Polychromatic neural CBCT reconstruction through density-attenuation modeling
Physics in Medicine & Biology · 2025
DOI: 10.1088/1361-6560/ae28af ↗Kurz gefasst
Fachartikel in der Zeitschrift Physics in Medicine & Biology, 2025. Verfasst von Lukas Birklein und 3 weiteren Autor:innen. Beteiligte Einrichtung: Johannes Gutenberg University, Mainz, Germany. Hauptthemen laut MEDLINE: Cone-Beam Computed Tomography, Neural Networks, Computer, Image Processing, Computer-Assisted. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Monochromatic cone beam computed tomography reconstruction algorithms are still most prominent in practice. Since the x-ray detectors of today’s machines are mostly energy integrating detectors and thus not able to resolve photon energy levels, reconstruction artifacts, often termed as beam-hardening artifacts, are a frequent observation. We propose a polychromatic 3D reconstruction technique, using a coordinate based neural representation, that requires zero additional prior information, in which we model attenuation related to a fixed energy level E 0 together with its derivative. We concurrently optimize an intermediate density value for each spatial position together with a composite attenuation function. It assigns each intermediate density value its attenuation coefficient and computes the derivative of the attenuation coefficient w.r.t. the energy. We implement this function as a neural network that models a monotonic relationship between intermediate density and attenuation. In our results we can show that the proposed method is able to considerably improve reconstruction quality in various scenarios, both quantitatively using a synthetic numerical phantom as well as visual quality in real-world clinical examples.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Johannes Gutenberg University, Mainz, Germany.
- Rhein-Main University of Applied Sciences, Wiesbaden, Germany.
- University of Bern, Bern, Switzerland.
ORCID-Profile: Lukas Birklein, Elmar Schömer, Ulrich Schwanecke, Ralf Schulze
Zitieren
APA
Birklein, L., Schömer, E., Schwanecke, U., & Schulze, R. (2025). Polychromatic neural CBCT reconstruction through density-attenuation modeling. Physics in Medicine & Biology. https://doi.org/10.1088/1361-6560/ae28af
Vancouver
Birklein L, Schömer E, Schwanecke U, Schulze R. Polychromatic neural CBCT reconstruction through density-attenuation modeling. Physics in Medicine & Biology. 2025. doi:10.1088/1361-6560/ae28af
BibTeX
@article{Birklein2025,
author = {Birklein, Lukas and Schömer, Elmar and Schwanecke, Ulrich and Schulze, Ralf},
title = {Polychromatic neural CBCT reconstruction through density-attenuation modeling},
journal = {Physics in Medicine & Biology},
year = {2025},
doi = {10.1088/1361-6560/ae28af}
}
EUVIMED