EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A diffusion-based generative prior approach to sparse-view computed tomography

Davide Evangelista, Pasquale Cascarano, Elena Loli Piccolomini

Computerized Medical Imaging and Graphics · 2026-08 · 134 · 102802

DOI: 10.1016/j.compmedimag.2026.102802 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computerized Medical Imaging and Graphics, 2026-08. Verfasst von Davide Evangelista und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, Mura Anteo Zamboni, 7, Bologna, 40126, Bologna, Italy. Electronic address: davide.evangelista5@unibo.…. Hauptthemen laut MEDLINE: Tomography, X-Ray Computed, Image Processing, Computer-Assisted. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Gruppo Nazionale per il Calcolo Scientifico.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The reconstruction of X-rays CT images from sparse or limited-angle geometries is a highly challenging task. The lack of data typically results in artifacts in the reconstructed image and may even lead to object distortions. For this reason, the use of deep generative models in this context has great interest and potential success. In the Deep Generative Prior (DGP) framework, the use of diffusion-based generative models is combined with an iterative optimization algorithm for the reconstruction of CT images from sinograms acquired under sparse geometries, to maintain the explainability of a model-based approach while introducing the generative power of a neural network. There are therefore several aspects that can be further investigated within these frameworks to improve reconstruction quality, such as image generation, the model, and the iterative algorithm used to solve the minimization problem, for which we propose modifications with respect to existing approaches. The results obtained even under highly sparse geometries are very promising, although further research is clearly needed in this direction.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Tomography, X-Ray ComputedImage Processing, Computer-AssistedAlgorithmsHumansGenerative Artificial IntelligenceNeural Networks, Computer

Stichwörter der Autor:innen

Deep Generative PriorDiffusion modelsModel-based reconstructionRegularizationSparse tomography

Autor:innen und Institutionen

  • Department of Computer Science and Engineering, Mura Anteo Zamboni, 7, Bologna, 40126, Bologna, Italy. Electronic address: davide.evangelista5@unibo.it.
  • Department of the Arts, University of Bologna, via Barberia, 4, Bologna, 40123, Bologna, Italy. Electronic address: pasquale.cascarano2@unibo.it.
  • Department of Computer Science and Engineering, Mura Anteo Zamboni, 7, Bologna, 40126, Bologna, Italy. Electronic address: elena.loli@unibo.it.

Förderung

  • Gruppo Nazionale per il Calcolo Scientifico

Zitieren

APA

Evangelista, D., Cascarano, P., & Loli Piccolomini, E. (2026). A diffusion-based generative prior approach to sparse-view computed tomography. Computerized Medical Imaging and Graphics, 134, 102802. https://doi.org/10.1016/j.compmedimag.2026.102802

Vancouver

Evangelista D, Cascarano P, Loli Piccolomini E. A diffusion-based generative prior approach to sparse-view computed tomography. Computerized Medical Imaging and Graphics. 2026;134:102802. doi:10.1016/j.compmedimag.2026.102802

BibTeX
@article{Evangelista2026,
  author = {Evangelista, Davide and Cascarano, Pasquale and Loli Piccolomini, Elena},
  title = {A diffusion-based generative prior approach to sparse-view computed tomography},
  journal = {Computerized Medical Imaging and Graphics},
  year = {2026},
  volume = {134},
  pages = {102802},
  doi = {10.1016/j.compmedimag.2026.102802}
}
Kostenlos starten →