Skip to main content
SpringerLink
Log in

SwinDTI: swin transformer-based generalized fast estimation of diffusion tensor parameters from sparse data

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Diffusion tensor imaging (DTI) is a non-invasive technique for analyzing the movement of water in the brain. However, the precision of measurements required for tracking white matter pathways can lead to long scan times, which can be challenging for some patient populations such as pediatric patients. To address this issue, researchers have been experimenting with deep learning techniques for faster estimation of DTI parameters, which are helpful in neurological diagnosis, of diffusion-weighted images. Our proposed solution is a transformer neural network-based approach for fast estimation of diffusion tensor parameters using sparse measurements. While there have been attempts to address this problem, our proposed model handles both scalable and generalized estimation of DTI parameters using multiple sparse measurements. Through experimentation on the Human Connectome Project (HCP) Young Adult benchmark dataset, our proposed model demonstrated state-of-the-art results in terms of fractional anisotropy (FA), axial diffusivity (AD), and mean diffusivity (MD) when compared to traditional linear least square (LLS) fitting and 3D U-Net model with \(16 \times 16 \times 16\) input size (3D U-Net16).

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Algorithm 1
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18

Similar content being viewed by others

Data availability

Open Datasets HCP Young Adult [34, 35] (https://www.humanconnectome.org/study/hcp-young-adult). Johns Hopkins University (JHU) Stereotaxic White Matter Atlas [48] based on Diffusion Tensor Imaging in an ICBM Template (http://cmrm.med.jhmi.edu/ cmrm/ atlas/humandata/ file/ AtlasExplanation2.htm).

References

  1. Zhong L, Li T, Shu H, Huang C, Johnson JM, Schomer DF, Liu H-L, Feng Q, Yang W, Zhu H (2020) 2wm: tumor segmentation and tract statistics for assessing white matter integrity with applications to glioblastoma patients. Neuroimage 223:117368

    Article  Google Scholar 

  2. Zhang F, Breger A, Cho KIK, Ning L, Westin C-F, O’Donnell LJ, Pasternak O (2021) Deep learning based segmentation of brain tissue from diffusion MRI. Neuroimage 233:117934

    Article  Google Scholar 

  3. Douglas DB, Iv M, Douglas PK, Ariana A, Vos SB, Bammer R, Zeineh M, Wintermark M (2015) Diffusion tensor imaging of TBI: potentials and challenges. Top Magn Reson Imaging TMRI 24(5):241

    Article  Google Scholar 

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

    Article  Google Scholar 

  5. Gong T, Tong Q, Li Z, He H, Zhang H, Zhong J (2021) Deep learning-based method for reducing residual motion effects in diffusion parameter estimation. Magn Reson Med 85(4):2278–2293

    Article  Google Scholar 

  6. Douaud G, Jbabdi S, Behrens TE, Menke RA, Gass A, Monsch AU, Rao A, Whitcher B, Kindlmann G, Matthews PM et al (2011) Dti measures in crossing-fibre areas: increased diffusion anisotropy reveals early white matter alteration in mci and mild alzheimer’s disease. Neuroimage 55(3):880–890

    Article  Google Scholar 

  7. Lin Z, Gong T, Wang K, Li Z, He H, Tong Q, Yu F, Zhong J (2019) Fast learning of fiber orientation distribution function for MR tractography using convolutional neural network. Med Phys 46(7):3101–3116

    Article  Google Scholar 

  8. Consagra W, Venkataraman A, Zhang Z (2022) Optimized diffusion imaging for brain structural connectome analysis. IEEE Trans Med Imaging 41(8):2118–2129

    Article  Google Scholar 

  9. de Almeida Martins JP, Nilsson M, Lampinen B, While PT, Palombo M, Westin C-F, Szczepankiewicz F (2021) Neural networks for parameter estimation in microstructural MRI: application to a diffusion-relaxation model of white matter. NeuroImage 244:118601

    Article  Google Scholar 

  10. Karimi D, Gholipour A (2022) Diffusion tensor estimation with transformer neural networks. Artif Intell Med 130:102330

    Article  Google Scholar 

  11. Golkov V, Dosovitskiy A, Sperl JI, Menzel MI, Czisch M, Sämann P, Brox T, Cremers D (2016) Q-space deep learning: twelve-fold shorter and model-free diffusion mri scans. IEEE Trans Med Imaging 35(5):1344–1351

    Article  Google Scholar 

  12. Nir TM, Jahanshad N, Villalon-Reina JE, Toga AW, Jack CR, Weiner MW, Thompson PM (2013) Effectiveness of regional DTI measures in distinguishing Alzheimer’s disease, MCI, and normal aging. NeuroImage Clin 3:180–195

    Article  Google Scholar 

  13. Gupta V, Ayache N, Pennec X (2013) Improving DTI resolution from a single clinical acquisition: a statistical approach using spatial prior. Medical Image Computing and Computer-Assisted Intervention–MICCAI 2013: 16th International Conference, Nagoya, Japan, September 22–26, 2013, Proceedings, Part III 16. Springer, Berlin, Heidelberg, pp 477–484

  14. O’Donnell LJ, Suter Y, Rigolo L, Kahali P, Zhang F, Norton I, Albi A, Olubiyi O, Meola A, Essayed WI et al (2017) Automated white matter fiber tract identification in patients with brain tumors. NeuroImage Clin 13:138–153

    Article  Google Scholar 

  15. Aja-Fernández S, Martín-Martín C, Planchuelo-Gómez Á, Faiyaz A, Uddin MN, Schifitto G, Tiwari A, Shigwan SJ, Singh RK, Zheng T et al (2023) Validation of deep learning techniques for quality augmentation in diffusion MRI for clinical studies. NeuroImage Clin 39:103483

    Article  Google Scholar 

  16. Tiwari A, Singh RK (2022) Performance, trust, or both? covid-19 diagnosis and prognosis using deep ensemble transfer learning on x-ray images. In: Proceedings of the thirteenth indian conference on computer vision, graphics and image processing. pp 1–9

  17. Gibbons EK, Hodgson KK, Chaudhari AS, Richards LG, Majersik JJ, Adluru G, DiBella EV (2019) Simultaneous NODDI and GFA parameter map generation from subsampled q-space imaging using deep learning. Magn Reson Med 81(4):2399–2411

    Article  Google Scholar 

  18. Leming M (2020) Application of deep learning to brain connectivity classification in large mri datasets. Doctoral dissertation, University of Cambridge

  19. Tian Q, Li Z, Fan Q, Polimeni J, Bilgiç B, Salat DH, Huang SY (2021) Sdndti: self-supervised deep learning-based denoising for diffusion tensor MRI. NeuroImage 253:119033

    Article  Google Scholar 

  20. Zhang F, Xue T, Cai WT, Rathi Y, Westin C-F, O’Donnell LJ (2022) Tractoformer: a novel fiber-level whole brain tractography analysis framework using spectral embedding and vision transformers

  21. Tax CMW, Bastiani M, Veraart J, Garyfallidis E, Irfanoglu MO (2021) What’s new and what’s next in diffusion MRI preprocessing. NeuroImage 249(118):830

    Google Scholar 

  22. Karimi D, Jaimes C, Machado-Rivas F, Vasung L, Khan S, Warfield SK, Gholipour A (2021) Deep learning-based parameter estimation in fetal diffusion-weighted MRI. Neuroimage 243:118482

    Article  Google Scholar 

  23. Aliotta E, Nourzadeh H, Sanders J, Muller D, Ennis DB (2019) Highly accelerated, model-free diffusion tensor MRI reconstruction using neural networks. Med Phys 46(4):1581–1591

    Article  Google Scholar 

  24. Koay CG, Chang L-C, Carew JD, Pierpaoli C, Basser PJ (2006) A unifying theoretical and algorithmic framework for least squares methods of estimation in diffusion tensor imaging. J Magn Reson 182(1):115–125

    Article  Google Scholar 

  25. Nath V, Schilling KG, Parvathaneni P, Hansen CB, Hainline AE, Huo Y, Blaber JA, Lyu I, Janve V, Gao Y et al (2019) Deep learning reveals untapped information for local white-matter fiber reconstruction in diffusion-weighted MRI. Magn Reson Imaging 62:220–227

    Article  Google Scholar 

  26. Koppers S, Haarburger C, Edgar JC, Merhof D (2017) Reliable estimation of the number of compartments in diffusion mri. In: Proceedings des Workshops vom 12. bis 14. März 2017 in Heidelberg. Springer Berlin Heidelberg, pp 203–208

  27. Koppers S, Merhof D (2016) Direct estimation of fiber orientations using deep learning in diffusion imaging. Mach Learn Med Imaging 10019:53–60

    Article  Google Scholar 

  28. Koppers S, Friedrichs M, Merhof D (2017) Reconstruction of diffusion anisotropies using 3d deep convolutional neural networks in diffusion imaging. In: Modeling, analysis, and visualization of anisotropy. Springer International Publishing, pp 393–404

  29. Tian Q, Bilgic B, Fan Q, Liao C, Ngamsombat C, Hu Y, Witzel T, Setsompop K, Polimeni JR, Huang SY (2020) Deepdti: high-fidelity six-direction diffusion tensor imaging using deep learning. NeuroImage 219:117017

    Article  Google Scholar 

  30. Li H, Liang Z, Zhang C, Liu R, Li J, Zhang W, Liang D, Shen B, Zhang X, Ge Y et al (2021) Superdti: ultrafast DTI and fiber tractography with deep learning. Magn Reson Med 86(6):3334–3347

    Article  Google Scholar 

  31. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł., Polosukhin I (2017) Attention is all you need. Adv Neural Inf Process Syst 30

  32. Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 10 012–10 022

  33. Çiçek Ö, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O (2016) 3d u-net: learning dense volumetric segmentation from sparse annotation. In : Medical Image Computing and Computer-Assisted Intervention–MICCAI 2016: 19th International Conference, Athens, Greece, October 17–21, 2016, Proceedings, Part II 19. Springer, pp 424–432

  34. Elam JS, Glasser MF, Harms MP, Sotiropoulos SN, Andersson JL, Burgess GC, Curtiss SW, Oostenveld R, Larson-Prior LJ, Schoffelen J-M et al (2021) The human connectome project: a retrospective. NeuroImage 244:118543

    Article  Google Scholar 

  35. Liang Y, Xu G (2022) Multi-level functional connectivity fusion classification framework for brain disease diagnosis. IEEE J Biomed Health Inf 26(6):2714–2725

    Article  MathSciNet  Google Scholar 

  36. Yang Y-Q, Wang P-S, Liu Y (2021) Interpolation-aware padding for 3d sparse convolutional neural networks. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 7467–7475

  37. Ramachandran P, Parmar N, Vaswani A, Bello I, Levskaya A, Shlens J (2019) Stand-alone self-attention in vision models. Adv Neural Inf Process Syst 32

  38. Hu H, Zhang Z, Xie Z, Lin S (2019) Local relation networks for image recognition. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 3464–3473

  39. Garyfallidis E, Brett M, Amirbekian B, Rokem A, Van Der Walt S, Descoteaux M, Nimmo-Smith I, Contributors D (2014) Dipy, a library for the analysis of diffusion MRI data. Front Neuroinform 8:8

    Article  Google Scholar 

  40. Tuch DS (2004) Q-ball imaging. Magn Reson Med Off J Int Soc Magn Reson Med 52(6):1358–1372

    Article  Google Scholar 

  41. Baust M, Weinmann A, Wieczorek M, Lasser T, Storath M, Navab N (2016) Combined tensor fitting and tv regularization in diffusion tensor imaging based on a Riemannian manifold approach. IEEE Trans Med Imaging 35:1972–1989

    Article  Google Scholar 

  42. Le Bihan D, Mangin J-F, Poupon C, Clark CA, Pappata S, Molko N, Chabriat H (2001) Diffusion tensor imaging: concepts and applications. J Magn Reson Imaging Off J Int Soc Magn Reson Med 13(4):534–546

    Google Scholar 

  43. Malcolm JG, Shenton ME, Rathi Y (2010) Filtered multitensor tractography. IEEE Trans Med Imaging 29(9):1664–1675

    Article  Google Scholar 

  44. Jurick SM, Hoffman SN, Sorg S, Keller AV, Evangelista ND, DeFord NE, Sanderson-Cimino M, Bangen KJ, Delano-Wood L, Deoni S et al (2018) Pilot investigation of a novel white matter imaging technique in veterans with and without history of mild traumatic brain injury. Brain Injury 32(10):1255–1264

    Article  Google Scholar 

  45. Fani N, King TZ, Reiser E, Binder EB, Jovanovic T, Bradley B, Ressler KJ (2014) Fkbp5 genotype and structural integrity of the posterior cingulum. Neuropsychopharmacology 39(5):1206–1213

    Article  Google Scholar 

  46. Yeo C, Tan HL, Tan YH (2013) On rate distortion optimization using SSIM. IEEE Trans Circ Syst Video Technol 23(7):1170–1181

    Article  Google Scholar 

  47. Laguna PAL, Combes AJ, Streffer J, Einstein S, Timmers M, Williams SC, Dell’Acqua F (2020) Reproducibility, reliability and variability of fa and md in the older healthy population: a test-retest multiparametric analysis. NeuroImage Clin 26:102168

    Article  Google Scholar 

  48. Mori S, Oishi K, Jiang H, Jiang L, Li X, Akhter K, Hua K, Faria AV, Mahmood A, Woods R et al (2008) Stereotaxic white matter atlas based on diffusion tensor imaging in an ICBM template. Neuroimage 40(2):570–582

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, Shiv Nadar Institution of Eminence, Delhi NCR, India

    Abhishek Tiwari, Rajeev Kumar Singh & Saurabh J. Shigwan

Authors
  1. Abhishek Tiwari
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Rajeev Kumar Singh
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Saurabh J. Shigwan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Rajeev Kumar Singh.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tiwari, A., Singh, R.K. & Shigwan, S.J. SwinDTI: swin transformer-based generalized fast estimation of diffusion tensor parameters from sparse data. Neural Comput & Applic 36, 3179–3196 (2024). https://doi.org/10.1007/s00521-023-09206-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-023-09206-4

Keywords

Search

Navigation