Is a 3-Minute Knee MRI Protocol Sufficient for Daily Clinical Practice? A SuperResolution Reconstruction Approach Using AI and Compressed Sensing

<b>Objectives:</b> 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. <b>Methods:</b> In this prospective study, a total of 20 volunteers underwent imaging of...

Full description

Saved in:
Bibliographic Details
Main Authors: Robert Hahnfeldt, Robert Terzis, Thomas Dratsch, Lajos Maximilian Basten, Philip Rauen, Johannes Oppermann, David Grevenstein, Jan Paul Janßen, Nour El-Hoda Abou Zeid, Kristina Sonnabend, Christoph Katemann, Stephan Skornitzke, David Maintz, Jonathan Kottlors, Grischa Bratke, Andra-Iza Iuga
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/15/10/1206
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849711807387664384
author Robert Hahnfeldt
Robert Terzis
Thomas Dratsch
Lajos Maximilian Basten
Philip Rauen
Johannes Oppermann
David Grevenstein
Jan Paul Janßen
Nour El-Hoda Abou Zeid
Kristina Sonnabend
Christoph Katemann
Stephan Skornitzke
David Maintz
Jonathan Kottlors
Grischa Bratke
Andra-Iza Iuga
author_facet Robert Hahnfeldt
Robert Terzis
Thomas Dratsch
Lajos Maximilian Basten
Philip Rauen
Johannes Oppermann
David Grevenstein
Jan Paul Janßen
Nour El-Hoda Abou Zeid
Kristina Sonnabend
Christoph Katemann
Stephan Skornitzke
David Maintz
Jonathan Kottlors
Grischa Bratke
Andra-Iza Iuga
author_sort Robert Hahnfeldt
collection DOAJ
description <b>Objectives:</b> 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. <b>Methods:</b> 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. <b>Results:</b> 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. <b>Conclusions:</b> The CS-SuperRes method enables a 2D knee protocol to be completed in 3 min, with improved accuracy compared to the clinical standard.
format Article
id doaj-art-eef7f3d71be44df892d423bf43bbfe41
institution DOAJ
issn 2075-4418
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-eef7f3d71be44df892d423bf43bbfe412025-08-20T03:14:31ZengMDPI AGDiagnostics2075-44182025-05-011510120610.3390/diagnostics15101206Is a 3-Minute Knee MRI Protocol Sufficient for Daily Clinical Practice? A SuperResolution Reconstruction Approach Using AI and Compressed SensingRobert Hahnfeldt0Robert Terzis1Thomas Dratsch2Lajos Maximilian Basten3Philip Rauen4Johannes Oppermann5David Grevenstein6Jan Paul Janßen7Nour El-Hoda Abou Zeid8Kristina Sonnabend9Christoph Katemann10Stephan Skornitzke11David Maintz12Jonathan Kottlors13Grischa Bratke14Andra-Iza Iuga15Department of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50923 Cologne, GermanyDepartment of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50923 Cologne, GermanyDepartment of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50923 Cologne, GermanyDepartment of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50923 Cologne, GermanyDepartment of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50923 Cologne, GermanyOrthopaedic Surgery and Traumatology, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50923 Cologne, GermanyOrthopaedic Surgery and Traumatology, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50923 Cologne, GermanyDepartment of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50923 Cologne, GermanyDepartment of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50923 Cologne, GermanyDepartment of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50923 Cologne, GermanyPhilips GmbH Market DACH, 22335 Hamburg, GermanyDepartment of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50923 Cologne, GermanyDepartment of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50923 Cologne, GermanyDepartment of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50923 Cologne, GermanyDepartment of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50923 Cologne, GermanyDepartment of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50923 Cologne, Germany<b>Objectives:</b> 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. <b>Methods:</b> 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. <b>Results:</b> 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. <b>Conclusions:</b> The CS-SuperRes method enables a 2D knee protocol to be completed in 3 min, with improved accuracy compared to the clinical standard.https://www.mdpi.com/2075-4418/15/10/1206magnetic resonance imagingartificial intelligencemusculoskeletal radiologysuper resolution
spellingShingle Robert Hahnfeldt
Robert Terzis
Thomas Dratsch
Lajos Maximilian Basten
Philip Rauen
Johannes Oppermann
David Grevenstein
Jan Paul Janßen
Nour El-Hoda Abou Zeid
Kristina Sonnabend
Christoph Katemann
Stephan Skornitzke
David Maintz
Jonathan Kottlors
Grischa Bratke
Andra-Iza Iuga
Is a 3-Minute Knee MRI Protocol Sufficient for Daily Clinical Practice? A SuperResolution Reconstruction Approach Using AI and Compressed Sensing
Diagnostics
magnetic resonance imaging
artificial intelligence
musculoskeletal radiology
super resolution
title Is a 3-Minute Knee MRI Protocol Sufficient for Daily Clinical Practice? A SuperResolution Reconstruction Approach Using AI and Compressed Sensing
title_full Is a 3-Minute Knee MRI Protocol Sufficient for Daily Clinical Practice? A SuperResolution Reconstruction Approach Using AI and Compressed Sensing
title_fullStr Is a 3-Minute Knee MRI Protocol Sufficient for Daily Clinical Practice? A SuperResolution Reconstruction Approach Using AI and Compressed Sensing
title_full_unstemmed Is a 3-Minute Knee MRI Protocol Sufficient for Daily Clinical Practice? A SuperResolution Reconstruction Approach Using AI and Compressed Sensing
title_short Is a 3-Minute Knee MRI Protocol Sufficient for Daily Clinical Practice? A SuperResolution Reconstruction Approach Using AI and Compressed Sensing
title_sort is a 3 minute knee mri protocol sufficient for daily clinical practice a superresolution reconstruction approach using ai and compressed sensing
topic magnetic resonance imaging
artificial intelligence
musculoskeletal radiology
super resolution
url https://www.mdpi.com/2075-4418/15/10/1206
work_keys_str_mv AT roberthahnfeldt isa3minutekneemriprotocolsufficientfordailyclinicalpracticeasuperresolutionreconstructionapproachusingaiandcompressedsensing
AT robertterzis isa3minutekneemriprotocolsufficientfordailyclinicalpracticeasuperresolutionreconstructionapproachusingaiandcompressedsensing
AT thomasdratsch isa3minutekneemriprotocolsufficientfordailyclinicalpracticeasuperresolutionreconstructionapproachusingaiandcompressedsensing
AT lajosmaximilianbasten isa3minutekneemriprotocolsufficientfordailyclinicalpracticeasuperresolutionreconstructionapproachusingaiandcompressedsensing
AT philiprauen isa3minutekneemriprotocolsufficientfordailyclinicalpracticeasuperresolutionreconstructionapproachusingaiandcompressedsensing
AT johannesoppermann isa3minutekneemriprotocolsufficientfordailyclinicalpracticeasuperresolutionreconstructionapproachusingaiandcompressedsensing
AT davidgrevenstein isa3minutekneemriprotocolsufficientfordailyclinicalpracticeasuperresolutionreconstructionapproachusingaiandcompressedsensing
AT janpauljanßen isa3minutekneemriprotocolsufficientfordailyclinicalpracticeasuperresolutionreconstructionapproachusingaiandcompressedsensing
AT nourelhodaabouzeid isa3minutekneemriprotocolsufficientfordailyclinicalpracticeasuperresolutionreconstructionapproachusingaiandcompressedsensing
AT kristinasonnabend isa3minutekneemriprotocolsufficientfordailyclinicalpracticeasuperresolutionreconstructionapproachusingaiandcompressedsensing
AT christophkatemann isa3minutekneemriprotocolsufficientfordailyclinicalpracticeasuperresolutionreconstructionapproachusingaiandcompressedsensing
AT stephanskornitzke isa3minutekneemriprotocolsufficientfordailyclinicalpracticeasuperresolutionreconstructionapproachusingaiandcompressedsensing
AT davidmaintz isa3minutekneemriprotocolsufficientfordailyclinicalpracticeasuperresolutionreconstructionapproachusingaiandcompressedsensing
AT jonathankottlors isa3minutekneemriprotocolsufficientfordailyclinicalpracticeasuperresolutionreconstructionapproachusingaiandcompressedsensing
AT grischabratke isa3minutekneemriprotocolsufficientfordailyclinicalpracticeasuperresolutionreconstructionapproachusingaiandcompressedsensing
AT andraizaiuga isa3minutekneemriprotocolsufficientfordailyclinicalpracticeasuperresolutionreconstructionapproachusingaiandcompressedsensing