Investigative Magnetic Resonance Imaging

  • 제25권1호
  • /
  • Pages.10-22
  • /
  • 2021
  • /
  • 2384-1095(pISSN)
  • /
  • 2384-1109(eISSN)
대한자기공명의과학회 (Korean Society of Magnetic Resonance in Medicine)
권호 표지
DOI QR코드

DOI QR Code

Blended-Transfer Learning for Compressed-Sensing Cardiac CINE MRI

  • Park, Seong Jae (Department of Electrical Engineering, Kwangwoon University) ;
  • Ahn, Chang-Beom (Department of Electrical Engineering, Kwangwoon University)
  • 투고 : 2020.07.17
  • 심사 : 2020.11.02
  • 발행 : 2021.03.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Purpose: To overcome the difficulty in building a large data set with a high-quality in medical imaging, a concept of 'blended-transfer learning' (BTL) using a combination of both source data and target data is proposed for the target task. Materials and Methods: Source and target tasks were defined as training of the source and target networks to reconstruct cardiac CINE images from undersampled data, respectively. In transfer learning (TL), the entire neural network (NN) or some parts of the NN after conducting a source task using an open data set was adopted in the target network as the initial network to improve the learning speed and the performance of the target task. Using BTL, an NN effectively learned the target data while preserving knowledge from the source data to the maximum extent possible. The ratio of the source data to the target data was reduced stepwise from 1 in the initial stage to 0 in the final stage. Results: NN that performed BTL showed an improved performance compared to those that performed TL or standalone learning (SL). Generalization of NN was also better achieved. The learning curve was evaluated using normalized mean square error (NMSE) of reconstructed images for both target data and source data. BTL reduced the learning time by 1.25 to 100 times and provided better image quality. Its NMSE was 3% to 8% lower than with SL. Conclusion: The NN that performed the proposed BTL showed the best performance in terms of learning speed and learning curve. It also showed the highest reconstructed-image quality with the lowest NMSE for the test data set. Thus, BTL is an effective way of learning for NNs in the medical-imaging domain where both quality and quantity of data are always limited.

키워드

참고문헌

  1. Lee VS. Cardiovascular MRI: physical principles to practical protocols. Philadelphia: Lippincott Williams & Wilkins, 2006
  2. Manning WJ, Pennell DJ. Cardiovascular magnetic resonance. 2nd ed. Philadelphia: Saunders, 2010
  3. Park J, Hong HJ, Yang YJ, Ahn CB. Fast cardiac CINE MRI by iterative truncation of small transformed coefficients. Investig Magn Reson Imaging 2015;19:19-30 https://doi.org/10.13104/imri.2015.19.1.19
  4. Yoon JH, Kim PK, Yang YJ, Park J, Choi BW, Ahn CB. Biases in the assessment of left bentricular dunction by compressed sensing cardiovascular CINE MRI. Investig Magn Reson Imaging 2019;23:114-124 https://doi.org/10.13104/imri.2019.23.2.114
  5. Lustig M, Donoho D, Pauly JM. Sparse MRI: the application of compressed sensing for rapid MR imaging. Magn Reson Med 2007;58:1182-1195 https://doi.org/10.1002/mrm.21391
  6. Lee D, Lee J, Ko J, Yoon J, Ryu K, Nam Y. Deep learning in MR image processing. Investig Magn Reson Imaging 2019;23:81-99 https://doi.org/10.13104/imri.2019.23.2.81
  7. Wang S, Su Z, Ying L, et al. Accelerating magnetic resonance imaging via deep learning. Proc IEEE Int Symp Biomed Imaging 2016;2016:514-517
  8. Yang Y, Sun J, Li H, Xu Z. Deep ADMM-Net for compressive sensing MRI. Adv Neural Inf Process Syst (NIPS), 2016:10-18
  9. Yang G, Yu S, Dong H, et al. DAGAN: deep de-aliasing generative adversarial networks for fast compressed sensing MRI reconstruction. IEEE Trans Med Imaging 2018;37:1310-1321 https://doi.org/10.1109/tmi.2017.2785879
  10. Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial networks. Adv Neural Inf Process Syst (NIPS), 2014;2672-2680
  11. Radford A, Metz L, Chintala S. Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434, 2015
  12. Yu S, Dong H, Yang G, et al. Deep de-aliasing for fast compressive sensing MRI. arXiv preprint arXiv:1705.07137, 2017
  13. Zhu J, Yang G, Lio P. How can we make GAN performs better in single medical image super-resolution? A lesion focused multi-scale approach. Proc IEEE Int Symp Biomed Imaging (ISBI) 2019;1669-1673
  14. Wang C, Papanastasiou G, Tsaftaris S, et al. TPSDicyc: improved deformation invariant cross-domain medical image synthesis. Int Workshop on Mach Learn Med Image Reconstr (MLMIR) 2019;245-254
  15. Schlemper J, Yang G, Ferreira P, et al. Stochastic deep compressive sensing for the reconstruction of diffusion tensor cardiac MRI. Int Conf Med Image Comput Comput Assist Interv (MICCAI) 2018;295-303
  16. Zhu J, Yang G, Ferreira P, et al. A ROI focused multi-scale super-resolution method for the diffusion tensor cardiac magnetic resonance. Proc Int Soc Magn Reson Med (ISMRM) 2019;1
  17. Hyun CM, Kim HP, Lee SM, Lee S, Seo JK. Deep learning for undersampled MRI reconstruction. Phys Med Biol 2018;63:135007 https://doi.org/10.1088/0031-9155/63/13/135007
  18. Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation. Int Conf Med Image Comput Comput Assist Interv (MICCAI) 2015;234-241
  19. Kofler A, Dewey M, Schaeffter T, Wald C, Kolbitsch C. Spatio-temporal deep learning-based undersampling artefact reduction for 2D radial cine MRI with limited training data. IEEE Trans Med Imaging 2020;39:703-717 https://doi.org/10.1109/tmi.2019.2930318
  20. Pan SJ, Yang Q. A survey on transfer learning. IEEE Trans Knowl Data Eng 2010;22:1345-1359 https://doi.org/10.1109/TKDE.2009.191
  21. Park SJ, Yoon JH, Ahn CB, Transfer learning for compressedsensing cardiac CINE MRI. Proc Int Soc Magn Reason Med (ISMRM) 2020;2223
  22. Oquab M, Bottou L, Laptev I, Sivic J. Learning and transferring mid-level image representations using convolutional neural networks. Proc IEEE Comput Vis Pattern Revognit (CVPR), 2014:1717-1724
  23. Ciresan D C, Meier U, Schmidhuber J. Transfer learning for Latin and Chinese characters with deep neural networks. Proc Int Jt Conf Neural Netw (IJCNN) 2012;1-6
  24. Meng D, Zhang L, Cao G, Cao W, Zhang G, Hu B. Liver fibrosis classification based on transfer learning and FCNet for ultrasound images. IEEE Access 2017;5:5804-5810 https://doi.org/10.1109/ACCESS.2017.2689058
  25. Chen A, Zhou T, Icke I, et al. Transfer learning for the fully automatic segmentation of left ventricle myocardium in porcine cardiac cine MR images. Int Workshop on Stat Atlases Comput Models Heart (STACOM) 2017;21-31
  26. Dar SUH, Ozbey M, Catli AB, Cukur T. A transfer-learning approach for accelerated MRI using deep neural networks. Magn Reson Med 2020;84:663-685 https://doi.org/10.1002/mrm.28148
  27. Andreopoulos A, Tsotsos JK. Efficient and generalizable statistical models of shape and appearance for analysis of cardiac MRI. Med Image Anal 2008;12:335-357 https://doi.org/10.1016/j.media.2007.12.003
  28. Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks. Proc Int Conf Artif Intell Stat (AISTATS) 2010;249-256
  29. Seitzer M, Yang G, Schlemper J, et al. Adversarial and perceptual refinement for compressed sensing MRI reconstruction. Int Conf Med Image Comput Comput Assist Interv (MICCAI) 2018;232-240