EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Tuning Butterworth filter’s parameters in SPECT reconstructions via kernel-based Bayesian optimization with a no-reference image evaluation metric

Luca Pastrello, Diego Cecchin, Gabriele Santin, Francesco Marchetti

Mathematical Medicine and Biology: A Journal of the IMA · 2025

DOI: 10.1093/imammb/dqaf012 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematical Medicine and Biology: A Journal of the IMA, 2025. Verfasst von Luca Pastrello und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mathematics 'Tullio Levi-Civita', University of Padova, Via Trieste 63, 35121, Italy. Hauptthemen laut MEDLINE: Tomography, Emission-Computed, Single-Photon, Image Processing, Computer-Assisted. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In Single Photon Emission Computed Tomography (SPECT), the image reconstruction process involves many tunable parameters that have a significant impact on the quality of the resulting clinical images. Traditional image quality evaluation often relies on expert judgment and full-reference metrics such as Mean Squared Error and Structural Similarity Index. However, these approaches are limited by their subjectivity or the need for a ground-truth image. In this paper, we investigate the usage of a No-Reference Image Quality Assessment method in SPECT imaging, employing the Perception-based Image QUality Evaluator (PIQUE) score. Precisely, we propose a novel application of PIQUE in evaluating SPECT images reconstructed via filtered backprojection using a parameter-dependent Butterworth filter. For the optimization of filter’s parameters, we adopt a kernel-based Bayesian optimization framework grounded in reproducing kernel Hilbert space theory, highlighting the connections to recent greedy approximation techniques such as $P$- and $f$-greedy. Experimental results in a concrete clinical setting for SPECT imaging show the potential of this optimization approach for an objective and quantitative assessment of image quality, without requiring a reference image.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Tomography, Emission-Computed, Single-PhotonImage Processing, Computer-AssistedBayes TheoremHumansAlgorithmsMathematical ConceptsPhantoms, Imaging

Stichwörter der Autor:innen

Bayesian optimizationSPECT imaginggreedy kernel modelsno-reference metric

Autor:innen und Institutionen

  • Department of Mathematics 'Tullio Levi-Civita', University of Padova, Via Trieste 63, 35121, Italy.
  • Nuclear Medicine Unit, Department of Medicine-DIMED and Padova Neuroscience Center (PNC), University of Padova, Via Giustiniani 2, 35128, Italy.
  • Department of Environmental Sciences, Informatics and Statistics, Ca' Foscari University of Venice, Via Torino 155, 30172, Italy.
  • Department of Mathematics 'Tullio Levi-Civita' and Padova Neuroscience Center (PNC), University of Padova, Via Trieste 63, 35121, Italy.

Zitieren

APA

Pastrello, L., Cecchin, D., Santin, G., & Marchetti, F. (2025). Tuning Butterworth filter’s parameters in SPECT reconstructions via kernel-based Bayesian optimization with a no-reference image evaluation metric. Mathematical Medicine and Biology: A Journal of the IMA. https://doi.org/10.1093/imammb/dqaf012

Vancouver

Pastrello L, Cecchin D, Santin G, Marchetti F. Tuning Butterworth filter’s parameters in SPECT reconstructions via kernel-based Bayesian optimization with a no-reference image evaluation metric. Mathematical Medicine and Biology: A Journal of the IMA. 2025. doi:10.1093/imammb/dqaf012

BibTeX
@article{Pastrello2025,
  author = {Pastrello, Luca and Cecchin, Diego and Santin, Gabriele and Marchetti, Francesco},
  title = {Tuning Butterworth filter’s parameters in SPECT reconstructions via kernel-based Bayesian optimization with a no-reference image evaluation metric},
  journal = {Mathematical Medicine and Biology: A Journal of the IMA},
  year = {2025},
  doi = {10.1093/imammb/dqaf012}
}
Kostenlos starten →