Literature DB >> 31667138

MR image reconstruction using deep learning: evaluation of network structure and loss functions.

Vahid Ghodrati1,2, Jiaxin Shao1, Mark Bydder1, Ziwu Zhou1,3, Wotao Yin4, Kim-Lien Nguyen5, Yingli Yang2,6, Peng Hu1,2.   

Abstract

BACKGROUND: To review and evaluate approaches to convolutional neural network (CNN) reconstruction for accelerated cardiac MR imaging in the real clinical context.
METHODS: Two CNN architectures, Unet and residual network (Resnet) were evaluated using quantitative and qualitative assessment by radiologist. Four different loss functions were also considered: pixel-wise (L1 and L2), patch-wise structural dissimilarity (Dssim) and feature-wise (perceptual loss). The networks were evaluated using retrospectively and prospectively under-sampled cardiac MR data.
RESULTS: Based on our assessments, we find that Resnet and Unet achieve similar image quality but that former requires only 100,000 parameters compared to 1.3 million parameters for the latter. The perceptual loss function performed significantly better than L1, L2 or Dssim loss functions as determined by the radiologist scores.
CONCLUSIONS: CNN image reconstruction using Resnet yields comparable image quality to Unet with 10X the number of parameters. This has implications for training with significantly lower data requirements. Network training using the perceptual loss function was found to better agree with radiologist scoring compared to L1, L2 or Dssim loss functions. 2019 Quantitative Imaging in Medicine and Surgery. All rights reserved.

Entities:  

Keywords:  Magnetic resonance imaging; cardiac image reconstruction; convolutional Unet; deep learning; perceptual loss function; residual neural network

Year:  2019        PMID: 31667138      PMCID: PMC6785508          DOI: 10.21037/qims.2019.08.10

Source DB:  PubMed          Journal:  Quant Imaging Med Surg        ISSN: 2223-4306


  13 in total

1.  Generalized autocalibrating partially parallel acquisitions (GRAPPA).

Authors:  Mark A Griswold; Peter M Jakob; Robin M Heidemann; Mathias Nittka; Vladimir Jellus; Jianmin Wang; Berthold Kiefer; Axel Haase
Journal:  Magn Reson Med       Date:  2002-06       Impact factor: 4.668

2.  MR image reconstruction from highly undersampled k-space data by dictionary learning.

Authors:  Saiprasad Ravishankar; Yoram Bresler
Journal:  IEEE Trans Med Imaging       Date:  2010-11-01       Impact factor: 10.048

3.  Sparse MRI: The application of compressed sensing for rapid MR imaging.

Authors:  Michael Lustig; David Donoho; John M Pauly
Journal:  Magn Reson Med       Date:  2007-12       Impact factor: 4.668

4.  Deep Convolutional Neural Network for Inverse Problems in Imaging.

Authors:  Michael T McCann; Emmanuel Froustey; Michael Unser
Journal:  IEEE Trans Image Process       Date:  2017-06-15       Impact factor: 10.856

5.  Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration.

Authors:  Yunjin Chen; Thomas Pock
Journal:  IEEE Trans Pattern Anal Mach Intell       Date:  2016-08-01       Impact factor: 6.226

6.  Image Super-Resolution Using Deep Convolutional Networks.

Authors:  Chao Dong; Chen Change Loy; Kaiming He; Xiaoou Tang
Journal:  IEEE Trans Pattern Anal Mach Intell       Date:  2016-02       Impact factor: 6.226

7.  Low-Dose CT With a Residual Encoder-Decoder Convolutional Neural Network.

Authors:  Hu Chen; Yi Zhang; Mannudeep K Kalra; Feng Lin; Yang Chen; Peixi Liao; Jiliu Zhou; Ge Wang
Journal:  IEEE Trans Med Imaging       Date:  2017-06-13       Impact factor: 10.048

8.  A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction.

Authors:  Jo Schlemper; Jose Caballero; Joseph V Hajnal; Anthony N Price; Daniel Rueckert
Journal:  IEEE Trans Med Imaging       Date:  2017-10-13       Impact factor: 10.048

9.  Image reconstruction by domain-transform manifold learning.

Authors:  Bo Zhu; Jeremiah Z Liu; Stephen F Cauley; Bruce R Rosen; Matthew S Rosen
Journal:  Nature       Date:  2018-03-21       Impact factor: 49.962

10.  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

View more
  16 in total

1.  A fully automated left atrium segmentation approach from late gadolinium enhanced magnetic resonance imaging based on a convolutional neural network.

Authors:  Davide Borra; Alice Andalò; Michelangelo Paci; Claudio Fabbri; Cristiana Corsi
Journal:  Quant Imaging Med Surg       Date:  2020-10

2.  The 4D B-spline method of calculating left ventricular functional parameters of cardiac MRI to evaluate myocardial injury of the apical segment in patients with myocarditis: a case-controlled observational study.

Authors:  Xin-Xiang Zhao; Wei-Feng Yuan
Journal:  Quant Imaging Med Surg       Date:  2020-11

3.  Image restoration of motion artifacts in cardiac arteries and vessels based on a generative adversarial network.

Authors:  Fuquan Deng; Qian Wan; Yingting Zeng; Yanbin Shi; Huiying Wu; Yu Wu; Weifeng Xu; Greta S P Mok; Xiaochun Zhang; Zhanli Hu
Journal:  Quant Imaging Med Surg       Date:  2022-05

4.  Accelerating cardiac cine MRI using a deep learning-based ESPIRiT reconstruction.

Authors:  Christopher M Sandino; Peng Lai; Shreyas S Vasanawala; Joseph Y Cheng
Journal:  Magn Reson Med       Date:  2020-07-22       Impact factor: 4.668

5.  Deep learning based fully automatic segmentation of the left ventricular endocardium and epicardium from cardiac cine MRI.

Authors:  Yan Wang; Yue Zhang; Zhaoying Wen; Bing Tian; Evan Kao; Xinke Liu; Wanling Xuan; Karen Ordovas; David Saloner; Jing Liu
Journal:  Quant Imaging Med Surg       Date:  2021-04

6.  Parallel imaging with a combination of sensitivity encoding and generative adversarial networks.

Authors:  Jun Lv; Peng Wang; Xiangrong Tong; Chengyan Wang
Journal:  Quant Imaging Med Surg       Date:  2020-12

7.  Adaptive convolutional neural networks for accelerating magnetic resonance imaging via k-space data interpolation.

Authors:  Tianming Du; Honggang Zhang; Yuemeng Li; Stephen Pickup; Mark Rosen; Rong Zhou; Hee Kwon Song; Yong Fan
Journal:  Med Image Anal       Date:  2021-05-16       Impact factor: 13.828

Review 8.  Prospective Deployment of Deep Learning in MRI: A Framework for Important Considerations, Challenges, and Recommendations for Best Practices.

Authors:  Akshay S Chaudhari; Christopher M Sandino; Elizabeth K Cole; David B Larson; Garry E Gold; Shreyas S Vasanawala; Matthew P Lungren; Brian A Hargreaves; Curtis P Langlotz
Journal:  J Magn Reson Imaging       Date:  2020-08-24       Impact factor: 5.119

9.  Fast and accurate calculation of myocardial T1 and T2 values using deep learning Bloch equation simulations (DeepBLESS).

Authors:  Jiaxin Shao; Vahid Ghodrati; Kim-Lien Nguyen; Peng Hu
Journal:  Magn Reson Med       Date:  2020-05-16       Impact factor: 3.737

10.  A comprehensive review of deep learning-based single image super-resolution.

Authors:  Syed Muhammad Arsalan Bashir; Yi Wang; Mahrukh Khan; Yilong Niu
Journal:  PeerJ Comput Sci       Date:  2021-07-13
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.