Metraipolis › archive › dc_c7d60083becc

Multimodal Deep Learning for Uncertainty-Aware Radiation Pneumonitis Risk Prediction — arXiv:2608.28937

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.28937
License (as archived)
CC0-1.0
Archived
2026-10-17T10:43:05.323Z
SHA-256 of the archived text
fb8a1f7b04635b4e024b605d6167da0116c12bb70fc09f8039613f6be7e0d11c
Stable URL of this page
https://metraipolis.com/documento/dc_c7d60083becc

How to cite

Multimodal Deep Learning for Uncertainty-Aware Radiation Pneumonitis Risk Prediction — arXiv:2608.28937 — arXiv (en), https://arxiv.org/abs/2608.28937 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c7d60083becc (Metraipolis archive dc_c7d60083becc, sha256 fb8a1f7b04635b4e024b605d6167da0116c12bb70fc09f8039613f6be7e0d11c)
BibTeX
@misc{dcc7d60083becc,
  title = {Multimodal Deep Learning for Uncertainty-Aware Radiation Pneumonitis Risk Prediction — arXiv:2608.28937},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28937},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c7d60083becc; sha256 fb8a1f7b04635b4e024b605d6167da0116c12bb70fc09f8039613f6be7e0d11c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28937. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Radiation pneumonitis (RP) is a common and clinically significant toxicity of thoracic radiation therapy that can cause pulmonary morbidity and impair quality of life. Although conventional dose-volume histogram-based metrics and normal tissue complication probability models are widely used for RP risk assessment, they inadequately capture the complex spatial, anatomical, and patient-specific factors underlying radiation-induced lung injury. Recent machine learning approaches have improved RP risk prediction by integrating multimodal clinical and imaging information; however, most provide a point risk estimate without quantifying the reliability of individual predictions, limiting their potential clinical utility. We propose a Multimodal Bayesian Diffusion Transformer (MM-DiT) framework that jointly estimates RP risk and characterizes the sources of predictive uncertainty. MM-DiT integrates planning computed tomography (CT) images and three-dimensional radiation dose distributions through self-supervised multimodal pre-training, reducing reliance on limited and potentially noisy toxicity labels. The resulting representations are further refined using a latent diffusion transformer and transferred to a Bayesian prediction framework for probabilistic RP risk estimation. A learnable label-noise model is incorporated to explicitly account for uncertainty arising from imperfect toxicity annotations. Therefore, it provides individualized RP risk estimates with complementary measures of aleatoric, epistemic, and label uncertainty, enabling assessment of prediction reliability at the individual-patient level. We evaluated MM-DiT in two independent cohorts using complementary assessments of predictive discrimination, calibration, and uncertainty. The results demonstrate its potential to provide accurate RP risk estimates while quantifying clinically relevant sources of predictive uncertainty.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in eess.IV).
Categorie arXiv: Image and Video Processing (eess.IV).
Pagina del lavoro: https://arxiv.org/abs/2608.28937 — 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 2026-10-17T10:33:05.791Z dalla pagina https://arxiv.org/catchup/eess.IV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).