Literature DB >> 30860286

Dynamic MRI using model-based deep learning and SToRM priors: MoDL-SToRM.

Sampurna Biswas1, Hemant K Aggarwal1, Mathews Jacob1.   

Abstract

PURPOSE: To introduce a novel framework to combine deep-learned priors along with complementary image regularization penalties to reconstruct free breathing & ungated cardiac MRI data from highly undersampled multi-channel measurements.
METHODS: Image recovery is formulated as an optimization problem, where the cost function is the sum of data consistency term, convolutional neural network (CNN) denoising prior, and SmooThness regularization on manifolds (SToRM) prior that exploits the manifold structure of images in the dataset. An iterative algorithm, which alternates between denoizing of the image data using CNN and SToRM, and conjugate gradients (CG) step that minimizes the data consistency cost is introduced. Unrolling the iterative algorithm yields a deep network, which is trained using exemplar data.
RESULTS: The experimental results demonstrate that the proposed framework can offer fast recovery of free breathing and ungated cardiac MRI data from less than 8.2s of acquisition time per slice. The reconstructions are comparable in image quality to SToRM reconstructions from 42s of acquisition time, offering a fivefold reduction in scan time.
CONCLUSIONS: The results show the benefit in combining deep learned CNN priors with complementary image regularization penalties. Specifically, this work demonstrates the benefit in combining the CNN prior that exploits local and population generalizable redundancies together with SToRM, which capitalizes on patient-specific information including cardiac and respiratory patterns. The synergistic combination is facilitated by the proposed framework.
© 2019 International Society for Magnetic Resonance in Medicine.

Entities:  

Keywords:  alternating minimization; free breathing cardiac MR; learned prior; model-based; non-local prior; subject specific prior

Mesh:

Year:  2019        PMID: 30860286     DOI: 10.1002/mrm.27706

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


  15 in total

1.  Multi-scale Unrolled Deep Learning Framework for Accelerated Magnetic Resonance Imaging.

Authors:  Ukash Nakarmi; Joseph Y Cheng; Edgar P Rios; Morteza Mardani; John M Pauly; Leslie Ying; Shreyas S Vasanawala
Journal:  Proc IEEE Int Symp Biomed Imaging       Date:  2020-05-22

2.  Reconstruction of undersampled 3D non-Cartesian image-based navigators for coronary MRA using an unrolled deep learning model.

Authors:  Mario O Malavé; Corey A Baron; Srivathsan P Koundinyan; Christopher M Sandino; Frank Ong; Joseph Y Cheng; Dwight G Nishimura
Journal:  Magn Reson Med       Date:  2020-02-03       Impact factor: 4.668

3.  MoDL-MUSSELS: Model-Based Deep Learning for Multishot Sensitivity-Encoded Diffusion MRI.

Authors:  Hemant K Aggarwal; Merry P Mani; Mathews Jacob
Journal:  IEEE Trans Med Imaging       Date:  2019-10-09       Impact factor: 10.048

4.  Deep learning within a priori temporal feature spaces for large-scale dynamic MR image reconstruction: Application to 5-D cardiac MR Multitasking.

Authors:  Yuhua Chen; Jaime L Shaw; Yibin Xie; Debiao Li; Anthony G Christodoulou
Journal:  Med Image Comput Comput Assist Interv       Date:  2019-10-10

5.  DYNAMIC MRI USING DEEP MANIFOLD SELF-LEARNING.

Authors:  Abdul Haseeb Ahmed; Hemant Aggarwal; Prashant Nagpal; Mathews Jacob
Journal:  Proc IEEE Int Symp Biomed Imaging       Date:  2020-05-22

Review 6.  Cardiac MR: From Theory to Practice.

Authors:  Tevfik F Ismail; Wendy Strugnell; Chiara Coletti; Maša Božić-Iven; Sebastian Weingärtner; Kerstin Hammernik; Teresa Correia; Thomas Küstner
Journal:  Front Cardiovasc Med       Date:  2022-03-03

7.  MR Denoising Increases Radiomic Biomarker Precision and Reproducibility in Oncologic Imaging.

Authors:  Matías Fernández Patón; Leonor Cerdá Alberich; Cinta Sangüesa Nebot; Blanca Martínez de Las Heras; Diana Veiga Canuto; Adela Cañete Nieto; Luis Martí-Bonmatí
Journal:  J Digit Imaging       Date:  2021-09-10       Impact factor: 4.903

8.  Cine Cardiac MRI Motion Artifact Reduction Using a Recurrent Neural Network.

Authors:  Qing Lyu; Hongming Shan; Yibin Xie; Alan C Kwan; Yuka Otaki; Keiichiro Kuronuma; Debiao Li; Ge Wang
Journal:  IEEE Trans Med Imaging       Date:  2021-07-30       Impact factor: 11.037

9.  Magnetic resonance parameter mapping using model-guided self-supervised deep learning.

Authors:  Fang Liu; Richard Kijowski; Georges El Fakhri; Li Feng
Journal:  Magn Reson Med       Date:  2021-01-19       Impact factor: 3.737

10.  Free-breathing Accelerated Cardiac MRI Using Deep Learning: Validation in Children and Young Adults.

Authors:  Evan J Zucker; Christopher M Sandino; Aya Kino; Peng Lai; Shreyas S Vasanawala
Journal:  Radiology       Date:  2021-06-15       Impact factor: 29.146

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.