EUVIMEDEUVIMED entdecken
Crossref

Conformable Convolution for Topologically Constrained Learning of Complex Anatomical Structures

Yousef Yeganeh, Goktug Guvercin, Nassir Navab, Azade Farshad

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (14) · 11982-11990

DOI: 10.1609/aaai.v40i14.38186 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yousef Yeganeh und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

While conventional computer vision emphasizes pixel-level and feature-based objectives, medical image analysis of intricate biological structures necessitates explicit representation of their complex topological properties. Despite their successes, deep learning models often struggle to accurately capture the connectivity and continuity of fine, sometimes pixel-thin, yet critical structures due to their reliance on implicit learning from data. To address this challenge, we introduce Conformable Convolution, a novel convolutional layer designed to explicitly impose topological consistency. Conformable Convolution learns adaptive kernel offsets that focus on regions of high topological significance within an image. This prioritization is guided by our proposed Topological Posterior Generator (TPG) module, which leverages persistent homology. The TPG module identifies key topological features and guides the convolutional layers by applying persistent homology to feature maps transformed into cubical complexes. Unlike existing approaches that are merely aware of topology, our method explicitly constrains the learning process to ensure topological correctness. The proposed modules are architecture-agnostic, enabling them to be integrated seamlessly into various architectures. We showcase the effectiveness of our framework in the segmentation task, where preserving the interconnectedness of structures is critical. The results on three diverse datasets demonstrate that our framework effectively preserves the topology both quantitatively and qualitatively.

Zitieren

APA

Yeganeh, Y., Guvercin, G., Navab, N., & Farshad, A. (2026). Conformable Convolution for Topologically Constrained Learning of Complex Anatomical Structures. Proceedings of the AAAI Conference on Artificial Intelligence, 40(14), 11982-11990. https://doi.org/10.1609/aaai.v40i14.38186

Vancouver

Yeganeh Y, Guvercin G, Navab N, Farshad A. Conformable Convolution for Topologically Constrained Learning of Complex Anatomical Structures. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(14):11982-11990. doi:10.1609/aaai.v40i14.38186

BibTeX
@article{Yeganeh2026,
  author = {Yeganeh, Yousef and Guvercin, Goktug and Navab, Nassir and Farshad, Azade},
  title = {Conformable Convolution for Topologically Constrained Learning of Complex Anatomical Structures},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {14},
  pages = {11982--11990},
  doi = {10.1609/aaai.v40i14.38186}
}
Kostenlos starten →