Metraipolis › archive › dc_10be778e9895

Meta-Initialization of Implicit Neural Representations to Accelerate Deformable Medical Image Registration — arXiv:2610.37965

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.37965
License (as archived)
CC0-1.0
Archived
2026-11-01T02:26:50.530Z
SHA-256 of the archived text
3980a60b62391d0c0bd8c402128b7cc1887abb35e7de074cf69e5c7a41264704
Stable URL of this page
https://metraipolis.com/documento/dc_10be778e9895

How to cite

Meta-Initialization of Implicit Neural Representations to Accelerate Deformable Medical Image Registration — arXiv:2610.37965 — arXiv (en), https://arxiv.org/abs/2610.37965 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_10be778e9895 (Metraipolis archive dc_10be778e9895, sha256 3980a60b62391d0c0bd8c402128b7cc1887abb35e7de074cf69e5c7a41264704)
BibTeX
@misc{dc10be778e9895,
  title = {Meta-Initialization of Implicit Neural Representations to Accelerate Deformable Medical Image Registration — arXiv:2610.37965},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.37965},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_10be778e9895; sha256 3980a60b62391d0c0bd8c402128b7cc1887abb35e7de074cf69e5c7a41264704},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.37965. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Implicit neural representation (INR) methods for deformable medical image registration require the network parameters to be optimized for each new image pair, making adaptation speed a practical limitation. This work investigates whether early adaptation can be accelerated using an initialization learned from a collection of previously solved registration tasks. We examine two schemes: Reptile meta-initialization and STRAINER transfer of the shared component of a coordinate network. KAN-IDIR is used as the base INR displacement-field model. Experiments are conducted on OASIS-1, with 364 consecutive pairs used for training and 49 pairs for test-time adaptation. Registration quality is evaluated using mean Dice and HD95, together with the fraction of voxels with a negative Jacobian determinant at iteration 1500. In the configurations studied, both schemes yield higher Dice and lower HD95 at early iterations than random initialization. Reptile numerically outperforms STRAINER under a small iteration budget, although their pretraining budgets are not matched. As the number of iterations increases, the differences between the schemes shrink. STRAINER pretraining takes 39-40 minutes, compared with 44.98 hours for Reptile.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.37965 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-01T02:12:44.237Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).