Hybrid deep-learning-based denoising method for compressed sensing in pituitary MRI: comparison with the conventional wavelet-based denoising method.
Deep learning
Magnetic resonance imaging
Pituitary diseases
Retrospective studies
Journal
European radiology
ISSN: 1432-1084
Titre abrégé: Eur Radiol
Pays: Germany
ID NLM: 9114774
Informations de publication
Date de publication:
Jul 2022
Jul 2022
Historique:
received:
19
07
2021
accepted:
07
11
2021
revised:
10
10
2021
pubmed:
17
2
2022
medline:
24
6
2022
entrez:
16
2
2022
Statut:
ppublish
Résumé
This study aimed to evaluate the efficacy of a combined wavelet and deep-learning reconstruction (DLR) method for under-sampled pituitary MRI. This retrospective study included 28 consecutive patients who underwent under-sampled pituitary T2-weighted images (T2WI). Images were reconstructed using either the conventional wavelet denoising method (wavelet method) or the wavelet and DLR methods combined (hybrid DLR method) at five denoising levels. The signal-to-noise ratio (SNR) of the CSF, hypothalamic, and pituitary images and the contrast between structures were compared between the two image types. Noise quality, contrast, sharpness, artifacts, and overall image quality were evaluated by two board-certified radiologists. The quantitative and the qualitative analyses were performed with robust two-way repeated analyses of variance. Using the hybrid DLR method, the SNR of the CSF progressively increased as denoising levels increased. By contrast, with the wavelet method, the SNR of the CSF, hypothalamus, and pituitary did not increase at higher denoising levels. There was a significant main effect of denoising methods (p < 0.001) and denoising levels (p < 0.001), and an interaction between denoising methods and denoising levels (p < 0.001). For all five qualitative scores, there was a significant main effect of denoising methods (p < 0.001) and an interaction between denoising methods and denoising levels (p < 0.001). The hybrid DLR method can provide higher image quality for T2WI of the pituitary with compressed sensing (CS) than the wavelet method alone, especially at higher denoising levels. • The signal-to-noise ratios of cerebrospinal fluid progressively increased with the hybrid DLR method, with an increase in the denoising level for cerebrospinal fluid in pituitary T2WI with CS. • The signal-to-noise ratios of cerebrospinal fluid using the conventional wavelet method did not increase at higher denoising levels. • All qualitative scores of hybrid deep-learning reconstructions at all denoising levels were higher than those for the wavelet denoising method.
Identifiants
pubmed: 35169896
doi: 10.1007/s00330-022-08552-6
pii: 10.1007/s00330-022-08552-6
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
4527-4536Informations de copyright
© 2022. The Author(s), under exclusive licence to European Society of Radiology.
Références
Pinker K, Ba-Ssalamah A, Wolfsberger S, Mlynarik V, Knosp E, Trattnig S (2005) The value of high-field MRI (3T) in the assessment of sellar lesions. Eur J Radiol 54:327–334
doi: 10.1016/j.ejrad.2004.08.006
Wang Y (2000) Description of parallel imaging in MRI using multiple coils. Magn Reson Med 44:495–499
doi: 10.1002/1522-2594(200009)44:3<495::AID-MRM23>3.0.CO;2-S
Hamilton J, Franson D, Seiberlich N (2017) Recent advances in parallel imaging for MRI. Prog Nucl Magn Reson Spectrosc 101:71–95
doi: 10.1016/j.pnmrs.2017.04.002
Ham CL, Engels JM, van de Wiel GT, Machielsen A (1997) Peripheral nerve stimulation during MRI: effects of high gradient amplitudes and switching rates. J Magn Reson Imaging 7:933–937
doi: 10.1002/jmri.1880070524
Zhou R, Huang W, Yang Y et al (2018) Simple motion correction strategy reduces respiratory-induced motion artifacts for k-t accelerated and compressed-sensing cardiovascular magnetic resonance perfusion imaging. J Cardiovasc Magn Reson 20:6
doi: 10.1186/s12968-018-0427-1
Li S, Zhu Y, Xie Y, Gao S (2018) Dynamic magnetic resonance imaging method based on golden-ratio cartesian sampling and compressed sensing. PLoS One 13:e0191569
doi: 10.1371/journal.pone.0191569
Lustig M, Donoho D, Pauly JM (2007) Sparse MRI: the application of compressed sensing for rapid MR imaging. Magn Reson Med 58:1182–1195
doi: 10.1002/mrm.21391
Monch S, Sollmann N, Hock A, Zimmer C, Kirschke JS, Hedderich DM (2020) Magnetic resonance imaging of the brain using compressed sensing - quality assessment in daily clinical routine. Clin Neuroradiol 30:279–286
doi: 10.1007/s00062-019-00789-x
Jiang D, Dou W, Vosters L, Xu X, Sun Y, Tan T (2018) Denoising of 3D magnetic resonance images with multi-channel residual learning of convolutional neural network. Jpn J Radiol 36:566–574
doi: 10.1007/s11604-018-0758-8
Kidoh M, Shinoda K, Kitajima M et al (2020) Deep learning based noise reduction for brain MR imaging: tests on phantoms and healthy volunteers. Magn Reson Med Sci 19:195–206
doi: 10.2463/mrms.mp.2019-0018
Uetani H, Nakaura T, Kitajima M et al (2021) A preliminary study of deep learning-based reconstruction specialized for denoising in high-frequency domain: usefulness in high-resolution three-dimensional magnetic resonance cisternography of the cerebellopontine angle. Neuroradiology 63:63–71
doi: 10.1007/s00234-020-02513-w
Basser PJ, Mattiello J, LeBihan D (1994) Estimation of the effective self-diffusion tensor from the NMR spin echo. J Magn Reson B 103:247–254
doi: 10.1006/jmrb.1994.1037
Yoshida M, Nakaura T, Inoue T et al (2018) Magnetic resonance cholangiopancreatography with GRASE sequence at 3.0T: does it improve image quality and acquisition time as compared with 3D TSE? Eur Radiol 28:2436–2443
doi: 10.1007/s00330-017-5240-y
Meixner CR, Liebig P, Speier P et al (2019) High resolution time-of-flight MR-angiography at 7T exploiting VERSE saturation, compressed sensing and segmentation. Magn Reson Imaging 63:193–204
doi: 10.1016/j.mri.2019.08.014
Stalder AF, Schmidt M, Quick HH et al (2015) Highly undersampled contrast-enhanced MRA with iterative reconstruction: integration in a clinical setting. Magn Reson Med 74:1652–1660
doi: 10.1002/mrm.25565
Marin D, Nelson RC, Schindera ST et al (2010) Low-tube-voltage, high-tube-current multidetector abdominal CT: improved image quality and decreased radiation dose with adaptive statistical iterative reconstruction algorithm--initial clinical experience. Radiology 254:145–153
doi: 10.1148/radiol.09090094
Li K, Tang J, Chen GH (2014) Statistical model based iterative reconstruction (MBIR) in clinical CT systems: experimental assessment of noise performance. Med Phys 41:041906
doi: 10.1118/1.4867863
Li G, Liu X, Dodge CT, Jensen CT, Rong XJ (2016) A noise power spectrum study of a new model-based iterative reconstruction system: Veo 3.0. J Appl Clin Med Phys 17:428–439
doi: 10.1120/jacmp.v17i5.6225