Skip to main content
Top
Published in: Skeletal Radiology 8/2023

21-03-2023 | Magnetic Resonance Imaging | Scientific Article

Comparison of deep learning-based reconstruction of PROPELLER Shoulder MRI with conventional reconstruction

Authors: Seok Hahn, Jisook Yi, Ho-Joon Lee, Yedaun Lee, Joonsung Lee, Xinzeng Wang, Maggie Fung

Published in: Skeletal Radiology | Issue 8/2023

Login to get access

Abstract

Objective

To compare the image quality and agreement among conventional and accelerated periodically rotated overlapping parallel lines with enhanced reconstruction (PROPELLER) MRI with both conventional reconstruction (CR) and deep learning–based reconstruction (DLR) methods for evaluation of shoulder.

Materials and methods

We included patients who underwent conventional (acquisition time, 8 min) and accelerated (acquisition time, 4 min and 24 s; 45% reduction) PROPELLER shoulder MRI using both CR and DLR methods between February 2021 and February 2022 on a 3 T MRI system. Quantitative evaluation was performed by calculating the signal-to-noise ratio (SNR). Two musculoskeletal radiologists compared the image quality using conventional sequence with CR as the reference standard. Interobserver agreement between image sets for evaluating shoulder was analyzed using weighted/unweighted kappa statistics.

Results

Ninety-two patients with 100 shoulder MRI scans were included. Conventional sequence with DLR had the highest SNR (P < .001), followed by accelerated sequence with DLR, conventional sequence with CR, and accelerated sequence with CR. Comparison of image quality by both readers revealed that conventional sequence with DLR (P = .003 and P < .001) and accelerated sequence with DLR (P = .016 and P < .001) had better image quality than the conventional sequence with CR. Interobserver agreement was substantial to almost perfect for detecting shoulder abnormalities (κ = 0.600–0.884). Agreement between the image sets was substantial to almost perfect (κ = 0.691–1).

Conclusion

Accelerated PROPELLER with DLR showed even better image quality than conventional PROPELLER with CR and interobserver agreement for shoulder pathologies comparable to that of conventional PROPELLER with CR, despite the shorter scan time.
Appendix
Available only for authorised users
Literature
1.
go back to reference Subhas N, Benedick A, Obuchowski NA, Polster JM, Beltran LS, Schils J, et al. Comparison of a fast 5-minute shoulder MRI protocol with a standard shoulder MRI protocol: a multiinstitutional multireader study. AJR Am J Roentgenol. 2017;208(4):W146–54.CrossRefPubMed Subhas N, Benedick A, Obuchowski NA, Polster JM, Beltran LS, Schils J, et al. Comparison of a fast 5-minute shoulder MRI protocol with a standard shoulder MRI protocol: a multiinstitutional multireader study. AJR Am J Roentgenol. 2017;208(4):W146–54.CrossRefPubMed
2.
go back to reference Lee SH, Lee YH, Song H-T, Suh J-S. Rapid acquisition of magnetic resonance imaging of the shoulder using three-dimensional fast spin echo sequence with compressed sensing. Magn Reson Imaging. 2017;42:152–7.CrossRefPubMed Lee SH, Lee YH, Song H-T, Suh J-S. Rapid acquisition of magnetic resonance imaging of the shoulder using three-dimensional fast spin echo sequence with compressed sensing. Magn Reson Imaging. 2017;42:152–7.CrossRefPubMed
3.
go back to reference Del Grande F, Rashidi A, Luna R, Delcogliano M, Stern SE, Dalili D, et al. Five-minute five-sequence knee MRI using combined simultaneous multislice and parallel imaging acceleration: comparison with 10-minute parallel imaging knee MRI. Radiology. 2021;299(3):635–46.CrossRefPubMed Del Grande F, Rashidi A, Luna R, Delcogliano M, Stern SE, Dalili D, et al. Five-minute five-sequence knee MRI using combined simultaneous multislice and parallel imaging acceleration: comparison with 10-minute parallel imaging knee MRI. Radiology. 2021;299(3):635–46.CrossRefPubMed
4.
go back to reference Fritz J, Guggenberger R, Grande FD. Rapid musculoskeletal MRI in 2021: clinical application of advanced accelerated techniques. AJR Am J Roentgenol. 2021;216(3):718–33.CrossRefPubMed Fritz J, Guggenberger R, Grande FD. Rapid musculoskeletal MRI in 2021: clinical application of advanced accelerated techniques. AJR Am J Roentgenol. 2021;216(3):718–33.CrossRefPubMed
5.
go back to reference Kijowski R, Rosas H, Samsonov A, King K, Peters R, Liu F. Knee imaging: Rapid three-dimensional fast spin-echo using compressed sensing. J Magn Reson Imaging. 2017;45(6):1712–22.CrossRefPubMed Kijowski R, Rosas H, Samsonov A, King K, Peters R, Liu F. Knee imaging: Rapid three-dimensional fast spin-echo using compressed sensing. J Magn Reson Imaging. 2017;45(6):1712–22.CrossRefPubMed
6.
go back to reference Hou B, Li Y, Xiong Y, Morelli JN, Wang J, Liu C, et al. Comparison of CAIPIRINHA-accelerated 3D fat-saturated-SPACE MRI with 2D MRI sequences for the assessment of shoulder pathology. Eur Radiol. 2022;32(1):593–601.CrossRefPubMed Hou B, Li Y, Xiong Y, Morelli JN, Wang J, Liu C, et al. Comparison of CAIPIRINHA-accelerated 3D fat-saturated-SPACE MRI with 2D MRI sequences for the assessment of shoulder pathology. Eur Radiol. 2022;32(1):593–601.CrossRefPubMed
7.
go back to reference Pipe JG. Motion correction with PROPELLER MRI: application to head motion and free breathing cardiac imaging. Magn Reson Med. 1999;42(5):963–9.CrossRefPubMed Pipe JG. Motion correction with PROPELLER MRI: application to head motion and free breathing cardiac imaging. Magn Reson Med. 1999;42(5):963–9.CrossRefPubMed
8.
go back to reference Fellner C, Menzel C, Fellner F, Ginthoer C, Zorger N, Schreyer A, et al. BLADE in sagittal T2-weighted MR imaging of the cervical spine. AJNR Am J Neuroradiol. 2010;31(4):674–81.CrossRefPubMedPubMedCentral Fellner C, Menzel C, Fellner F, Ginthoer C, Zorger N, Schreyer A, et al. BLADE in sagittal T2-weighted MR imaging of the cervical spine. AJNR Am J Neuroradiol. 2010;31(4):674–81.CrossRefPubMedPubMedCentral
9.
go back to reference Forbes KP, Pipe JG, Karis JP, Farthing V, Heiserman JE. Brain imaging in the unsedated pediatric patient: comparison of periodically rotated overlapping parallel lines with enhanced reconstruction and single-shot fast spin-echo sequences. AJNR Am J Neuroradiol. 2003;24(5):794–8.PubMedPubMedCentral Forbes KP, Pipe JG, Karis JP, Farthing V, Heiserman JE. Brain imaging in the unsedated pediatric patient: comparison of periodically rotated overlapping parallel lines with enhanced reconstruction and single-shot fast spin-echo sequences. AJNR Am J Neuroradiol. 2003;24(5):794–8.PubMedPubMedCentral
10.
go back to reference Ciet P, Serra G, Bertolo S, Spronk S, Ros M, Fraioli F, et al. Assessment of CF lung disease using motion corrected PROPELLER MRI: a comparison with CT. Eur Radiol. 2016;26(3):780–7.CrossRefPubMed Ciet P, Serra G, Bertolo S, Spronk S, Ros M, Fraioli F, et al. Assessment of CF lung disease using motion corrected PROPELLER MRI: a comparison with CT. Eur Radiol. 2016;26(3):780–7.CrossRefPubMed
11.
go back to reference Lane BF, Vandermeer FQ, Oz RC, Irwin EW, McMillan AB, Wong-You-Cheong JJ. Comparison of sagittal T2-weighted BLADE and fast spin-echo MRI of the female pelvis for motion artifact and lesion detection. AJR Am J Roentgenol. 2011;197(2):W307–13.CrossRefPubMed Lane BF, Vandermeer FQ, Oz RC, Irwin EW, McMillan AB, Wong-You-Cheong JJ. Comparison of sagittal T2-weighted BLADE and fast spin-echo MRI of the female pelvis for motion artifact and lesion detection. AJR Am J Roentgenol. 2011;197(2):W307–13.CrossRefPubMed
12.
go back to reference Dietrich TJ, Ulbrich EJ, Zanetti M, Fucentese SF, Pfirrmann CWA. PROPELLER technique to improve image quality of MRI of the shoulder. AJR Am J Roentgenol. 2011;197(6):W1093–100.CrossRefPubMed Dietrich TJ, Ulbrich EJ, Zanetti M, Fucentese SF, Pfirrmann CWA. PROPELLER technique to improve image quality of MRI of the shoulder. AJR Am J Roentgenol. 2011;197(6):W1093–100.CrossRefPubMed
13.
go back to reference Nagatomo K, Yabuuchi H, Yamasaki Y, Narita H, Kumazawa S, Kojima T, et al. Efficacy of periodically rotated overlapping parallel lines with enhanced reconstruction (PROPELLER) for shoulder magnetic resonance (MR) imaging. Eur J Radiol. 2016;85(10):1735–43.CrossRefPubMed Nagatomo K, Yabuuchi H, Yamasaki Y, Narita H, Kumazawa S, Kojima T, et al. Efficacy of periodically rotated overlapping parallel lines with enhanced reconstruction (PROPELLER) for shoulder magnetic resonance (MR) imaging. Eur J Radiol. 2016;85(10):1735–43.CrossRefPubMed
14.
go back to reference Lavdas E, Vlychou M, Zaloni E, Vassiou K, Tsagkalis A, Dailiana Z, et al. Elimination of motion and pulsation artifacts using BLADE sequences in shoulder MR imaging. Skeletal Radiol. 2015;44(11):1619–26.CrossRefPubMed Lavdas E, Vlychou M, Zaloni E, Vassiou K, Tsagkalis A, Dailiana Z, et al. Elimination of motion and pulsation artifacts using BLADE sequences in shoulder MR imaging. Skeletal Radiol. 2015;44(11):1619–26.CrossRefPubMed
15.
go back to reference Kohli A, Pilkinton DT, Xi Y, Cho G, Moore D, Mohammadi D, et al. Image quality improvement and motion degradation reduction in shoulder MR imaging: comparison of BLADE and rectilinear techniques at 3-Tesla scanning. Skeletal Radiol. 2022;51(12):2291–7. Kohli A, Pilkinton DT, Xi Y, Cho G, Moore D, Mohammadi D, et al. Image quality improvement and motion degradation reduction in shoulder MR imaging: comparison of BLADE and rectilinear techniques at 3-Tesla scanning. Skeletal Radiol. 2022;51(12):2291–7.
17.
go back to reference Ueda T, Ohno Y, Yamamoto K, Murayama K, Ikedo M, Yui M, et al. Deep Learning Reconstruction of Diffusion-weighted MRI Improves Image Quality for Prostatic Imaging. Radiology. 2022;303(2):373–81.CrossRefPubMed Ueda T, Ohno Y, Yamamoto K, Murayama K, Ikedo M, Yui M, et al. Deep Learning Reconstruction of Diffusion-weighted MRI Improves Image Quality for Prostatic Imaging. Radiology. 2022;303(2):373–81.CrossRefPubMed
18.
go back to reference Recht MP, Zbontar J, Sodickson DK, Knoll F, Yakubova N, Sriam A, et al. Using deep learning to accelerate knee MRI at 3 T: results of an interchangeability study. AJR Am J Roentgenol. 2020;215(6):1421.CrossRefPubMedPubMedCentral Recht MP, Zbontar J, Sodickson DK, Knoll F, Yakubova N, Sriam A, et al. Using deep learning to accelerate knee MRI at 3 T: results of an interchangeability study. AJR Am J Roentgenol. 2020;215(6):1421.CrossRefPubMedPubMedCentral
19.
go back to reference Kim M, Kim HS, Kim HJ, Park JE, Park SY, Kim Y, et al. Thin-slice pituitary MRI with deep learning-based reconstruction: diagnostic performance in a postoperative setting. Radiology. 2021;298(1):114–22.CrossRefPubMed Kim M, Kim HS, Kim HJ, Park JE, Park SY, Kim Y, et al. Thin-slice pituitary MRI with deep learning-based reconstruction: diagnostic performance in a postoperative setting. Radiology. 2021;298(1):114–22.CrossRefPubMed
20.
go back to reference Sun S, Tan ET, Mintz DN, Sahr M, Endo Y, Nguyen J, et al. Evaluation of deep learning reconstructed high-resolution 3D lumbar spine MRI. Eur Radiol. 2022;32(9):6167–77.CrossRefPubMed Sun S, Tan ET, Mintz DN, Sahr M, Endo Y, Nguyen J, et al. Evaluation of deep learning reconstructed high-resolution 3D lumbar spine MRI. Eur Radiol. 2022;32(9):6167–77.CrossRefPubMed
21.
go back to reference Yasaka K, Tanishima T, Ohtake Y, Tajima T, Akai H, Ohtomo K, et al. Deep learning reconstruction for 1.5 T cervical spine MRI: effect on interobserver agreement in the evaluation of degenerative changes. Eur Radiol 2022;32(9):6118–6125. Yasaka K, Tanishima T, Ohtake Y, Tajima T, Akai H, Ohtomo K, et al. Deep learning reconstruction for 1.5 T cervical spine MRI: effect on interobserver agreement in the evaluation of degenerative changes. Eur Radiol 2022;32(9):6118–6125.
22.
go back to reference Hahn S, Yi J, Lee H-J, Lee Y, Lim Y-J, Bang J-Y, et al. Image quality and diagnostic performance of accelerated shoulder MRI with deep learning–based reconstruction. AJR Am J Roentgenol 2022;218(3):506–16. Hahn S, Yi J, Lee H-J, Lee Y, Lim Y-J, Bang J-Y, et al. Image quality and diagnostic performance of accelerated shoulder MRI with deep learning–based reconstruction. AJR Am J Roentgenol 2022;218(3):506–16.
23.
go back to reference Johnson PM, Tong A, Donthireddy A, Melamud K, Petrocelli R, Smereka P, et al. Deep learning reconstruction enables highly accelerated biparametric mr imaging of the prostate. J Magn Reson Imaging. 2022;56(1):184–95.CrossRefPubMed Johnson PM, Tong A, Donthireddy A, Melamud K, Petrocelli R, Smereka P, et al. Deep learning reconstruction enables highly accelerated biparametric mr imaging of the prostate. J Magn Reson Imaging. 2022;56(1):184–95.CrossRefPubMed
24.
go back to reference van der Velde N, Hassing HC, Bakker BJ, Wielopolski PA, Lebel RM, Janich MA, et al. Improvement of late gadolinium enhancement image quality using a deep learning-based reconstruction algorithm and its influence on myocardial scar quantification. Eur Radiol. 2021;31(6):3846–55.CrossRefPubMed van der Velde N, Hassing HC, Bakker BJ, Wielopolski PA, Lebel RM, Janich MA, et al. Improvement of late gadolinium enhancement image quality using a deep learning-based reconstruction algorithm and its influence on myocardial scar quantification. Eur Radiol. 2021;31(6):3846–55.CrossRefPubMed
25.
go back to reference Pimpalkhute VA, Page R, Kothari A, Bhurchandi KM, Kamble VM. Digital image noise estimation using DWT coefficients. IEEE Trans Image Process. 2021;30:1962–72.CrossRefPubMed Pimpalkhute VA, Page R, Kothari A, Bhurchandi KM, Kamble VM. Digital image noise estimation using DWT coefficients. IEEE Trans Image Process. 2021;30:1962–72.CrossRefPubMed
26.
go back to reference Liu P, Wang Q, Peng C, Luo B, Zhang J. Combined application of isotropic three-dimensional fast spin echo (3D-FSE-Cube) with 2-point Dixon fat/water separation (FLEX) and 3D-FSE-cube in MR dacryocystography. Br J Radiol. 2019;92(1094):20180157. 1 Liu P, Wang Q, Peng C, Luo B, Zhang J. Combined application of isotropic three-dimensional fast spin echo (3D-FSE-Cube) with 2-point Dixon fat/water separation (FLEX) and 3D-FSE-cube in MR dacryocystography. Br J Radiol. 2019;92(1094):20180157. 1
27.
go back to reference Siegel S. Nonparametric statistics. Am Stat. 1957;11(3):13–9. Siegel S. Nonparametric statistics. Am Stat. 1957;11(3):13–9.
28.
go back to reference Wilcoxon F. Individual comparisons by ranking methods. Biom Bull. 1945;1:80–3.CrossRef Wilcoxon F. Individual comparisons by ranking methods. Biom Bull. 1945;1:80–3.CrossRef
29.
go back to reference Rayat CS. Statistical Methods in Medical Research. Singapore: Springer; 2018. p. 69–79. Rayat CS. Statistical Methods in Medical Research. Singapore: Springer; 2018. p. 69–79.
30.
go back to reference Landis JR, Koch GG. The measurement of observer agreement for categorical data. Biometrics. 1977;33:159–74.CrossRefPubMed Landis JR, Koch GG. The measurement of observer agreement for categorical data. Biometrics. 1977;33:159–74.CrossRefPubMed
31.
go back to reference Holm S. A simple sequentially rejective multiple test procedure. Scand J Stat. 1979;65–70. Holm S. A simple sequentially rejective multiple test procedure. Scand J Stat. 1979;65–70.
32.
go back to reference Glockner JF, Hu HH, Stanley DW, Angelos L, King K. Parallel MR imaging: a user’s guide. Radiographics. 2005;25(5):1279–97.CrossRefPubMed Glockner JF, Hu HH, Stanley DW, Angelos L, King K. Parallel MR imaging: a user’s guide. Radiographics. 2005;25(5):1279–97.CrossRefPubMed
33.
go back to reference Reeder SB. Measurement of signal-to-noise ratio and parallel imaging. Parallel imaging in clinical MR applications. Springer; 2007, p. 49–61. Reeder SB. Measurement of signal-to-noise ratio and parallel imaging. Parallel imaging in clinical MR applications. Springer; 2007, p. 49–61.
35.
go back to reference Chang Y, Pipe JG, Karis JP, Gibbs WN, Zwart NR, Schar M. The effects of SENSE on PROPELLER imaging. Magn Reson Med. 2015;74(6):1598–608.CrossRefPubMed Chang Y, Pipe JG, Karis JP, Gibbs WN, Zwart NR, Schar M. The effects of SENSE on PROPELLER imaging. Magn Reson Med. 2015;74(6):1598–608.CrossRefPubMed
Metadata
Title
Comparison of deep learning-based reconstruction of PROPELLER Shoulder MRI with conventional reconstruction
Authors
Seok Hahn
Jisook Yi
Ho-Joon Lee
Yedaun Lee
Joonsung Lee
Xinzeng Wang
Maggie Fung
Publication date
21-03-2023
Publisher
Springer Berlin Heidelberg
Published in
Skeletal Radiology / Issue 8/2023
Print ISSN: 0364-2348
Electronic ISSN: 1432-2161
DOI
https://doi.org/10.1007/s00256-023-04321-8

Other articles of this Issue 8/2023

Skeletal Radiology 8/2023 Go to the issue

Test Yourself: Question

Neck pain in a teenager