EUVIMEDEUVIMED entdecken
Crossref

Vertex Correspondence and Self-Intersection Reduction in Cortical Surface Reconstruction

Anne-Marie Rickmann, Fabian Bongratz, Christian Wachinger

IEEE Transactions on Medical Imaging · 2025

DOI: 10.1109/tmi.2025.3562443 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2025. Verfasst von Anne-Marie Rickmann und 2 weiteren Autor:innen. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Cerebral Cortex, Magnetic Resonance Imaging, Neuroimaging. Die Arbeit nennt 27 Literaturangaben. Gefördert von: Deutsche Forschungsgemeinschaft, Federal Ministry of Education and Research in the call for Computational Life Sciences.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Mesh-based cortical surface reconstruction is essential for neuroimaging, enabling precise measurements of brain morphology such as cortical thickness. Establishing vertex correspondence between individual cortical meshes and group templates allows vertex-level comparisons, but traditional methods require time-consuming post-processing steps to achieve vertex correspondence. While deep learning has improved accuracy in cortical surface reconstruction, optimizing vertex correspondence has not been the focus of prior work. We introduce Vox2Cortex with Correspondence (V2CC), an extension of Vox2Cortex, which replaces the commonly used Chamfer loss with L1 loss on registered surfaces. This approach improves inter- and intra-subject correspondence, which makes it suitable for direct group comparisons and atlas-based parcellation. Additionally, we analyze mesh self-intersections, categorizing them into minor (neighboring faces) and major (non-neighboring faces) types.To address major self-intersections, which are not effectively handled by standard regularization losses, we propose a novel Self-Proximity loss, designed to adjust non-neighboring vertices within a defined proximity threshold. Comprehensive evaluations demonstrate that recent deep learning methods inadequately address vertex correspondence, often causing inaccuracies in parcellation. In contrast, our method achieves accurate correspondence and reduces self-intersections to below 1% for both pial and white matter surfaces.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedCerebral CortexMagnetic Resonance ImagingNeuroimagingHumansDeep LearningAlgorithms

Förderung

  • Deutsche Forschungsgemeinschaft
  • Federal Ministry of Education and Research in the call for Computational Life Sciences

Zitieren

APA

Rickmann, A. M., Bongratz, F., & Wachinger, C. (2025). Vertex Correspondence and Self-Intersection Reduction in Cortical Surface Reconstruction. IEEE Transactions on Medical Imaging. https://doi.org/10.1109/tmi.2025.3562443

Vancouver

Rickmann AM, Bongratz F, Wachinger C. Vertex Correspondence and Self-Intersection Reduction in Cortical Surface Reconstruction. IEEE Transactions on Medical Imaging. 2025. doi:10.1109/tmi.2025.3562443

BibTeX
@article{Rickmann2025,
  author = {Rickmann, Anne-Marie and Bongratz, Fabian and Wachinger, Christian},
  title = {Vertex Correspondence and Self-Intersection Reduction in Cortical Surface Reconstruction},
  journal = {IEEE Transactions on Medical Imaging},
  year = {2025},
  doi = {10.1109/tmi.2025.3562443}
}
Kostenlos starten →