Deep Learning for Efficient Reconstruction of Highly Accelerated 3D FLAIR MRI in Neurological Deficits

Overview

Journal MAGMA

Publisher Springer

Date 2024 Aug 30

PMID 39212832

Authors

Luka C Liebrand

Dimitrios Karkalousos

Emilie Poirion

Bart J Emmer

Stefan D Roosendaal

Henk A Marquering

Charles B L M Majoie

Julien Savatovsky

Matthan W A Caan

Affiliations

Soon will be listed here.

Abstract

Objective: To compare compressed sensing (CS) and the Cascades of Independently Recurrent Inference Machines (CIRIM) with respect to image quality and reconstruction times when 12-fold accelerated scans of patients with neurological deficits are reconstructed.

Materials And Methods: Twelve-fold accelerated 3D T2-FLAIR images were obtained from a cohort of 62 patients with neurological deficits on 3 T MRI. Images were reconstructed offline via CS and the CIRIM. Image quality was assessed in a blinded and randomized manner by two experienced interventional neuroradiologists and one experienced pediatric neuroradiologist on imaging artifacts, perceived spatial resolution (sharpness), anatomic conspicuity, diagnostic confidence, and contrast. The methods were also compared in terms of self-referenced quality metrics, image resolution, patient groups and reconstruction time. In ten scans, the contrast ratio (CR) was determined between lesions and white matter. The effect of acceleration factor was assessed in a publicly available fully sampled dataset, since ground truth data are not available in prospectively accelerated clinical scans. Specifically, 451 FLAIR scans, including scans with white matter lesions, were adopted from the FastMRI database to evaluate structural similarity (SSIM) and the CR of lesions and white matter on ranging acceleration factors from four-fold up to 12-fold.

Results: Interventional neuroradiologists significantly preferred the CIRIM for imaging artifacts, anatomic conspicuity, and contrast. One rater significantly preferred the CIRIM in terms of sharpness and diagnostic confidence. The pediatric neuroradiologist preferred CS for imaging artifacts and sharpness. Compared to CS, the CIRIM reconstructions significantly improved in terms of imaging artifacts and anatomic conspicuity (p < 0.01) for higher resolution scans while yielding a 28% higher SNR (p = 0.001) and a 5.8% lower CR (p = 0.04). There were no differences between patient groups. Additionally, CIRIM was five times faster than CS was. An increasing acceleration factor did not lead to changes in CR (p = 0.92), but led to lower SSIM (p = 0.002).

Discussion: Patients with neurological deficits can undergo MRI at a range of moderate to high acceleration. DL reconstruction outperforms CS in terms of image resolution, efficient denoising with a modest reduction in contrast and reduced reconstruction times.

References

Griswold M, Jakob P, Heidemann R, Nittka M, Jellus V, Wang J . Generalized autocalibrating partially parallel acquisitions (GRAPPA). Magn Reson Med. 2002; 47(6):1202-10. DOI: 10.1002/mrm.10171. View

Estler A, Hauser T, Mengel A, Brunnee M, Zerweck L, Richter V . Deep Learning Accelerated Image Reconstruction of Fluid-Attenuated Inversion Recovery Sequence in Brain Imaging: Reduction of Acquisition Time and Improvement of Image Quality. Acad Radiol. 2023; 31(1):180-186. DOI: 10.1016/j.acra.2023.05.010. View

Zhao R, Yaman B, Zhang Y, Stewart R, Dixon A, Knoll F . fastMRI+, Clinical pathology annotations for knee and brain fully sampled magnetic resonance imaging data. Sci Data. 2022; 9(1):152. PMC: 8983757. DOI: 10.1038/s41597-022-01255-z. View

Forman S, Cohen J, Fitzgerald M, Eddy W, Mintun M, Noll D . Improved assessment of significant activation in functional magnetic resonance imaging (fMRI): use of a cluster-size threshold. Magn Reson Med. 1995; 33(5):636-47. DOI: 10.1002/mrm.1910330508. View

Lonning K, Putzky P, Sonke J, Reneman L, Caan M, Welling M . Recurrent inference machines for reconstructing heterogeneous MRI data. Med Image Anal. 2019; 53:64-78. DOI: 10.1016/j.media.2019.01.005. View

Vranic J, Cross N, Wang Y, Hippe D, De Weerdt E, Mossa-Basha M . Compressed Sensing-Sensitivity Encoding (CS-SENSE) Accelerated Brain Imaging: Reduced Scan Time without Reduced Image Quality. AJNR Am J Neuroradiol. 2018; 40(1):92-98. PMC: 7048595. DOI: 10.3174/ajnr.A5905. View

Pruessmann K, Weiger M, Scheidegger M, Boesiger P . SENSE: sensitivity encoding for fast MRI. Magn Reson Med. 1999; 42(5):952-62. View

Jiang L, Peng M, Geng W, Chen H, Su H, Zhao B . FLAIR hyperintensities-DWI mismatch in acute stroke: associations with DWI volume and functional outcome. Brain Imaging Behav. 2019; 14(4):1230-1237. DOI: 10.1007/s11682-019-00156-x. View

Shaul R, David I, Shitrit O, Riklin Raviv T . Subsampled brain MRI reconstruction by generative adversarial neural networks. Med Image Anal. 2020; 65:101747. DOI: 10.1016/j.media.2020.101747. View

10.

Muckley M, Riemenschneider B, Radmanesh A, Kim S, Jeong G, Ko J . Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstruction. IEEE Trans Med Imaging. 2021; 40(9):2306-2317. PMC: 8428775. DOI: 10.1109/TMI.2021.3075856. View

11.

Lu S, Qi M, Zhang X, Mu X, Schmidt M, Sun Y . Clinical Evaluation of Highly Accelerated Compressed Sensing Time-of-Flight MR Angiography for Intracranial Arterial Stenosis. AJNR Am J Neuroradiol. 2018; 39(10):1833-1838. PMC: 7410741. DOI: 10.3174/ajnr.A5786. View

12.

Okano Y, Ishimatsu K, Kato Y, Yamaga J, Kuwahara K, Okumoto K . Clinical features of stroke mimics in the emergency department. Acute Med Surg. 2018; 5(3):241-248. PMC: 6028791. DOI: 10.1002/ams2.338. View

13.

Hammernik K, Klatzer T, Kobler E, Recht M, Sodickson D, Pock T . Learning a variational network for reconstruction of accelerated MRI data. Magn Reson Med. 2017; 79(6):3055-3071. PMC: 5902683. DOI: 10.1002/mrm.26977. View

14.

Garcia-Tornel A, Campos D, Rubiera M, Boned S, Olive-Gadea M, Requena M . Ischemic Core Overestimation on Computed Tomography Perfusion. Stroke. 2021; 52(5):1751-1760. DOI: 10.1161/STROKEAHA.120.031800. View

15.

Thomalla G, Cheng B, Ebinger M, Hao Q, Tourdias T, Wu O . DWI-FLAIR mismatch for the identification of patients with acute ischaemic stroke within 4·5 h of symptom onset (PRE-FLAIR): a multicentre observational study. Lancet Neurol. 2011; 10(11):978-86. DOI: 10.1016/S1474-4422(11)70192-2. View

16.

Kiryu S, Akai H, Yasaka K, Tajima T, Kunimatsu A, Yoshioka N . Clinical Impact of Deep Learning Reconstruction in MRI. Radiographics. 2023; 43(6):e220133. DOI: 10.1148/rg.220133. View

17.

Bash S, Wang L, Airriess C, Zaharchuk G, Gong E, Shankaranarayanan A . Deep Learning Enables 60% Accelerated Volumetric Brain MRI While Preserving Quantitative Performance: A Prospective, Multicenter, Multireader Trial. AJNR Am J Neuroradiol. 2021; 42(12):2130-2137. PMC: 8805755. DOI: 10.3174/ajnr.A7358. View

18.

Virtanen P, Gommers R, Oliphant T, Haberland M, Reddy T, Cournapeau D . SciPy 1.0: fundamental algorithms for scientific computing in Python. Nat Methods. 2020; 17(3):261-272. PMC: 7056644. DOI: 10.1038/s41592-019-0686-2. View

19.

Ding J, Duan Y, Zhuo Z, Yuan Y, Zhang G, Song Q . Acceleration of Brain TOF-MRA with Compressed Sensitivity Encoding: A Multicenter Clinical Study. AJNR Am J Neuroradiol. 2021; 42(7):1208-1215. PMC: 8324268. DOI: 10.3174/ajnr.A7091. View

20.

Toledano-Massiah S, Sayadi A, de Boer R, Gelderblom J, Mahdjoub R, Gerber S . Accuracy of the Compressed Sensing Accelerated 3D-FLAIR Sequence for the Detection of MS Plaques at 3T. AJNR Am J Neuroradiol. 2018; 39(3):454-458. PMC: 7655323. DOI: 10.3174/ajnr.A5517. View