Metraipolis › archive › dc_f65fab693c16

Volumetric Latent Diffusion for Brain Tumour Segmentation with Missing Modalities — arXiv:2611.08540

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08540
License (as archived)
CC0-1.0
Archived
2026-11-09T23:04:28.491Z
SHA-256 of the archived text
7a3773eb47da56c80d8930572887ac64aed6604b1393ee74661e5f2fe37a449a
Stable URL of this page
https://metraipolis.com/documento/dc_f65fab693c16

How to cite

Volumetric Latent Diffusion for Brain Tumour Segmentation with Missing Modalities — arXiv:2611.08540 — arXiv (en), https://arxiv.org/abs/2611.08540 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f65fab693c16 (Metraipolis archive dc_f65fab693c16, sha256 7a3773eb47da56c80d8930572887ac64aed6604b1393ee74661e5f2fe37a449a)
BibTeX
@misc{dcf65fab693c16,
  title = {Volumetric Latent Diffusion for Brain Tumour Segmentation with Missing Modalities — arXiv:2611.08540},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08540},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f65fab693c16; sha256 7a3773eb47da56c80d8930572887ac64aed6604b1393ee74661e5f2fe37a449a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08540. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Brain tumour segmentation from magnetic resonance imaging normally assumes that all four imaging sequences are available, but in clinical practice one or more are frequently missing. Existing methods for incomplete inputs learn modality-invariant representations or distil from a full-modality teacher, and return a single deterministic mask. Gen- erative formulations instead model a distribution over plausible masks, but the cost of sampling at full resolution has largely confined them to two dimensions. This paper proposes a three-dimensional conditional latent diffusion framework for whole-tumour segmentation from incom- plete multi-sequence MRI. Images and annotations are first compressed by two volumetric autoencoders, which makes diffusion over whole vol- umes affordable, and sequences are dropped at random during training so that a single model handles every combination of missing sequences. Because the model samples rather than predicts, repeated draws also yield a voxel-wise map of disagreement at no extra training cost. Evalu- ations on 2,601 studies from BraTS 2023 and 2024 show that the method reaches 0.955 Dice with all four sequences and 0.904 with FLAIR alone, and that it is the most accurate of the four methods compared in eight of the fifteen configurations. The disagreement between draws widens as sequences are withheld, giving a signal that accompanies the prediction rather than replacing it

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv eess.IV, nuovi lavori del giorno).
Categorie arXiv: Image and Video Processing (eess.IV).
Pagina del lavoro: https://arxiv.org/abs/2611.08540 — 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 2026-11-09T22:59:37.164Z dalla pagina https://arxiv.org/list/eess.IV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).