Skip to main content
SpringerLink
Log in

Comparison of model-based versus deep learning-based image reconstruction for thin-slice T2-weighted spin-echo prostate MRI

  • Pelvis
  • Published:
Abdominal Radiology Aims and scope Submit manuscript

Abstract

Purpose

To compare a previous model-based image reconstruction (MBIR) with a newly developed deep learning (DL)-based image reconstruction for providing improved signal-to-noise ratio (SNR) in high through-plane resolution (1 mm) T2-weighted spin-echo (T2SE) prostate MRI.

Methods

Large-area contrast and high-contrast spatial resolution of the reconstruction methods were assessed quantitatively in experimental phantom studies. The methods were next evaluated radiologically in 17 subjects at 3.0 Tesla for whom prostate MRI was clinically indicated. For each subject, the axial T2SE raw data were directed to MBIR and to the DL reconstruction at three vendor-provided levels: (L)ow, (M)edium, and (H)igh. Thin-slice images from the four reconstructions were compared using evaluation criteria related to SNR, sharpness, contrast fidelity, and reviewer preference. Results were compared using the Wilcoxon signed-rank test using Bonferroni correction, and inter-reader comparisons were done using the Cohen and Krippendorf tests.

Results

Baseline contrast and resolution in phantom studies were equivalent for all four reconstruction pathways as desired. In vivo, all three DL levels (L, M, H) provided improved SNR versus MBIR. For virtually, all other evaluation criteria DL L and M were superior to MBIR. DL L and M were evaluated as superior to DL H in fidelity of contrast. For 44 of the 51 evaluations, the DL M reconstruction was preferred.

Conclusion

The deep learning reconstruction method provides significant SNR improvement in thin-slice (1 mm) T2SE images of the prostate while retaining image contrast. However, if taken to too high a level (DL High), both radiological sharpness and fidelity of contrast diminish.

Graphical abstract

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

Similar content being viewed by others

References

  1. Crooks LE, Ortendahl DA, Kaufman L, et al. Clinical efficacy of nuclear magnetic resonance imaging. Radiology. 1983;146:123-8.

    Article  CAS  PubMed  Google Scholar 

  2. Hennig J, Nauerth A, Friedburg H. RARE imaging: a fast imaging method for clinical MR. Magn Reson Med. 1986;3:823-33.

    Article  CAS  PubMed  Google Scholar 

  3. Mugler JP, Bao S, Mulkern RV, et al. Optimized single slab three-dimensional spin-echo MR imaging of the brain. Radiology. 2000;216:891-9.

    Article  PubMed  Google Scholar 

  4. Busse RF, Hariharan H, Vu A, Brittain JH. Fast spin echo sequences with very long echo trains: design of variable refocusing flip angle schedules and generation of clinical T2 contrast. Magn Reson Med. 2006;55:1030-7.

    Article  PubMed  Google Scholar 

  5. Gold GE, Busse RF, Beehler C, et al. Isotropic MRI of the knee with 3D fast spin-echo extended echo-train acquistiion (XETA): initial experience. AJR. 2007;188:1287-93.

    Article  PubMed  Google Scholar 

  6. Rosenkrantz AB, Neil J, Kong X, et al. Prostate cancer: comparison of 3D T2-weighted with conventional 2D T2-weighted imaging for image quality and tumor detection. Am J Roentgenol. 2010;194:446-52.

    Article  Google Scholar 

  7. Aiken AH, Mukherjee P, Green AJ, Glastonbury CM. MR imaging of optic neuropathy with extended echo-train acquisition fluid-attenuated inversion recovery. Am J Neuroradiol. 2011;32:301-5.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  8. Mugler JP. Optimized three-dimensional fast-spin-echo MRI. J Magn Reson Img. 2014;39:745-67.

    Article  Google Scholar 

  9. Srinivasan S, Wu HH, Sung K, Margolis DJA, Ennis DB. Fast 3D T2-weighted imaging usign variable flip angle transition into driven equilibrium (3D T2-TIDE) balanced SSFP for prostate imaging at 3T. Magn Reson Med. 2015;74:442-51.

    Article  PubMed  Google Scholar 

  10. Vidya Shankar R, Roccia E, Cruz G, et al. Accelerated 3D T2w-imaging of the prostate with 1-millimeter isotropic resolution in less than 3 minutes. Magn Reson Med. 2019;82:721-31.

    Article  PubMed  PubMed Central  Google Scholar 

  11. Wilman AH, Riederer SJ. Improved centric phase encoding orders for three dimensional magnetization prepared MR angiography. Magn Reson Med. 1996;36:384-92.

    Article  CAS  PubMed  Google Scholar 

  12. Choi MH, Kim DH, Lee YJ, Rha SE, Lee JY. Image features of the PI-RADS for predicting extraprostatic extension of prostate cancer: systematic review and meta-analysis. Insights into Imaging. 2023;14:77.

    Article  PubMed  PubMed Central  Google Scholar 

  13. Karademir I, Shen D, Peng Y, et al. Prostate volumes derived from MRI and volume-adjusted serum prostate-specific antigen: correlation with Gleason score of prostate cancer. 2013;201:1041-8.

    Google Scholar 

  14. Vargas HA, Akin O, Shukla-Dave A, et al. Performance characteristics of MR imaging in the evaluation of clincally low-risk prostate cancer: a prospective study. Radiology. 2012;265:478-87.

    Article  PubMed  PubMed Central  Google Scholar 

  15. Greenspan H, Oz G, Kiryati N, Peled S. MRI inter-slice reconstruction using super-resolution. Magn Reson Img. 2002;20:437-46.

    Article  CAS  Google Scholar 

  16. Shilling RZ, Robbie TQ, Bailloeul T, Mewes K, Mersereau RM, Brummer ME. A super-resolution framework for 3-D high-resolution and high-contrast imaging using 2-D multislice MRI. IEEE Trans Med Img. 2009;28:633-44.

    Article  Google Scholar 

  17. Aganj I, Lenglet C, Yacoub E, Sapiro G, Harel N. A 3D wavelet fusion approach for the reconstruction of isotropic-resolution MR images from orthogonal anisotropic resolution scans. Magn Reson Med. 2012;67:1167-72.

    Article  PubMed  Google Scholar 

  18. Plenge E, Poot DHJ, Bernsen M, et al. Super-resolution methods in MRI: can they improve the trade-off between resolution, signal-to-noise ratio, and acquisition time? Magn Reson Med. 2012;68:1983-93.

    Article  PubMed  Google Scholar 

  19. Gholipour A, Afacan O, Aganj I, et al. Super-resolution reconstruction in frequency, image, and wavelet domains to reduce through-plane partial voluming in MRI. Med Phys. 2015;42:6919-32.

    Article  PubMed  PubMed Central  Google Scholar 

  20. Okanovic M, Hillig B, Breuer F, Jakob P, Blaimer M. Time-of-flight MR-angiography with a helical trajectory and slice-super-resolution reconstruction. Magn Reson Med. 2018;80:1812-23.

    Article  PubMed  Google Scholar 

  21. Kargar S, Borisch EA, Froemming AT, et al. Use of kZ-space for high through-plane resolution in multi-slice MRI: application to prostate. Magn Reson Med. 2019;81:3691-704.

    Article  PubMed  Google Scholar 

  22. Borisch EA, Grimm RC, Froemming AT, Kawashima A, Trzasko JD, Riederer SJ. Model-based image reconstruction with wavelet sparsity regularization for through-plane resolution restoration in T2-weighted spin-echo prostate MRI. Magn Reson Med. 2023;89:454-68.

    Article  CAS  PubMed  Google Scholar 

  23. Wang X, Ma J, Bhosale P, et al. Novel deep learning-based noise reduction technique for prostate magnetic resonance imaging. Abdom Radiol. 2021;46:3378-86.

    Article  Google Scholar 

  24. Gassenmaier S, Afat S, Nickel D, Mostapha M, Hermann J, Othman AE. Deep learning-accelerated T2-weighted imaging of the prostate: reduction of acquisition time and improvement of image quality. Eur J Radiol. 2021;137:109600.

    Article  PubMed  Google Scholar 

  25. Park JC, Park EJ, Park MY, Kim M, Kim JK. Fast T2-weighted imaging with deep learning-based reconstruction: evaluation of image quality and diagnostic performance in patients undergoing radical prostatectomy. J Magn Reson Img. 2022;55:1734-44.

    Google Scholar 

  26. Kelleher CB, Macdonald J, Jaffe TA, et al. A faster prostate MRI: comparing a novel denoised, single-average T2 sequence to the conventional multiaverage T2 sequence regarding lesion detection and PI-RADS score assessment. J Magn Reson Img. 2023;58:620-9.

    Article  Google Scholar 

  27. Tong A, Bagga B, Petrocelli R, et al. Comparison of a deep learning-accelerated vs. conventional T2-weighted sequence in biparametric MRI of the prostate. J Magn Reson Img. 2023;58:1055–64.

  28. Kargar S, Borisch EA, Froemming AT, et al. Modified acquisition strategy for reduced motion artifact in super resolution T2FSE multislice MRI: application to prostate. Magn Reson Med. 2020;84:2537-50.

    Article  PubMed  PubMed Central  Google Scholar 

  29. Lebel RM. Performance characteristization of a novel deep learning-based MR image reconstruction pipeline. arXiv. 2020;arXiv:2008.06559.

  30. Turkbey B, Rosenkrantz AB, Haider MA, et al. Prostate imaging reporting and data system version 2.1: 2019 update of prostate imaging reporting and data system version 2. Eur Urology. 2019;76:340-51.

    Article  Google Scholar 

  31. Keenan KE, Stupic KF, Boss MA, et al. Multi-site, multi-vendor comparison of T1 measurement using ISMRM/NIST system phantom. 24th Annual Mtg, ISMRM. Singapore2016; p. 3290.

  32. Senn S, Stevens L, Chaturvedi N. Repeated measures in clinical trials: simple strategies for analysis using summary measures. Statistics in Med. 2000;19:861-77.

    Article  CAS  Google Scholar 

  33. Schober P, Vetter TR. Repeated measures designs and analysis of longitudinal data: if a first you do not succeed - try, try again. Anesth & Analg. 2018;127:569-74.

    Article  Google Scholar 

  34. Rosner B. Fundamentals of Biostatistics. Sixth ed. Belmont CA: Thomson, 2006; p. 868.

  35. Cohen J. A coefficeint of agreement for nominal scales. Educ Psych Meas. 1960;20:37-46.

    Article  Google Scholar 

  36. Krippendorf K. Content analysis: an introduction to its methodology. Thousand Oaks CA, 2013: 221–250.

  37. Lee CH. Quantitative T2-mapping using MRI for detection of prostate malignancy: a systematic review of the literature. Acta Radiologica. 2019;60:1181-9.

    Article  PubMed  Google Scholar 

  38. Mai J, Abubrig A, Lehmann T, et al. T2 mapping in prostate cancer. Invest Radiol. 2019;54:146-52.

    Article  PubMed  Google Scholar 

  39. Klingebiel M, Schimmoller L, Weiland E, et al. Value of T2 mapping MRI for prostate cancer detection and classification. J Magn Reson Img. 2022;54:413-22.

    Article  Google Scholar 

Download references

Acknowledgements

We would like to acknowledge Kathy J. Brown and Corey C. Woxland, R.T., for assistance with the human studies and Nicholas B. Larson, Ph.D., for consultation on statistical evaluation.

Funding

National Institutes of Health RR018898; National Institutes of Health R01 EB031790; Mayo Discovery-Translation Program; Mayo Imaging Biomarker Program; General Electric Healthcare.

Author information

Authors and Affiliations

  1. Department of Radiology, Mayo Clinic, Rochester, MN, 55905, USA

    Stephen J. Riederer, Eric A. Borisch, Adam T. Froemming & Naoki Takahashi

  2. Department of Radiology, Mayo Clinic, Phoenix, AZ, USA

    Akira Kawashima

Authors
  1. Stephen J. Riederer
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Eric A. Borisch
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Adam T. Froemming
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Akira Kawashima
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Naoki Takahashi
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors contributed to the study conception and design. Material preparation, data collection, and analysis were performed by S. J. Riederer and E. A. Borisch. The first draft of the manuscript was written by S. J. Riederer, and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Stephen J. Riederer.

Ethics declarations

Conflict of interest

SJR and EAB are inventors of a US patent related to the technology discussed. ATF, AK, and NT declare no relevant financial or non-financial interests.

Additional information

Publisher's Note

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

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (PNG 66 kb)

Supplementary file2 (PNG 272 kb)

Supplementary file3 (PNG 275 kb)

Supplementary file4 (PNG 289 kb)

Supplementary file5 (PNG 261 kb)

Supplementary file6 (MP4 39946 kb)

Supplementary file7 (MP4 42759 kb)

Supplementary file8 (MP4 30339 kb)

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

Riederer, S.J., Borisch, E.A., Froemming, A.T. et al. Comparison of model-based versus deep learning-based image reconstruction for thin-slice T2-weighted spin-echo prostate MRI. Abdom Radiol (2024). https://doi.org/10.1007/s00261-024-04256-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s00261-024-04256-1

Keywords

Search

Navigation