EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Reconstruction of 3D knee MRI using deep learning and compressed sensing: a validation study on healthy volunteers

Thomas Dratsch, Charlotte Zäske, Florian Siedek, Philip Rauen, Nils Große Hokamp, Kristina Sonnabend, David Maintz, Grischa Bratke, Andra Iuga

European Radiology Experimental · 15.04.2024 · 8 (1)

DOI: 10.1186/s41747-024-00446-0 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Radiology Experimental, online erschienen am 15.04.2024. Verfasst von Thomas Dratsch und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Str. 62, …. Hauptthemen laut MEDLINE: Artificial Intelligence, Deep Learning. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universitätsklinikum Köln.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

To investigate the potential of combining compressed sensing (CS) and artificial intelligence (AI), in particular deep learning (DL), for accelerating three-dimensional (3D) magnetic resonance imaging (MRI) sequences of the knee.

Methods

Twenty healthy volunteers were examined using a 3-T scanner with a fat-saturated 3D proton density sequence with four different acceleration levels (10, 13, 15, and 17). All sequences were accelerated with CS and reconstructed using the conventional and a new DL-based algorithm (CS-AI). Subjective image quality was evaluated by two blinded readers using seven criteria on a 5-point-Likert-scale (overall impression, artifacts, delineation of the anterior cruciate ligament, posterior cruciate ligament, menisci, cartilage, and bone). Using mixed models, all CS-AI sequences were compared to the clinical standard (sense sequence with an acceleration factor of 2) and CS sequences with the same acceleration factor.

Results

3D sequences reconstructed with CS-AI achieved significantly better values for subjective image quality compared to sequences reconstructed with CS with the same acceleration factor ( p ≤ 0.001). The images reconstructed with CS-AI showed that tenfold acceleration may be feasible without significant loss of quality when compared to the reference sequence ( p ≥ 0.999).

Conclusions

For 3-T 3D-MRI of the knee, a DL-based algorithm allowed for additional acceleration of acquisition times compared to the conventional approach. This study, however, is limited by its small sample size and inclusion of only healthy volunteers, indicating the need for further research with a more diverse and larger sample.

Trial registration

DRKS00024156. Relevance statement Using a DL-based algorithm, 54% faster image acquisition (178 s versus 384 s) for 3D-sequences may be possible for 3-T MRI of the knee. Key points • Combination of compressed sensing and DL improved image quality and allows for significant acceleration of 3D knee MRI. • DL-based algorithm achieved better subjective image quality than conventional compressed sensing. • For 3D knee MRI at 3 T, 54% faster image acquisition may be possible. Graphical Abstract

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceDeep LearningHumansHealthy VolunteersAnterior Cruciate LigamentMagnetic Resonance Imaging

Stichwörter der Autor:innen

ArtifactsArtificial intelligenceDeep learningKnee jointMagnetic resonance imaging

Autor:innen und Institutionen

  • Department of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Str. 62, Cologne, 50937, Germany. thomas.dratsch@uk-koeln.de.
  • Department of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Str. 62, Cologne, 50937, Germany.
  • Philips GmbH Market DACH, Röntgenstrasse 22, Hamburg, 22335, Germany.

Förderung

  • Universitätsklinikum Köln

Zitieren

APA

Dratsch, T., Zäske, C., Siedek, F., Rauen, P., Hokamp, N. G., Sonnabend, K., Maintz, D., Bratke, G., & Iuga, A. (2024). Reconstruction of 3D knee MRI using deep learning and compressed sensing: a validation study on healthy volunteers. European Radiology Experimental, 8(1). https://doi.org/10.1186/s41747-024-00446-0

Vancouver

Dratsch T, Zäske C, Siedek F, Rauen P, Hokamp NG, Sonnabend K, et al. Reconstruction of 3D knee MRI using deep learning and compressed sensing: a validation study on healthy volunteers. European Radiology Experimental. 2024;8(1). doi:10.1186/s41747-024-00446-0

BibTeX
@article{Dratsch2024,
  author = {Dratsch, Thomas and Zäske, Charlotte and Siedek, Florian and Rauen, Philip and Hokamp, Nils Große and Sonnabend, Kristina and Maintz, David and Bratke, Grischa and Iuga, Andra},
  title = {Reconstruction of 3D knee MRI using deep learning and compressed sensing: a validation study on healthy volunteers},
  journal = {European Radiology Experimental},
  year = {2024},
  volume = {8},
  number = {1},
  doi = {10.1186/s41747-024-00446-0}
}
Kostenlos starten →