Top

Published in:

Open Access 07-04-2022 | Magnetic Resonance Imaging | Musculoskeletal

Feasibility of an accelerated 2D-multi-contrast knee MRI protocol using deep-learning image reconstruction: a prospective intraindividual comparison with a standard MRI protocol

Authors: Judith Herrmann, Gabriel Keller, Sebastian Gassenmaier, Dominik Nickel, Gregor Koerzdoerfer, Mahmoud Mostapha, Haidara Almansour, Saif Afat, Ahmed E. Othman

Published in: European Radiology | Issue 9/2022

Abstract

Objectives

The aim of this study was to evaluate the image quality and diagnostic performance of a deep-learning (DL)–accelerated two–dimensional (2D) turbo spin echo (TSE) MRI of the knee at 1.5 and 3 T in clinical routine in comparison to standard MRI.

Material and methods

Sixty participants, who underwent knee MRI at 1.5 and 3 T between October/2020 and March/2021 with a protocol using standard 2D–TSE (TSE_S) and DL–accelerated 2D–TSE sequences (TSE_DL), were enrolled in this prospective institutional review board–approved study. Three radiologists assessed the sequences regarding structural abnormalities and evaluated the images concerning overall image quality, artifacts, noise, sharpness, subjective signal-to-noise ratio, and diagnostic confidence using a Likert scale (1–5, 5 = best).

Results

Overall image quality for TSE_DL was rated to be excellent (median 5, IQR 4–5), significantly higher compared to TSE_S (median 5, IQR 4 – 5, p < 0.05), showing significantly lower extents of noise and improved sharpness (p < 0.001). Inter- and intra-reader agreement was almost perfect (κ = 0.92–1.00) for the detection of internal derangement and substantial to almost perfect (κ = 0.58–0.98) for the assessment of cartilage defects. No difference was found concerning the detection of bone marrow edema and fractures. The diagnostic confidence of TSE_DL was rated to be comparable to that of TSE_S (median 5, IQR 5–5, p > 0.05). Time of acquisition could be reduced to 6:11 min using TSE_DL compared to 11:56 min for a protocol using TSE_S.

Conclusion

TSE_DL of the knee is clinically feasible, showing excellent image quality and equivalent diagnostic performance compared to TSE_S, reducing the acquisition time about 50%.

Key Points

• Deep-learning reconstructed TSE imaging is able to almost halve the acquisition time of a three-plane knee MRI with proton density and T1-weighted images, from 11:56 min to 6:11 min at 3 T.

• Deep-learning reconstructed TSE imaging of the knee provided significant improvement of noise levels (p < 0.001), providing higher image quality (p < 0.05) compared to conventional TSE imaging.

• Deep-learning reconstructed TSE imaging of the knee had similar diagnostic performance for internal derangement of the knee compared to standard TSE.

Available only for authorised users

Vahey TN, Meyer SF, Shelbourne KD, Klootwyk TE (1994) MR imaging of anterior cruciate ligament injuries. Magn Reson Imaging Clin N Am 2:365–380CrossRef

Schnaiter JW, Roemer F, McKenna-Kuettner A et al (2018) Diagnostic accuracy of an MRI protocol of the knee accelerated through parallel imaging in correlation to arthroscopy. Rofo 190:265–272CrossRef

Smith C, McGarvey C, Harb Z et al (2016) Diagnostic efficacy of 3-T MRI for knee injuries using arthroscopy as a reference standard: a meta-analysis. AJR Am J Roentgenol 207:369–377CrossRef

Fritz J, Fritz B, Thawait GG, Meyer H, Gilson WD, Raithel E (2016) Three-dimensional CAIPIRINHA SPACE TSE for 5-minute high-resolution MRI of the knee. Invest Radiol 51:609–617CrossRef

Notohamiprodjo M, Horng A, Pietschmann MF et al (2009) MRI of the knee at 3T: first clinical results with an isotropic PDfs-weighted 3D-TSE-sequence. Invest Radiol 44:585–597CrossRef

Kijowski R, Davis KW, Blankenbaker DG, Woods MA, Del Rio AM, De Smet AA (2012) Evaluation of the menisci of the knee joint using three-dimensional isotropic resolution fast spin-echo imaging: diagnostic performance in 250 patients with surgical correlation. Skeletal Radiol 41:169–178CrossRef

Del Grande F, Delcogliano M, Guglielmi R et al (2018) Fully automated 10-minute 3D CAIPIRINHA SPACE TSE MRI of the knee in adults: a multicenter, multireader, multifield-strength validation study. Invest Radiol 53:689–697CrossRef

Recht MP, Zbontar J, Sodickson DK et al (2020) Using deep learning to accelerate knee MRI at 3 T: results of an interchangeability study. AJR Am J Roentgenol. https://doi.org/10.2214/AJR.20.23313:1-9

Schlemper J, Caballero J, Hajnal JV, Price AN, Rueckert D (2018) A deep cascade of convolutional neural networks for dynamic MR image reconstruction. IEEE Trans Med Imaging 37:491–503CrossRef

10.

Hammernik K, Klatzer T, Kobler E et al (2018) Learning a variational network for reconstruction of accelerated MRI data. Magn Reson Med 79:3055–3071CrossRef

11.

Flack VF, Afifi A, Lachenbruch P, Schouten H (1988) Sample size determinations for the two rater kappa statistic. Psychometrika 53:321–325CrossRef

12.

Knoll F, Hammernik K, Kobler E, Pock T, Recht MP, Sodickson DK (2019) Assessment of the generalization of learned image reconstruction and the potential for transfer learning. Magn Reson Med 81:116–128CrossRef

13.

Herrmann J, Koerzdoerfer G, Nickel D et al (2021) Feasibility and implementation of a deep learning MR reconstruction for TSE sequences in musculoskeletal imaging. Diagnostics 11(8):1484. https://doi.org/10.3390/diagnostics11081484CrossRefPubMedPubMedCentral

14.

Kannengiesser S, Maihle B, Nadar M (2016) Universal iterative denoising of complex-valued volumetric MR image data using supplementary information. Proc ISMRM, pp 1779

15.

Chaudhari AS, Fang Z, Kogan F et al (2018) Super-resolution musculoskeletal MRI using deep learning. Magn Reson Med 80:2139–2154CrossRef

16.

Defazio A, Murrell T, Recht MP (2020) MRI banding removal via adversarial training. arXiv preprint arXiv:200108699

17.

Notohamiprodjo M, Horng A, Kuschel B et al (2012) 3D-imaging of the knee with an optimized 3D-FSE-sequence and a 15-channel knee-coil. Eur J Radiol 81:3441–3449CrossRef

18.

Lee S, Lee GY, Kim S, Park YB, Lee HJ (2020) Clinical utility of fat-suppressed 3-dimensional controlled aliasing in parallel imaging results in higher acceleration sampling perfection with application optimized contrast using different flip angle evolutions MRI of the knee in adults. Br J Radiol 93:20190725CrossRef

19.

Fritz J, Raithel E, Thawait GK, Gilson W, Papp DF (2016) Six-fold acceleration of high-spatial resolution 3D SPACE MRI of the knee through incoherent k-space undersampling and iterative reconstruction-first experience. Investig Radiol 51:400–409CrossRef

20.

Fritz J, Fritz B, Zhang J et al (2017) Simultaneous multislice accelerated turbo spin echo magnetic resonance imaging: comparison and combination with in-plane parallel imaging acceleration for high-resolution magnetic resonance imaging of the knee. Invest Radiol 52:529–537CrossRef

21.

Iuga AI, Abdullayev N, Weiss K et al (2020) Accelerated MRI of the knee. Quality and efficiency of compressed sensing. Eur J Radiol 132:109273CrossRef

22.

Matcuk GR, Gross JS, Fields BKK, Cen S (2020) Compressed sensing MR imaging (CS-MRI) of the knee: assessment of quality, inter-reader agreement, and acquisition time. Magn Reson Med Sci 19:254–258CrossRef

23.

Niitsu M, Ikeda K (2003) Routine MR examination of the knee using parallel imaging. Clin Radiol 58:801–807CrossRef

24.

Kreitner KF, Romaneehsen B, Krummenauer F, Oberholzer K, Muller LP, Duber C (2006) Fast magnetic resonance imaging of the knee using a parallel acquisition technique (mSENSE): a prospective performance evaluation. Eur Radiol 16:1659–1666CrossRef

25.

Deshmane A, Gulani V, Griswold MA, Seiberlich N (2012) Parallel MR imaging. J Magn Reson Imaging 36:55–72CrossRef

26.

Benali S, Johnston PR, Gholipour A et al (2018) Simultaneous multi-slice accelerated turbo spin echo of the knee in pediatric patients. Skeletal Radiol 47:821–831CrossRef

27.

Herrmann J, Gassenmaier S, Nickel D et al (2020) Diagnostic confidence and feasibility of a deep learning accelerated HASTE sequence of the abdomen in a single breath-hold. Invest Radiol. https://doi.org/10.1097/rli.0000000000000743

28.

Herrmann J, Nickel D, Mugler JP 3rd et al (2021) Development and evaluation of deep learning-accelerated single-breath-hold abdominal HASTE at 3 T using variable refocusing flip angles. Investig Radiol. https://doi.org/10.1097/RLI.0000000000000785

29.

Gassenmaier S, Afat S, Nickel D, Mostapha M, Herrmann J, Othman AE (2021) Deep learning-accelerated T2-weighted imaging of the prostate: reduction of acquisition time and improvement of image quality. Eur J Radiol 137:109600CrossRef

30.

Almansour H, Gassenmaier S, Nickel D et al (2021) Deep learning-based superresolution reconstruction for upper abdominal magnetic resonance imaging: an analysis of image quality, diagnostic confidence, and lesion conspicuity. Invest Radiol. https://doi.org/10.1097/RLI.0000000000000769

31.

Gassenmaier S, Afat S, Nickel MD et al (2021) Accelerated T2-weighted TSE imaging of the prostate using deep learning image reconstruction: a prospective comparison with standard T2-weighted TSE imaging. Cancers 13(14):3593. https://doi.org/10.3390/cancers13143593CrossRefPubMedPubMedCentral

32.

Quatman CE, Hettrich CM, Schmitt LC, Spindler KP (2011) The clinical utility and diagnostic performance of magnetic resonance imaging for identification of early and advanced knee osteoarthritis: a systematic review. Am J Sports Med 39:1557–1568CrossRef

33.

Jaspan ON, Fleysher R, Lipton ML (2015) Compressed sensing MRI: a review of the clinical literature. Br J Radiol 88:20150487CrossRef

34.

Lustig M, Donoho D, Pauly JM (2007) Sparse MRI: the application of compressed sensing for rapid MR imaging. Magn Reson Med 58:1182–1195CrossRef

Title: Feasibility of an accelerated 2D-multi-contrast knee MRI protocol using deep-learning image reconstruction: a prospective intraindividual comparison with a standard MRI protocol
Authors: Judith Herrmann
Gabriel Keller
Sebastian Gassenmaier
Dominik Nickel
Gregor Koerzdoerfer
Mahmoud Mostapha
Haidara Almansour
Saif Afat
Ahmed E. Othman
Publication date: 07-04-2022
Publisher: Springer Berlin Heidelberg
Keywords: Magnetic Resonance Imaging
Magnetic Resonance Imaging
Published in: European Radiology / Issue 9/2022
Print ISSN: 0938-7994
Electronic ISSN: 1432-1084
DOI: https://doi.org/10.1007/s00330-022-08753-z

Keynote webinar | Spotlight on sleep in brain health

Springer Medicine

Feasibility of an accelerated 2D-multi-contrast knee MRI protocol using deep-learning image reconstruction: a prospective intraindividual comparison with a standard MRI protocol

Abstract

Objectives

Material and methods

Results

Conclusion

Key Points

Keynote webinar | Spotlight on sleep in brain health

Springer Medicine

Abstract

Objectives

Material and methods

Results

Conclusion

Key Points

Please log in to get access to this content

Other articles of this Issue 9/2022

A deep learning masked segmentation alternative to manual segmentation in biparametric MRI prostate cancer radiomics

Radiomics in precision medicine for gastric cancer: opportunities and challenges

Arterial transit artifacts on arterial spin labeling MRI can predict cerebral hyperperfusion after carotid endarterectomy: an initial study

Screen-detected and interval breast cancer after concordant and discordant interpretations in a population based screening program using independent double reading

Two nomograms for differentiating mass-forming chronic pancreatitis from pancreatic ductal adenocarcinoma in patients with chronic pancreatitis

Sonographic assessment of minor extrathyroidal extension of papillary thyroid microcarcinoma involving the posterior thyroid capsule