Skip to main content
SpringerLink
Log in

Diffusion-weighted MRI with deep learning for visualizing treatment results of MR-guided HIFU ablation of uterine fibroids

  • Interventional
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objectives

No method is available to determine the non-perfused volume (NPV) repeatedly during magnetic resonance–guided high-intensity focused ultrasound (MR-HIFU) ablations of uterine fibroids, as repeated acquisition of contrast-enhanced T1-weighted (CE-T1w) scans is inhibited by safety concerns. The objective of this study was to develop and test a deep learning–based method for translation of diffusion-weighted imaging (DWI) into synthetic CE-T1w scans, for monitoring MR-HIFU treatment progression.

Methods

The algorithm was retrospectively trained and validated on data from 33 and 20 patients respectively who underwent an MR-HIFU treatment of uterine fibroids between June 2017 and January 2019. Postablation synthetic CE-T1w images were generated by a deep learning network trained on paired DWI and reference CE-T1w scans acquired during the treatment procedure. Quantitative analysis included calculation of the Dice coefficient of NPVs delineated on synthetic and reference CE-T1w scans. Four MR-HIFU radiologists assessed the outcome of MR-HIFU treatments and NPV ratio based on the synthetic and reference CE-T1w scans.

Results

Dice coefficient of NPVs was 71% (± 22%). The mean difference in NPV ratio was 1.4% (± 22%) and not statistically significant (p = 0.79). Absolute agreement of the radiologists on technical treatment success on synthetic and reference CE-T1w scans was 83%. NPV ratio estimations on synthetic and reference CE-T1w scans were not significantly different (p = 0.27).

Conclusions

Deep learning–based synthetic CE-T1w scans derived from intraprocedural DWI allow gadolinium-free visualization of the predicted NPV, and can potentially be used for repeated gadolinium-free monitoring of treatment progression during MR-HIFU therapy for uterine fibroids.

Key Points

• Synthetic CE-T1w scans can be derived from diffusion-weighted imaging using deep learning.

• Synthetic CE-T1w scans may be used for visualization of the NPV without using a contrast agent directly after MR-HIFU ablations of uterine fibroids.

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

Similar content being viewed by others

Abbreviations

CE-T1w:

Contrast-enhanced T1-weighted

cGAN:

Conditional generative adversarial network

DL:

Deep learning

DWI:

Diffusion-weighted imaging

FA:

Flip angle

Gd:

Gadolinium

MAE:

Mean absolute error

MR-HIFU:

Magnetic resonance–guided high-intensity focused ultrasound

MSE:

Mean squared error

NPV:

Non-perfused volume

TE:

Echo time

TR:

Repetition time

UF:

Uterine fibroid

References

  1. Verpalen IM, Anneveldt KJ, Nijholt IM et al (2019) Magnetic resonance-high intensity focused ultrasound (MR-HIFU) therapy of symptomatic uterine fibroids with unrestrictive treatment protocols: a systematic review and meta-analysis. Eur J Radiol 120:108700

    Article  PubMed  Google Scholar 

  2. Fennessy FM, Tempany CM, McDannold NJ et al (2007) Uterine leiomyomas: MR imaging-guided focused ultrasound surgery - results of different treatment protocols. Radiology 243:885–893

    Article  PubMed  Google Scholar 

  3. Park MJ, Kim YS, Rhim H, Lim HK (2014) Safety and therapeutic efficacy of complete or near-complete ablation of symptomatic uterine fibroid tumors by MR imaging-guided high-intensity focused US Therapy. J Vasc Interv Radiol 25:231–239

    Article  PubMed  Google Scholar 

  4. Al Hilli MM, Stewart EA (2010) Magnetic resonance-guided focused ultrasound surgery. Semin Reprod Med 28:242–249

    Article  PubMed  Google Scholar 

  5. Stewart EA, Gostout B, Rabinovici J, Kim HS, Regan L, Tempany CMC (2007) Sustained relief of leiomyoma symptoms by using focused ultrasound surgery. Obstet Gynecol 110:279–287

    Article  PubMed  Google Scholar 

  6. Verpalen IM, de Boer JP, Linstra M et al (2020) The Focused Ultrasound Myoma Outcome Study (FUMOS); a retrospective cohort study on long-term outcomes of MR-HIFU therapy. Eur Radiol 30:2473–2482

    Article  PubMed  Google Scholar 

  7. Keserci B, Duc NM (2017) The role of T1 perfusion-based classification in magnetic resonance-guided high-intensity focused ultrasound ablation of uterine fibroids. Eur Radiol 27:5299–5308

    Article  PubMed  Google Scholar 

  8. Hijnen NM, Elevelt A, Pikkemaat J, Bos C, Bartels LW, Grüll H (2013) The magnetic susceptibility effect of gadolinium-based contrast agents on PRFS-based MR thermometry during thermal interventions. J Ther Ultrasound 1:8

    Article  PubMed  PubMed Central  Google Scholar 

  9. Hijnen NM, Elevelt A, Grüll H (2013) Stability and trapping of magnetic resonance imaging contrast agents during high-intensity focused ultrasound ablation therapy. Invest Radiol 48:517–524

    Article  CAS  PubMed  Google Scholar 

  10. Hectors SJCG, Jacobs I, Heijman E et al (2015) Multiparametric MRI analysis for the evaluation of MR-guided high intensity focused ultrasound tumor treatment. NMR Biomed 28:1125–1140

    Article  PubMed  Google Scholar 

  11. Zimmerman BE, Johnson S, Odeen H et al (2021) Learning multiparametric biomarkers for assessing MR-guided focused ultrasound treatment of malignant tumors. IEEE Trans Biomed Eng 68:1737–1747

    Article  PubMed  PubMed Central  Google Scholar 

  12. Morochnik S, Ozhinsky E, Rieke V, Bucknor MD (2019) T2 mapping as a predictor of nonperfused volume in MRgFUS treatment of desmoid tumors. Int J Hyperthermia 36:1272–1277

  13. Jacobs MA, Herskovits EH, Kim HS (2005) Uterine fibroids: diffusion-weighted MR imaging for monitoring therapy with focused ultrasound surgery - preliminary study. Radiology 236:196–203

    Article  PubMed  Google Scholar 

  14. Giles SL, Winfield JM, Collins DJ et al (2018) Value of diffusion-weighted imaging for monitoring tissue change during magnetic resonance-guided high-intensity focused ultrasound therapy in bone applications: an ex-vivo study. Eur Radiol Exp 2:10

    Article  PubMed  PubMed Central  Google Scholar 

  15. Chetan MR, Lyon PC, Wu F et al (2019) Role of diffusion-weighted imaging in monitoring treatment response following high-intensity focused ultrasound ablation of recurrent sacral chordoma. Radiol Case Rep 14:1197–1201

  16. Walker MR, Zhong J, Waspe AC et al (2019) Acute MR-guided high-intensity focused ultrasound lesion assessment using diffusion-weighted imaging and histological analysis. Front Neurol 10:1069

    Article  PubMed  PubMed Central  Google Scholar 

  17. Jacobs MA, Ouwerkerk R, Kamel I, Bottomley PA, Bluemke DA, Kim HS (2009) Proton, diffusion-weighted imaging, and sodium (23Na) MRI of uterine leiomyomata after MR-guided high intensity focused ultrasound: a preliminary study. J Magn Reson Imaging 29:649

    Article  PubMed  PubMed Central  Google Scholar 

  18. Jacobs MA, Gultekin DH, Kim HS (2010) Comparison between diffusion-weighted imaging, -weighted, and postcontrast -weighted imaging after MR-guided, high intensity, focused ultrasound treatment of uterine leiomyomata: preliminary results. Med Phys 37:4768–4776

    Article  PubMed  PubMed Central  Google Scholar 

  19. Pilatou MC, Stewart EA, Maier SE et al (2009) MRI-based thermal dosimetry and diffusion-weighted imaging of MRI-guided focused ultrasound thermal ablation of uterine fibroids. J Magn Reson Imaging 29:404

    Article  PubMed  PubMed Central  Google Scholar 

  20. Verpalen I, Boomsma M, Edens M, Heijman E (2019) The evaluation of the non-perfused volume after MR-HIFU treatment of uterine fibroids using quantitative T2-mapping and diffusion weighted imaging. In: 19th International Symposium of ISTU and 5th European Symposium of EUFUS. Barcelona, p 143

    Google Scholar 

  21. Ikink ME, Voogt MJ, Van Den Bosch MAAJ et al (2014) Diffusion-weighted magnetic resonance imaging using different b-value combinations for the evaluation of treatment results after volumetric MR-guided high-intensity focused ultrasound ablation of uterine fibroids. Eur Radiol 24:2118–2127

    Article  PubMed  Google Scholar 

  22. Ikink ME, Van Breugel JMM, Nijenhuis RJ, et al (2014) Intravoxel incoherent motion MRI for the characterization of uterine fibroids before MR-guided high-intensity focused ultrasound ablation. In: Proceedings of the Joint Annual Meeting International Society for Magnetic Resonance In Medicine - European Society for Magnetic Resonance in Medicine and Biology. Milan, p 3693

  23. Verpalen IM (2021) Diffusion-weighted imaging to monitor treatment progression of magnetic resonance guided focused ultrasound fibroid ablation. In: Improving treatment efficacy of MR-HIFU fibroid ablation, Thesis. pp 131–148

  24. Iima M, Le Bihan D (2016) Clinical intravoxel incoherent motion and diffusion MR imaging: past, present, and future. Radiology 278:13–32

    Article  PubMed  Google Scholar 

  25. Le Bihan D, Turner R (1992) The capillary network: a link between ivim and classical perfusion. Magn Reson Med 27:171–178

    Article  PubMed  Google Scholar 

  26. Dijkstra H, Oudkerk M, Kappert P, Sijens PE (2017) Assessment of the link between quantitative biexponential diffusion-weighted imaging and contrast-enhanced MRI in the liver. Magn Reson Imaging 38:47–53

    Article  PubMed  Google Scholar 

  27. Le Bihan D (2019) What can we see with IVIM MRI? Neuroimage 187:56–67

    Article  PubMed  Google Scholar 

  28. Guo Z, Zhang Q, Li X, Jing Z (2015) Intravoxel incoherent motion diffusion weighted MR imaging for monitoring the instantly therapeutic efficacy of radiofrequency ablation in rabbit VX2 tumors without evident links between conventional perfusion weighted images. PLoS One. https://doi.org/10.1371/journal.pone.0127964

  29. Verpalen IM, Anneveldt KJ, Vos PC et al (2020) Use of multiparametric MRI to characterize uterine fibroid tissue types. MAGMA. https://doi.org/10.1007/s10334-020-00841-9

  30. Klein S, Staring M, Murphy K, Viergever MA, Pluim JPW (2010) Elastix: a toolbox for intensity-based medical image registration. IEEE Trans Med Imaging 29:196–205

    Article  PubMed  Google Scholar 

  31. Gong E, Pauly JM, Wintermark M, Zaharchuk G (2018) Deep learning enables reduced gadolinium dose for contrast-enhanced brain MRI. J Magn Reson Imaging 48:330–340

    Article  PubMed  Google Scholar 

  32. Sun H, Liu X, Feng X, et al (2020) Substituting gadolinium in brain MRI using DeepContrast. Proc - Int Symp Biomed Imaging 2020-April:908–912

  33. Zhao J, Li D, Kassam Z et al (2020) Tripartite-GAN: synthesizing liver contrast-enhanced MRI to improve tumor detection. Med Image Anal 63:101667

    Article  PubMed  Google Scholar 

  34. Kleesiek J, Morshuis JN, Isensee F et al (2019) Can virtual contrast enhancement in brain MRI replace gadolinium? Invest Radiol 54:653–660

    Article  CAS  PubMed  Google Scholar 

  35. Riexinger A, Martin J, Wetscherek A et al (2021) An optimized b-value distribution for triexponential intravoxel incoherent motion (IVIM) in the liver. Magn Reson Med 85:2095–2108

    Article  CAS  PubMed  Google Scholar 

  36. Wang L, Chen W, Yang W, Bi F, Yu FR (2020) A state-of-the-art review on image synthesis with generative adversarial networks. IEEE Access 8:63514–63537

    Article  Google Scholar 

  37. Mongan J, Moy L, Kahn CE (2020) Checklist for Artificial Intelligence in Medical Imaging (CLAIM): a guide for authors and reviewers. Radiol Artif Intell 2:e200029

    Article  PubMed  PubMed Central  Google Scholar 

  38. Keenan KE, Peskin AP, Wilmes LJ et al (2016) Variability and bias assessment in breast ADC measurement across multiple systems. J Magn Reson Imaging 44:846–855

    Article  PubMed  PubMed Central  Google Scholar 

  39. Jafar MM (2016) Diffusion-weighted magnetic resonance imaging in cancer: reported apparent diffusion coefficients, in-vitro and in-vivo reproducibility. World J Radiol 8:21

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Funding

The authors state that this work has not received any funding.

Author information

Authors and Affiliations

  1. Department of Radiology, Isala Hospital, Zwolle, The Netherlands

    Derk J. Slotman, Aylene Zijlstra, Inez M. Verpalen, Jochen A. C. van Osch, Ingrid M. Nijholt, Miranda van ‘t Veer-ten Kate, Erwin de Boer, Rolf D. van den Hoed & Martijn F. Boomsma

  2. Imaging & Oncology Division, Image Sciences Institute, University Medical Center Utrecht, Utrecht, The Netherlands

    Derk J. Slotman, Lambertus W. Bartels & Martijn Froeling

  3. Department of Radiology, Amsterdam University Medical Center, Amsterdam, The Netherlands

    Inez M. Verpalen

  4. Faculty of Medicine and University Hospital of Cologne, Institute of Diagnostic and Interventional Radiology, University of Cologne, Cologne, Germany

    Edwin Heijman

  5. Philips Research Eindhoven, High Tech Campus, Eindhoven, The Netherlands

    Edwin Heijman

Authors
  1. Derk J. Slotman
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lambertus W. Bartels
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Aylene Zijlstra
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Inez M. Verpalen
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jochen A. C. van Osch
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Ingrid M. Nijholt
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Edwin Heijman
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Miranda van ‘t Veer-ten Kate
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Erwin de Boer
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Rolf D. van den Hoed
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Martijn Froeling
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Martijn F. Boomsma
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Derk J. Slotman.

Ethics declarations

Guarantor

The scientific guarantor of this publication is M. F. Boomsma, MD PhD.

Conflict of interest

One of the authors (Edwin Heijman) is an employee of Philips. The remaining authors declare no relationships with any companies whose products or services may be related to the subject matter of the article

Statistics and biometry

One of the authors has significant statistical expertise.

Informed consent

Written informed consent was obtained from all subjects (patients) in the source studies (MASS1 and MASS2). This consent included the authorization to analyse study data outside the scope of the source studies, in the context of MR-HIFU treatments of uterine fibroids. Therefore, no post hoc contact with patients was required for the current retrospective study. Both the source studies and the retrospective study presented here have been approved by the institutional review board (IRB).

Ethical approval

Institutional review board approval was obtained.

Methodology

• retrospective

• method comparison study

• performed at one institution

Additional information

Publisher’s note

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

Supplementary information

ESM 1

(PDF 291 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

Slotman, D.J., Bartels, L.W., Zijlstra, A. et al. Diffusion-weighted MRI with deep learning for visualizing treatment results of MR-guided HIFU ablation of uterine fibroids. Eur Radiol 33, 4178–4188 (2023). https://doi.org/10.1007/s00330-022-09294-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-022-09294-1

Keywords

Search

Navigation