EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Benchmarking deep learning‐based low‐dose CT image denoising algorithms

Elias Eulig, Björn Ommer, Marc Kachelrieß

Medical Physics · 2024-12 · 51 (12) · 8776-8788

DOI: 10.1002/mp.17379 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Physics, online erschienen am 17.09.2024. Verfasst von Elias Eulig und 2 weiteren Autor:innen. Beteiligte Einrichtung: Division of X-Ray Imaging and Computed Tomography, German Cancer Research Center (DKFZ), Heidelberg, Germany. Hauptthemen laut MEDLINE: Deep Learning, Benchmarking, Tomography, X-Ray Computed, Radiation Dosage. Die Arbeit wurde bisher 44-mal zitiert (Crossref) und nennt 79 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Helmholtz International Graduate School for Cancer Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Long‐lasting efforts have been made to reduce radiation dose and thus the potential radiation risk to the patient for computed tomography (CT) acquisitions without severe deterioration of image quality. To this end, various techniques have been employed over the years including iterative reconstruction methods and noise reduction algorithms.

Purpose

Recently, deep learning‐based methods for noise reduction became increasingly popular and a multitude of papers claim ever improving performance both quantitatively and qualitatively. However, the lack of a standardized benchmark setup and inconsistencies in experimental design across studies hinder the verifiability and reproducibility of reported results.

Methods

In this study, we propose a benchmark setup to overcome those flaws and improve reproducibility and verifiability of experimental results in the field. We perform a comprehensive and fair evaluation of several state‐of‐the‐art methods using this standardized setup.

Results

Our evaluation reveals that most deep learning‐based methods show statistically similar performance, and improvements over the past years have been marginal at best.

Conclusions

This study highlights the need for a more rigorous and fair evaluation of novel deep learning‐based methods for low‐dose CT image denoising. Our benchmark setup is a first and important step towards this direction and can be used by future researchers to evaluate their algorithms.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningBenchmarkingTomography, X-Ray ComputedRadiation DosageImage Processing, Computer-AssistedSignal-To-Noise RatioAlgorithmsHumans

Stichwörter der Autor:innen

benchmarkingcomputed tomographydeep learningdenoisinglow‐dose

Autor:innen und Institutionen

  • Division of X-Ray Imaging and Computed Tomography, German Cancer Research Center (DKFZ), Heidelberg, Germany.
  • Faculty of Physics and Astronomy, Heidelberg University, Heidelberg, Germany.
  • CompVis @ LMU Munich, MCML, Munich, Germany.
  • Medical Faculty Heidelberg, Heidelberg University, Heidelberg, Germany.

Förderung

  • Helmholtz International Graduate School for Cancer Research

Zitieren

APA

Eulig, E., Ommer, B., & Kachelrieß, M. (2024). Benchmarking deep learning‐based low‐dose CT image denoising algorithms. Medical Physics, 51(12), 8776-8788. https://doi.org/10.1002/mp.17379

Vancouver

Eulig E, Ommer B, Kachelrieß M. Benchmarking deep learning‐based low‐dose CT image denoising algorithms. Medical Physics. 2024;51(12):8776-8788. doi:10.1002/mp.17379

BibTeX
@article{Eulig2024,
  author = {Eulig, Elias and Ommer, Björn and Kachelrieß, Marc},
  title = {Benchmarking deep learning‐based low‐dose CT image denoising algorithms},
  journal = {Medical Physics},
  year = {2024},
  volume = {51},
  number = {12},
  pages = {8776--8788},
  doi = {10.1002/mp.17379}
}
Kostenlos starten →