Universität zu Köln

Hahnfeldt, Robert ORCID: 0000-0001-7997-3216, Terzis, Robert ORCID: 0009-0007-1068-8477, Dratsch, Thomas, Basten, Lajos Maximilian ORCID: 0000-0001-7273-6111, Rauen, Philip ORCID: 0000-0002-3849-6537, Oppermann, Johannes ORCID: 0000-0002-0742-7440, Grevenstein, David ORCID: 0000-0003-4823-7739, Janßen, Jan Paul ORCID: 0000-0003-0980-4606, Zeid, Nour El-Hoda Abou, Sonnabend, Kristina ORCID: 0000-0003-3064-0247, Katemann, Christoph ORCID: 0000-0002-5199-0644, Skornitzke, Stephan, Maintz, David ORCID: 0000-0002-8942-3776, Kottlors, Jonathan ORCID: 0000-0001-5021-6895, Bratke, Grischa ORCID: 0000-0002-5696-9828 and Iuga, Andra-Iza ORCID: 0000-0002-3694-0235 (2025). Is a 3-Minute Knee MRI Protocol Sufficient for Daily Clinical Practice? A SuperResolution Reconstruction Approach Using AI and Compressed Sensing. Diagnostics, 15 (10). MDPI. ISSN 2075-4418

PDF diagnostics-15-01206-v2.pdf Bereitstellung unter der CC-Lizenz: Creative Commons Attribution. Download (4MB)

Abstract

[Artikel-Nr.: 1206] Objectives: The purpose of this study was to assess whether a 3-min 2D knee protocol can meet the needs for clinical application if using a SuperResolution reconstruction approach. Methods: In this prospective study, a total of 20 volunteers underwent imaging of the knee using a 3T MRI scanner (Philips Ingenia Elition X 3.0T, Philips). The imaging protocol, consisting of a fat-saturated 2D proton density sequence in coronal, sagittal, and transverse orientations, as well as a sagittal T1-weighted sequence, was acquired with standard and ultra-low resolution. The standard sequences were reconstructed using an AI-assisted Compressed SENSE method (SmartSpeed). The ultra-low-resolution sequences have been reconstructed using a vendor-provided prototype. Four experienced readers (two radiologists and two orthopedic surgeons) evaluated the sequences for image quality, anatomical structures, and incidental pathologies. The consensus evaluation of two different experienced radiologists specialized in musculoskeletal imaging served as the gold standard. Results: The acquisition time for the entire protocol was 11:01 min for standard resolution and 03:36 min for ultra-low resolution. In the overall assessment, CS-SuperRes-reconstructed sequences showed slightly improved accuracy and increased specificity compared to the standard CS-AI method (0.87 vs. 0.86 and 0.9 vs. 0.87, respectively), while the standard method exhibited a higher sensitivity (0.73 vs. 0.57). Overall, 24 out of 40 pathologies were detected in the ultra-low-resolution images compared to 26 in the standard images. Conclusions: The CS-SuperRes method enables a 2D knee protocol to be completed in 3 min, with improved accuracy compared to the clinical standard.

Item Type:	Article
Creators:	Creators Email ORCID ORCID Put Code Hahnfeldt, Robert UNSPECIFIED https://orcid.org/0000-0001-7997-3216 UNSPECIFIED Terzis, Robert UNSPECIFIED https://orcid.org/0009-0007-1068-8477 UNSPECIFIED Dratsch, Thomas UNSPECIFIED UNSPECIFIED UNSPECIFIED Basten, Lajos Maximilian UNSPECIFIED https://orcid.org/0000-0001-7273-6111 UNSPECIFIED Rauen, Philip UNSPECIFIED https://orcid.org/0000-0002-3849-6537 UNSPECIFIED Oppermann, Johannes UNSPECIFIED https://orcid.org/0000-0002-0742-7440 UNSPECIFIED Grevenstein, David UNSPECIFIED https://orcid.org/0000-0003-4823-7739 UNSPECIFIED Janßen, Jan Paul UNSPECIFIED https://orcid.org/0000-0003-0980-4606 UNSPECIFIED Zeid, Nour El-Hoda Abou UNSPECIFIED UNSPECIFIED UNSPECIFIED Sonnabend, Kristina UNSPECIFIED https://orcid.org/0000-0003-3064-0247 UNSPECIFIED Katemann, Christoph UNSPECIFIED https://orcid.org/0000-0002-5199-0644 UNSPECIFIED Skornitzke, Stephan UNSPECIFIED UNSPECIFIED UNSPECIFIED Maintz, David UNSPECIFIED https://orcid.org/0000-0002-8942-3776 UNSPECIFIED Kottlors, Jonathan UNSPECIFIED https://orcid.org/0000-0001-5021-6895 UNSPECIFIED Bratke, Grischa UNSPECIFIED https://orcid.org/0000-0002-5696-9828 UNSPECIFIED Iuga, Andra-Iza UNSPECIFIED https://orcid.org/0000-0002-3694-0235 UNSPECIFIED
URN:	urn:nbn:de:hbz:38-799937
Identification Number:	10.3390/diagnostics15101206
Journal or Publication Title:	Diagnostics
Volume:	15
Number:	10
Number of Pages:	14
Date:	9 May 2025
Publisher:	MDPI
ISSN:	2075-4418
Language:	English
Faculty:	Faculty of Medicine
Divisions:	Faculty of Medicine > Orthopädie > Klinik und Poliklinik für Orthopädie und Unfallchirurgie Faculty of Medicine > Radiologische Diagnostik > Institut und Poliklinik für Radiologische Diagnostik
Subjects:	Medical sciences Medicine
Uncontrolled Keywords:	Keywords Language magnetic resonance imaging ; artificial intelligence ; musculoskeletal radiology ; super resolution English
['eprint_fieldname_oa_funders' not defined]:	Publikationsfonds UzK
Refereed:	Yes
URI:	http://kups.ub.uni-koeln.de/id/eprint/79993