JudgeMI: Towards Accurate Metrics for Assessing Deep Learning Based Structural 
MRI Motion Correction

Mahler, L; Steiglechner, J; Wang, Q; Scheffler, K; Lohmann, G

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsRelease HistoryDetailsSummary

Released

Poster

JudgeMI: Towards Accurate Metrics for Assessing Deep Learning Based Structural MRI Motion Correction

MPS-Authors

/persons/resource/persons273224

Mahler, L
Department High-Field Magnetic Resonance, Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons252833

Steiglechner, J
Department High-Field Magnetic Resonance, Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons251740

Wang, Q
Department High-Field Magnetic Resonance, Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons84187

Scheffler, K
Department High-Field Magnetic Resonance, Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons133483

Lohmann, G
Department High-Field Magnetic Resonance, Max Planck Institute for Biological Cybernetics, Max Planck Society;

External Resource

https://ww6.aievolution.com/hbm2301/index.cfm?do=abs.viewAbs&abs=1802
(Abstract)

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

Fulltext (public)

There are no public fulltexts stored in PuRe

Supplementary Material (public)

There is no public supplementary material available

Citation

Mahler, L., Steiglechner, J., Wang, Q., Scheffler, K., & Lohmann, G. (2023). JudgeMI: Towards Accurate Metrics for Assessing Deep Learning Based Structural MRI Motion Correction. Poster presented at 29th Annual Meeting of the Organization for Human Brain Mapping (OHBM 2023), Montreal, Canada.

Cite as: https://hdl.handle.net/21.11116/0000-000D-8F95-A

Abstract

Structural MRI is often prone to motion artifacts which are particularly pronounced in ultra-high-field MRI, leading to severe image degradation and negatively impacting downstream analysis. In this work, we propose a novel image similarity function that utilizes deep 3D features of pre-trained CNNs as a proxy for human perception of image similarity. We show that it outperforms classical metrics like L1, L2, PSNR and SSIM, and when used as a loss function it improves the performance of MRI motion correction models and address the limitations of per-pixel similarity measures commonly used in regression problems, which are inadequate in capturing structural and content-based differences between images.