Universität zu Köln

Dratsch, Thomas ORCID: 0000-0003-4014-7763, Zäske, Charlotte ORCID: 0000-0003-3746-8523, Siedek, Florian ORCID: 0000-0001-7144-2680, Rauen, Philip ORCID: 0000-0002-3849-6537, Hokamp, Nils Große ORCID: 0000-0001-7928-0487, Sonnabend, Kristina, Maintz, David ORCID: 0000-0002-8942-3776, Bratke, Grischa ORCID: 0000-0002-5696-9828 and Iuga, Andra ORCID: 0000-0002-3694-0235 (2024). Reconstruction of 3D knee MRI using deep learning and compressed sensing: a validation study on healthy volunteers. European Radiology Experimental, 8 (1). pp. 1-9. Springer Nature. ISSN 2509-9280

PDF s41747-024-00446-0.pdf Bereitstellung unter der CC-Lizenz: Creative Commons Attribution. Download (1MB)

Abstract

[Artikel-Nr.: 47] 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.

Item Type:	Article
Creators:	Creators Email ORCID ORCID Put Code Dratsch, Thomas UNSPECIFIED https://orcid.org/0000-0003-4014-7763 UNSPECIFIED Zäske, Charlotte UNSPECIFIED https://orcid.org/0000-0003-3746-8523 UNSPECIFIED Siedek, Florian UNSPECIFIED https://orcid.org/0000-0001-7144-2680 UNSPECIFIED Rauen, Philip UNSPECIFIED https://orcid.org/0000-0002-3849-6537 UNSPECIFIED Hokamp, Nils Große UNSPECIFIED https://orcid.org/0000-0001-7928-0487 UNSPECIFIED Sonnabend, Kristina UNSPECIFIED UNSPECIFIED UNSPECIFIED Maintz, David UNSPECIFIED https://orcid.org/0000-0002-8942-3776 UNSPECIFIED Bratke, Grischa UNSPECIFIED https://orcid.org/0000-0002-5696-9828 UNSPECIFIED Iuga, Andra UNSPECIFIED https://orcid.org/0000-0002-3694-0235 UNSPECIFIED
URN:	urn:nbn:de:hbz:38-815375
Identification Number:	10.1186/s41747-024-00446-0
Journal or Publication Title:	European Radiology Experimental
Volume:	8
Number:	1
Page Range:	pp. 1-9
Number of Pages:	9
Date:	15 April 2024
Publisher:	Springer Nature
ISSN:	2509-9280
Language:	English
Faculty:	Faculty of Medicine
Divisions:	Faculty of Medicine > Radiologische Diagnostik > Institut und Poliklinik für Radiologische Diagnostik
Subjects:	Medical sciences Medicine
Uncontrolled Keywords:	Keywords Language Artifacts ; Artificial intelligence ; Deep learning ; Knee joint ; Magnetic resonance imaging English
['eprint_fieldname_oa_funders' not defined]:	Publikationsfonds UzK
Refereed:	Yes
URI:	http://kups.ub.uni-koeln.de/id/eprint/81537