Literature DB >> 29582464

Super-resolution musculoskeletal MRI using deep learning.

Akshay S Chaudhari1,2, Zhongnan Fang3, Feliks Kogan1, Jeff Wood1, Kathryn J Stevens1,4, Eric K Gibbons5, Jin Hyung Lee2,3,6,7, Garry E Gold1,2,4, Brian A Hargreaves1,2,7.   

Abstract

PURPOSE: To develop a super-resolution technique using convolutional neural networks for generating thin-slice knee MR images from thicker input slices, and compare this method with alternative through-plane interpolation methods.
METHODS: We implemented a 3D convolutional neural network entitled DeepResolve to learn residual-based transformations between high-resolution thin-slice images and lower-resolution thick-slice images at the same center locations. DeepResolve was trained using 124 double echo in steady-state (DESS) data sets with 0.7-mm slice thickness and tested on 17 patients. Ground-truth images were compared with DeepResolve, clinically used tricubic interpolation, and Fourier interpolation methods, along with state-of-the-art single-image sparse-coding super-resolution. Comparisons were performed using structural similarity, peak SNR, and RMS error image quality metrics for a multitude of thin-slice downsampling factors. Two musculoskeletal radiologists ranked the 3 data sets and reviewed the diagnostic quality of the DeepResolve, tricubic interpolation, and ground-truth images for sharpness, contrast, artifacts, SNR, and overall diagnostic quality. Mann-Whitney U tests evaluated differences among the quantitative image metrics, reader scores, and rankings. Cohen's Kappa (κ) evaluated interreader reliability.
RESULTS: DeepResolve had significantly better structural similarity, peak SNR, and RMS error than tricubic interpolation, Fourier interpolation, and sparse-coding super-resolution for all downsampling factors (p < .05, except 4 × and 8 × sparse-coding super-resolution downsampling factors). In the reader study, DeepResolve significantly outperformed (p < .01) tricubic interpolation in all image quality categories and overall image ranking. Both readers had substantial scoring agreement (κ = 0.73).
CONCLUSION: DeepResolve was capable of resolving high-resolution thin-slice knee MRI from lower-resolution thicker slices, achieving superior quantitative and qualitative diagnostic performance to both conventionally used and state-of-the-art methods.
© 2018 International Society for Magnetic Resonance in Medicine.

Entities:  

Keywords:  deep learning; interpolation; isotropic MRI; musculoskeletal MRI; super-resolution; unsupervised sparsity learning

Mesh:

Year:  2018        PMID: 29582464      PMCID: PMC6107420          DOI: 10.1002/mrm.27178

Source DB:  PubMed          Journal:  Magn Reson Med        ISSN: 0740-3194            Impact factor:   4.668


  31 in total

1.  Effect of windowing and zero-filled reconstruction of MRI data on spatial resolution and acquisition strategy.

Authors:  M A Bernstein; S B Fain; S J Riederer
Journal:  J Magn Reson Imaging       Date:  2001-09       Impact factor: 4.813

2.  Image quality assessment: from error visibility to structural similarity.

Authors:  Zhou Wang; Alan Conrad Bovik; Hamid Rahim Sheikh; Eero P Simoncelli
Journal:  IEEE Trans Image Process       Date:  2004-04       Impact factor: 10.856

3.  Fast spin echo sequences with very long echo trains: design of variable refocusing flip angle schedules and generation of clinical T2 contrast.

Authors:  Reed F Busse; Hari Hariharan; Anthony Vu; Jean H Brittain
Journal:  Magn Reson Med       Date:  2006-05       Impact factor: 4.668

4.  Imaging and T2 relaxometry of short-T2 connective tissues in the knee using ultrashort echo-time double-echo steady-state (UTEDESS).

Authors:  Akshay S Chaudhari; Bragi Sveinsson; Catherine J Moran; Emily J McWalter; Ethan M Johnson; Tao Zhang; Garry E Gold; Brian A Hargreaves
Journal:  Magn Reson Med       Date:  2017-01-11       Impact factor: 4.668

5.  Reduction of partial-volume artifacts with zero-filled interpolation in three-dimensional MR angiography.

Authors:  Y P Du; D L Parker; W L Davis; G Cao
Journal:  J Magn Reson Imaging       Date:  1994 Sep-Oct       Impact factor: 4.813

Review 6.  A system for grading articular cartilage lesions at arthroscopy.

Authors:  F R Noyes; C L Stabler
Journal:  Am J Sports Med       Date:  1989 Jul-Aug       Impact factor: 6.202

7.  A simple analytic method for estimating T2 in the knee from DESS.

Authors:  B Sveinsson; A S Chaudhari; G E Gold; B A Hargreaves
Journal:  Magn Reson Imaging       Date:  2016-12-23       Impact factor: 2.546

8.  Fast comprehensive single-sequence four-dimensional pediatric knee MRI with T2 shuffling.

Authors:  Shanshan Bao; Jonathan I Tamir; Jeffrey L Young; Umar Tariq; Martin Uecker; Peng Lai; Weitian Chen; Michael Lustig; Shreyas S Vasanawala
Journal:  J Magn Reson Imaging       Date:  2016-10-11       Impact factor: 4.813

9.  Learning a variational network for reconstruction of accelerated MRI data.

Authors:  Kerstin Hammernik; Teresa Klatzer; Erich Kobler; Michael P Recht; Daniel K Sodickson; Thomas Pock; Florian Knoll
Journal:  Magn Reson Med       Date:  2017-11-08       Impact factor: 4.668

10.  Vastly undersampled isotropic projection steady-state free precession imaging of the knee: diagnostic performance compared with conventional MR.

Authors:  Richard Kijowski; Donna G Blankenbaker; Jessica L Klaers; Kazuhiko Shinki; Arthur A De Smet; Walter F Block
Journal:  Radiology       Date:  2009-02-12       Impact factor: 11.105

View more
  60 in total

Review 1.  Current applications and future directions of deep learning in musculoskeletal radiology.

Authors:  Pauley Chea; Jacob C Mandell
Journal:  Skeletal Radiol       Date:  2019-08-04       Impact factor: 2.199

2.  Training a neural network for Gibbs and noise removal in diffusion MRI.

Authors:  Matthew J Muckley; Benjamin Ades-Aron; Antonios Papaioannou; Gregory Lemberskiy; Eddy Solomon; Yvonne W Lui; Daniel K Sodickson; Els Fieremans; Dmitry S Novikov; Florian Knoll
Journal:  Magn Reson Med       Date:  2020-07-14       Impact factor: 4.668

3.  Combined 5-minute double-echo in steady-state with separated echoes and 2-minute proton-density-weighted 2D FSE sequence for comprehensive whole-joint knee MRI assessment.

Authors:  Akshay S Chaudhari; Kathryn J Stevens; Bragi Sveinsson; Jeff P Wood; Christopher F Beaulieu; Edwin H G Oei; Jarrett K Rosenberg; Feliks Kogan; Marcus T Alley; Garry E Gold; Brian A Hargreaves
Journal:  J Magn Reson Imaging       Date:  2018-12-23       Impact factor: 4.813

Review 4.  Artificial Intelligence: reshaping the practice of radiological sciences in the 21st century.

Authors:  Issam El Naqa; Masoom A Haider; Maryellen L Giger; Randall K Ten Haken
Journal:  Br J Radiol       Date:  2020-02-01       Impact factor: 3.039

Review 5.  Improving the Speed of MRI with Artificial Intelligence.

Authors:  Patricia M Johnson; Michael P Recht; Florian Knoll
Journal:  Semin Musculoskelet Radiol       Date:  2020-01-28       Impact factor: 1.777

6.  Utility of deep learning super-resolution in the context of osteoarthritis MRI biomarkers.

Authors:  Akshay S Chaudhari; Kathryn J Stevens; Jeff P Wood; Amit K Chakraborty; Eric K Gibbons; Zhongnan Fang; Arjun D Desai; Jin Hyung Lee; Garry E Gold; Brian A Hargreaves
Journal:  J Magn Reson Imaging       Date:  2019-07-16       Impact factor: 4.813

7.  Learning osteoarthritis imaging biomarkers from bone surface spherical encoding.

Authors:  Alejandro Morales Martinez; Francesco Caliva; Io Flament; Felix Liu; Jinhee Lee; Peng Cao; Rutwik Shah; Sharmila Majumdar; Valentina Pedoia
Journal:  Magn Reson Med       Date:  2020-04-03       Impact factor: 4.668

8.  Artificial Intelligence in Imaging: The Radiologist's Role.

Authors:  Daniel L Rubin
Journal:  J Am Coll Radiol       Date:  2019-09       Impact factor: 5.532

9.  Deep Learning Based High-Resolution Reconstruction of Trabecular Bone Microstructures from Low-Resolution CT Scans using GAN-CIRCLE.

Authors:  Indranil Guha; Syed Ahmed Nadeem; Chenyu You; Xiaoliu Zhang; Steven M Levy; Ge Wang; James C Torner; Punam K Saha
Journal:  Proc SPIE Int Soc Opt Eng       Date:  2020-02-28

10.  Multi-Contrast Super-Resolution MRI Through a Progressive Network.

Authors:  Qing Lyu; Hongming Shan; Cole Steber; Corbin Helis; Chris Whitlow; Michael Chan; Ge Wang
Journal:  IEEE Trans Med Imaging       Date:  2020-02-18       Impact factor: 10.048

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.