564-05-003 ISMRM Abstract

Deep learning-based relaxometry from conventional brain MRI: applications to a large-scale, clinically heterogeneous dataset

Primary: Analysis Methods - Image Synthesis and Translation

Secondary: Acquisition & Reconstruction - Quantitative Imaging: relaxometry, multi-parametric, MR Fingerprinting, and synthetic MRI

564-05-003 · The qMRI Variety Show: A Little Bit of Everything · Wednesday, 13 May, 4:00 PM–4:55 PM · Digital Posters Row E

Keywords: Analysis/Processing Neuro Quantitative Mapping Physics-guided deep learning Image synthesis

Accepted

Jelmer van Lune ¹, Stefano Mandija¹, Oscar van der Heide¹, Matteo Maspero¹, Martin B Schilder¹, Cornelis A van den Berg¹, Alessandro A Sbrizzi¹

¹Computational Imaging Group for MRI Therapy & Diagnostics, UMC Utrecht, Utrecht, Netherlands

Presenting Author: Jelmer van Lune

Synopsis

Motivation:

Goals:

Approach:

Results:

Full abstract & presentation

The full text, figures, and any recorded presentation for this abstract are not shown here. Log in if you are a member or registered attendee with access.

Full abstracts, figures, and presentations for Cape Town - 2026 ISMRM-ISMRT Annual Meeting and Exhibition are available to registered attendees. This content becomes freely available to the public roughly two years after the meeting.

To request or purchase access, contact the ISMRM Central Office at info@ismrm.org.

References

1. M. Bento, I. Fantini, J. Park, L. Rittner, and R. Frayne, ‘Deep Learning in Large and Multi-Site Structural Brain MR Imaging Datasets’, Front Neuroinform, vol. 15, 2022, doi: 10.3389/fninf.2021.805669. [doi]

2. F. Hu et al., ‘Image harmonization: A review of statistical and deep learning methods for removing batch effects and evaluation metrics for effective harmonization’, Neuroimage, vol. 274, p. 120125, 2023, doi: 10.1016/j.neuroimage.2023.120125. [doi]

3. G. Mårtensson et al., ‘The reliability of a deep learning model in clinical out-of-distribution MRI data: A multicohort study’, Med Image Anal, vol. 66, p. 101714, 2020, doi: 10.1016/j.media.2020.101714. [doi]

4. G. Wen et al., ‘Machine Learning for Brain MRI Data Harmonisation: A Systematic Review’, Bioengineering, vol. 10, no. 4, p. 397, Apr. 2023, doi: 10.3390/bioengineering10040397. [doi]

5. F. Tixier, V. Jaouen, C. Hognon, O. Gallinato, T. Colin, and D. Visvikis, ‘Evaluation of conventional and deep learning based image harmonization methods in radiomics studies’, Phys Med Biol, vol. 66, no. 24, p. 245009, 2021, doi: 10.1088/1361-6560/ac39e5. [doi]

6. E. Moya-Sáez, R. De Luis-García, and C. Alberola-López, ‘A self-supervised deep learning approach to synthesize weighted images and T1, T2, and PD parametric maps based on MR physics priors’, Virtual: In Proc ISMRM, 2021, p. 2169. Accessed: Oct. 20, 2025. [Online]. Available: https://archive.ismrm.org/2021/2169.html

7. S. Qiu, L. Wang, P. Sati, A. G. Christodoulou, Y. Xie, and D. Li, ‘Physics-guided self-supervised learning for retrospective T1 and T2 mapping from conventional weighted brain MRI: Technical developments and initial validation in glioblastoma’, Magn Reson Med, vol. 92, no. 6, pp. 2683–2695, 2024, doi: 10.1002/mrm.30226. [doi]

8. S. Qiu et al., ‘Protocol-aware unsupervised retrospective T1 and T2 mapping with diverse imaging parameters’, Singapore: In Proc ISMRM, 2024, p. 1192. . Available: https://archive.ismrm.org/2024/1192.html

9. P. Xu et al., ‘Weakly-Supervised Learning for Retrospective T1 and T2 Mapping from Conventional Weighted Brain MRI’, Honolulu, Hawaii, USA: In Proc ISMRM, 2025, p. 3998. Available: https://archive.ismrm.org/2025/3998.html

10. J. van Lune et al., ‘Retrospective relaxometry from conventional contrasts by physics-informed deep learning: A pilot on Tumor, MS, Stroke and Epilepsy patients’, Honolulu, Hawaii, USA: In Proc ISMRM, 2025, p. 1045. Available: https://archive.ismrm.org/2025/1045.html

11. L. Jacobs, S. Mandija, H. Liu, C. A. T. van den Berg, A. Sbrizzi, and M. Maspero, ‘Generalizable synthetic MRI with physics-informed convolutional networks’, Med Phys, vol. 51, no. 5, pp. 3348–3359, 2024, doi: 10.1002/mp.16884. [doi]

12. B. B. Avants, N. Tustison, and G. Song, ‘Advanced normalization tools (ANTS)’, Insight j, vol. 2, no. 365, pp. 1–35, 2009.

13. J. B. M. Warntjes, O. Dahlqvist Leinhard, J. West, and P. Lundberg, ‘Rapid magnetic resonance quantification on the brain: Optimization for clinical usage’, Magn Reson Med, vol. 60, no. 2, pp. 320–329, Aug. 2008, doi: 10.1002/MRM.21635. [doi]

14. Y. Zhang, M. Brady, and S. Smith, ‘Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm’, IEEE Trans Med Imaging, vol. 20, no. 1, pp. 45–57, 2001, doi: 10.1109/42.906424. [doi]

15. J. Z. Bojorquez, S. Bricq, C. Acquitter, F. Brunotte, P. M. Walker, and A. Lalande, ‘What are normal relaxation times of tissues at 3 T?’, Magn Reson Imaging, vol. 35, pp. 69–80, Jan. 2017, doi: 10.1016/J.MRI.2016.08.021. [doi]

16. G. J. Stanisz et al., ‘T1, T2 relaxation and magnetization transfer in tissue at 3T’, Magn Reson Med, vol. 54, no. 3, pp. 507–512, Sep. 2005, doi: 10.1002/MRM.20605. [doi]

17. J. P. Wansapura, S. K. Holland, R. S. Dunn, and W. S. Ball, ‘NMR Relaxation Times in the Human Brain at 3.0 Tesla’, J. Magn. Reson. Imaging, pp. 531–538, 1999, doi: 10.1002/(SICI)1522-2586(199904)9:4. [doi]

Cite this abstract

http://echo.ismrm.org/p/ISMRM2026/564-05-003