Metraipolis › archive › dc_01cb396b1031

Geometric-to-Semantic Spherical Transfer Learning for Cortical Sulci Labeling — arXiv:2609.12627

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.12627
License (as archived)
CC0-1.0
Archived
2026-10-16T03:15:49.633Z
SHA-256 of the archived text
7047213650582f6c38f4b64f9ae2be3bb464f0c5fd9652ea209e48183e192731
Stable URL of this page
https://metraipolis.com/documento/dc_01cb396b1031

How to cite

Geometric-to-Semantic Spherical Transfer Learning for Cortical Sulci Labeling — arXiv:2609.12627 — arXiv (en), https://arxiv.org/abs/2609.12627 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_01cb396b1031 (Metraipolis archive dc_01cb396b1031, sha256 7047213650582f6c38f4b64f9ae2be3bb464f0c5fd9652ea209e48183e192731)
BibTeX
@misc{dc01cb396b1031,
  title = {Geometric-to-Semantic Spherical Transfer Learning for Cortical Sulci Labeling — arXiv:2609.12627},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12627},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_01cb396b1031; sha256 7047213650582f6c38f4b64f9ae2be3bb464f0c5fd9652ea209e48183e192731},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12627. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deep learning on cortical surfaces faces a dilemma: capturing the complex topology of over 60 nomenclature-dependent sulci per hemisphere requires high-capacity models, yet the extreme scarcity of expert annotations ($N=62$ subjects) inevitably causes overfitting. Standard supervised approaches fail to generalize in this data-scarce regime, particularly for variable and small sulci where topological ambiguity is high. To overcome this limitation, we introduce a Geometric-to-Semantic Spherical Transfer Learning framework. First, we leverage massive unlabeled data (UK Biobank, $\approx$30,000 subjects) to pre-train a spherical encoder using a locally-optimized strategy. By relying solely on continuous surface features (curvature and depth), the relevance of this pre-training is confirmed by the model's ability to detect localized and rare topological traits, such as sulcal interruptions. The downstream labeling task, however, introduces extracted sulcal fundi (lines) as an explicit semantic input. To bridge this dimensional domain gap (from purely geometric to semantic) without causing catastrophic forgetting, these anatomical lines are integrated into the pre-trained backbone via a soft-initialized Topological Prior Injector. Our experiments demonstrate that this approach outperforms fully supervised baselines trained from scratch, achieving a mean Dice of 0.77. Crucially, a local analysis reveals that the self-supervised geometric priors yield the largest performance gains on variable and tertiary sulci (up to 14.8%), confirming that learning the cortex shape is highly beneficial for identifying its rarest parts.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.12627 — 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 2026-10-16T03:05:44.054Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).