507-02-001 ISMRM Abstract

Harmonization for a Black-box Model using Disentanglement-based Generator and Bayesian Optimization

Primary: Analysis Methods - Image Synthesis and Translation

Secondary: Analysis Methods - Image Registration and Alignment

507-02-001 · Generative Modeling: A Unifying Lens on MRI · Wednesday, 13 May, 8:20 AM–10:10 AM · Meeting Room 1.40

Keywords: AI/ML Image Reconstruction AI/ML Software Deep learning Domain adaptation Harmonization

Accepted

Minjun Kim ¹, Dong Ju Mun¹, Hwihun Jeong², Haechang Lee¹, Se Young Chun¹, Jongho Lee¹

¹Department of Electrical and Computer Engineering, Seoul National University, Seoul, Korea, Republic of

²Department of Psychiatry, Brigham and Women's Hospital and Harvard Medical School, Boston, United States of America

Presenting Author: Minjun Kim

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. Price, W. Nicholson. "Big data and black-box medical algorithms." Science translational medicine 10.471 (2018): eaao5333.

2. Dewey, Blake E., et al. "DeepHarmony: A deep learning approach to contrast harmonization across scanner changes." Magnetic resonance imaging 64 (2019): 160-170.

3. Liu, Mengting, et al. "Style transfer using generative adversarial networks for multi-site MRI harmonization." International conference on medical image computing and computer-assisted intervention. Cham: Springer International Publishing, 2021.

4. Jeong, Hwihun, et al. "BlindHarmony: "Blind" Harmonization for MR Images via Flow model." Proceedings of the IEEE/CVF International Conference on Computer Vision. 2023.

5. Beizaee, Farzad, et al. "Harmonizing flows: Leveraging normalizing flows for unsupervised and source-free MRI harmonization." Medical Image Analysis 101 (2025): 103483.

6. Guan, Hao, et al. "Multi-site MRI harmonization via attention-guided deep domain adaptation for brain disorder identification." Medical image analysis 71 (2021): 102076.

7. Kim, Minjun, et al. "Harmonization for a black-box deep learning model." in Proceedings of the 2025 ISMRM & ISMRT Annual Meeting, 2025.

8. Kushol, Rafsanjany, et al. "DSMRI: domain shift analyzer for multi-center MRI datasets." Diagnostics 13.18 (2023): 2947.

9. LaMontagne, Pamela J., et al. "OASIS-3: longitudinal neuroimaging, clinical, and cognitive dataset for normal aging and Alzheimer disease." medrxiv (2019): 2019-12.

Cite this abstract

http://echo.ismrm.org/p/ISMRM2026/507-02-001