1

  • Published:

  • Publisher Name: Springer, Singapore

  • Print ISBN: 978-981-99-5970-9

  • Online ISBN: 978-981-99-5971-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics