Metraipolis › archive › dc_be970886397d

An Accurate and Interpretable Hyper Graph Neural Network for GBM Survival Prediction — arXiv:2609.25088

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.25088
License (as archived): CC0-1.0
Archived: 2026-10-08T13:44:48.538Z
SHA-256 of the archived text: ef222afb5751b3239a68c3a677ba72c79ee60874004748583f4d510997024234
Stable URL of this page: https://metraipolis.com/documento/dc_be970886397d

How to cite

An Accurate and Interpretable Hyper Graph Neural Network for GBM Survival Prediction — arXiv:2609.25088 — arXiv (en), https://arxiv.org/abs/2609.25088 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_be970886397d (Metraipolis archive dc_be970886397d, sha256 ef222afb5751b3239a68c3a677ba72c79ee60874004748583f4d510997024234)

BibTeX

@misc{dcbe970886397d,
  title = {An Accurate and Interpretable Hyper Graph Neural Network for GBM Survival Prediction — arXiv:2609.25088},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25088},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_be970886397d; sha256 ef222afb5751b3239a68c3a677ba72c79ee60874004748583f4d510997024234},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25088. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Survival prediction for glioblastoma multiforme (GBM) demands models that are both accurate and interpretable, yet existing approaches treat these objectives as com- peting, where performant models sacrifice transparency, while interpretable models accept degraded predictive power. We argue that this trade-off is not inherent. Graph neural net- works offer a structural foundation for extracting interpretable, explainable representations without compromising discriminative ability. Furthermore, current methods typically rely on a single imaging modality, underutilizing the complementary information available across multi-modal MRI and clinical metadata. We propose a multi-modal framework that inte- grates three components to address both objectives simultaneously: (1) a sheaf hypergraph neural network that captures higher-order relationships among tissue patches through direc- tional, asymmetric message passing; (2) a concept bottleneck layer that compresses learned representations into clinically grounded concepts, enforcing ante-hoc interpretability; and (3) an extension sufficiency test (EST) regularizer that penalizes unfaithful explanations during training, ensuring that model explanations genuinely reflect the internal decision process. Clinical and genomic features are incorporated through gated fusion, preserving the dominant prognostic signal of molecular markers while retaining concept-level traceabil- ity. Evaluated on 593 patients from the UPenn-GBM dataset under 5-fold cross-validation, our framework achieves a concordance index of 0.643 with the lowest fold-level variance among all compared models (std = 0.015). To our knowledge, this is the first work to unify sheaf hypergraph convolution, concept bottleneck supervision, and EST regularization for interpretable survival prediction from brain MRI

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.25088 — 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 2026-10-08T13:18:38.054Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).