Hyperelastic Regularization for Near-Diffeomorphic Transformer-Based Brain MRI Registration
Journal of Imaging · 24.06.2026 · 12 (7) · 276
DOI: 10.3390/jimaging12070276 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 24.06.2026. Verfasst von Shiyi Xu und 2 weiteren Autor:innen. Beteiligte Einrichtung: Capital Medical University Second Clinical School, Capital Medical University, Beijing 100050, China. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NCRR NIH HHS, NIA NIH HHS, NIMH NIH HHS.
Abstract (Originalsprache)
Transformer-based deformable brain MRI registration achieves high overlap accuracy, but predicted displacement fields can contain voxels with a non-positive Jacobian determinant—local foldings that violate the diffeomorphism assumption required by tensor-based morphometry and atlas-fusion segmentation workflows. We introduce HypEReg, a non-linear hyperelastic regularizer that acts directly on the Jacobian determinant of the predicted displacement field. HypEReg couples a clamped-rational volume-distortion penalty (detJϕ−1)2/max(detJϕ,ϵ) with an explicit per-voxel anti-folding hinge [max(0,ϵ−detJϕ)]2, integrated as a purely loss-side module into a TransMorph backbone with no inference-graph modifications. On the IXI atlas-to-subject benchmark (115 test subjects), HypEReg-TransMorph maintains grouped Dice (0.7537) while reducing the det(Jϕ)≤0 voxel ratio from 1.502×10−2 (TransMorph) to 1.5×10−5, with identical per-case runtime and parameter count to the unregularized baseline. In strict zero-shot transfer to OASIS Learn2Reg test pairs (no fine-tuning), HypEReg-TransMorph achieves Dice 0.7756 with a det(Jϕ)≤0 ratio of 7.6×10−5, roughly two orders of magnitude below plain TransMorph zero-shot (Dice 0.7691; ratio 9.6×10−3); downstream multi-atlas label fusion further confirms the practical benefit of fold suppression (fused Dice 0.8271 vs. 0.8201 for TransMorph). OASIS-2 longitudinal and ROI analyses support deformation plausibility (lower folding/SDlogJ and stronger ventricular ROI agreement), while clinical-covariate associations remain exploratory rather than biomarker-validating. Determinant-level, non-linear hyperelastic regularization substantially suppresses folding in Transformer dense-flow brain MRI registration while preserving alignment accuracy and adding zero inference cost, providing a practical drop-in regularization strategy that improves the reliability of deformation fields for morphometry-oriented deformable registration.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Capital Medical University Second Clinical School, Capital Medical University, Beijing 100050, China.
- School of Physics, Peking University, Beijing 100871, China.
- Dexmal, Beijing 100096, China.
ORCID-Profile: Shiyi Xu, Mohan Xu, Erjin Zhou
Förderung
- NCRR NIH HHS
- NIA NIH HHS
- NIMH NIH HHS
Zitieren
APA
Xu, S., Xu, M., & Zhou, E. (2026). Hyperelastic Regularization for Near-Diffeomorphic Transformer-Based Brain MRI Registration. Journal of Imaging, 12(7), 276. https://doi.org/10.3390/jimaging12070276
Vancouver
Xu S, Xu M, Zhou E. Hyperelastic Regularization for Near-Diffeomorphic Transformer-Based Brain MRI Registration. Journal of Imaging. 2026;12(7):276. doi:10.3390/jimaging12070276
BibTeX
@article{Xu2026,
author = {Xu, Shiyi and Xu, Mohan and Zhou, Erjin},
title = {Hyperelastic Regularization for Near-Diffeomorphic Transformer-Based Brain MRI Registration},
journal = {Journal of Imaging},
year = {2026},
volume = {12},
number = {7},
pages = {276},
doi = {10.3390/jimaging12070276}
}
EUVIMED