DOI QR코드

DOI QR Code

qMTNet+, an Improved qMTNet with Residual Connection for Accelerated Quantitative Magnetization Transfer Imaging

  • Luu, Huan Minh (Department of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology) ;
  • Kim, Dong-Hyun (Department of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology) ;
  • Choi, Seung-Hong (Department of Radiology, Seoul National University College of Medicine) ;
  • Park, Sung-Hong (Department of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology)
  • Received : 2020.11.08
  • Accepted : 2020.11.17
  • Published : 2020.12.31

Abstract

Purpose: To develop qMTNet+, an improved version of a recently proposed neural network called qMTNet, to accelerate quantitative magnetization transfer (qMT) imaging acquisition and processing. Materials and Methods: Conventional and inter-slice qMT data were acquired with two flip angles at six offset frequencies from seven subjects for developing networks and from four young and four older subjects for testing its generalizability. qMTNet+ was designed to incorporate residual and multi-task learning to improve its performance. qMTNet+ is composed of multiple fully-connected layers. It can simultaneously generate missing MT-weighted images and qMT parameters from undersampled MT images. The network was trained and validated with 7-fold cross-validation. Additional testing with unseen data was performed to assess the generalizability of the network. Performance of qMTNet+ was compared with that of qMTNet-1 and qMTNet-acq for fitting and MT images generation, respectively. Results: qMTNet+ achieved quantitative results that were better than qMTNet across all metrics (peak signal-to-noise ratio, structural similarity index, normalized mean squared error) for both conventional and inter-slice MT data. Produced offset images were better quantitatively than those produced by qMTNet-acq. Conclusion: qMTNet+ improves qMTNet, generating qMT parameters from undersampled MT data with higher agreement with ground truth values. Additionally, qMTNet+ can produce both qMT parameters and unsampled MT images with a single network in an end-to-end manner, obviating the need for separate networks required for qMTNet. qMTNet+ has the potential to accelerate qMT imaging for diagnostic and research purposes.

Keywords

References

  1. Henkelman RM, Huang X, Xiang QS, Stanisz GJ, Swanson SD, Bronskill MJ. Quantitative interpretation of magnetization transfer. Magn Reson Med 1993;29:759-766 https://doi.org/10.1002/mrm.1910290607
  2. Schmierer K, Tozer DJ, Scaravilli F, et al. Quantitative magnetization transfer imaging in postmortem multiple sclerosis brain. J Magn Reson Imaging 2007;26:41-51 https://doi.org/10.1002/jmri.20984
  3. Levesque IR, Giacomini PS, Narayanan S, et al. Quantitative magnetization transfer and myelin water imaging of the evolution of acute multiple sclerosis lesions. Magn Reson Med 2010;63:633-640 https://doi.org/10.1002/mrm.22244
  4. Garcia M, Gloor M, Bieri O, et al. Imaging of primary brain tumors and metastases with fast quantitative 3-dimensional magnetization transfer. J Neuroimaging 2015;25:1007-1014 https://doi.org/10.1111/jon.12222
  5. Harrison NA, Cooper E, Dowell NG, et al. Quantitative magnetization transfer imaging as a biomarker for effects of systemic inflammation on the brain. Biol Psychiatry 2015;78:49-57 https://doi.org/10.1016/j.biopsych.2014.09.023
  6. Cabana J-F, Gu Y, Boudreau M, et al. Quantitative magnetization transfer imaging made easy with qMTLab: software for data simulation, analysis, and visualization. Concepts Magn Reson 2015;44A:263-277 https://doi.org/10.1002/cmr.a.21357
  7. McLean MA. Accelerated quantitative magnetization transfer (qMT) imaging (unpublished master's thesis). University of Calgary, Calgary, AB, 2018:94
  8. Gochberg DF, Gore JC. Quantitative imaging of magnetization transfer using an inversion recovery sequence. Magn Reson Med 2003;49:501-505 https://doi.org/10.1002/mrm.10386
  9. Gochberg DF, Gore JC. Quantitative magnetization transfer imaging via selective inversion recovery with short repetition times. Magn Reson Med 2007;57:437-441 https://doi.org/10.1002/mrm.21143
  10. Li K, Zu Z, Xu J, et al. Optimized inversion recovery sequences for quantitative T1 and magnetization transfer imaging. Magn Reson Med 2010;64:491-500 https://doi.org/10.1002/mrm.22440
  11. Dortch RD, Li K, Gochberg DF, et al. Quantitative magnetization transfer imaging in human brain at 3 T via selective inversion recovery. Magn Reson Med 2011;66:1346-1352 https://doi.org/10.1002/mrm.22928
  12. Kim JW, Lee SL, Choi SH, Park SH. Rapid framework for quantitative magnetization transfer imaging with interslice magnetization transfer and dictionary-driven fitting approaches. Magn Reson Med 2019;82:1671-1683 https://doi.org/10.1002/mrm.27850
  13. Barker JW, Han PK, Choi SH, Bae KT, Park SH. Investigation of inter-slice magnetization transfer effects as a new method for MTR imaging of the human brain. PLoS One 2015;10:e0117101 https://doi.org/10.1371/journal.pone.0117101
  14. Han PK, Barker JW, Kim KH, Choi SH, Bae KT, Park SH. Inter-slice blood flow and magnetization transfer effects as a new simultaneous imaging strategy. PLoS One 2015;10:e0140560 https://doi.org/10.1371/journal.pone.0140560
  15. Park SH, Duong TQ. Alternate ascending/descending directional navigation approach for imaging magnetization transfer asymmetry. Magn Reson Med 2011;65:1702-1710 https://doi.org/10.1002/mrm.22568
  16. Park SH, Duong TQ. Brain MR perfusion-weighted imaging with alternate ascending/descending directional navigation. Magn Reson Med 2011;65:1578-1591 https://doi.org/10.1002/mrm.22580
  17. Park H, Lee J, Park SH, Choi SH. Evaluation of tumor blood flow using alternate ascending/descending directional navigation in primary brain tumors: a comparison study with dynamic susceptibility contrast magnetic resonance imaging. Korean J Radiol 2019;20:275-282 https://doi.org/10.3348/kjr.2018.0300
  18. Kim KH, Choi SH, Park SH. Feasibility of quantifying arterial cerebral blood volume using multiphase alternate ascending/descending directional navigation (ALADDIN). PLoS One 2016;11:e0156687 https://doi.org/10.1371/journal.pone.0156687
  19. Park SH, Zhao T, Kim JH, Boada FE, Bae KT. Suppression of effects of gradient imperfections on imaging with alternate ascending/descending directional navigation. Magn Reson Med 2012;68:1600-1606 https://doi.org/10.1002/mrm.24169
  20. Luu HM, Kim DH, Kim JW, Choi SH, Park SH. qMTNet: accelerated quantitative magnetization transfer imaging with artificial neural networks. Magn Reson Med 2020;85:298-308 https://doi.org/10.1002/mrm.28411
  21. Cercignani M, Alexander DC. Optimal acquisition schemes for in vivo quantitative magnetization transfer MRI. Magn Reson Med 2006;56:803-810 https://doi.org/10.1002/mrm.21003
  22. Abadi M, Barham P, Chen J, et al. TensorFlow: a system for large-scale machine learning. Proc the OSDI'16: 12th USENIX Symposium on Operating Systems Design and Implementation; Savannah, GA, USA: USENIX Association; 2016:265-283
  23. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016:770-778
  24. Srivastava N, Hinton GE, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 2014;15:1929-1958
  25. Kingma DP, Ba J. Adam: a method for stochastic optimization. Proc 3rd International Conference on Learning Representations (ICLR), 2015
  26. Wilcoxon F. Individual comparisons by ranking methods. Biometrics 1945;1:80-83 https://doi.org/10.2307/3001968
  27. Caruana R. Multitask learning. Machine Learning 1997;28:41-75 https://doi.org/10.1023/A:1007379606734
  28. Cohen O, Zhu B, Rosen MS. MR fingerprinting deep reconstruction network (DRONE). Magn Reson Med 2018;80:885-894 https://doi.org/10.1002/mrm.27198
  29. Yoon J, Gong E, Chatnuntawech I, et al. Quantitative susceptibility mapping using deep neural network: QSMnet. Neuroimage 2018;179:199-206 https://doi.org/10.1016/j.neuroimage.2018.06.030
  30. Lee J, Lee D, Choi JY, Shin D, Shin HG, Lee J. Artificial neural network for myelin water imaging. Magn Reson Med 2020;83:1875-1883 https://doi.org/10.1002/mrm.28038
  31. Heule R, Bause J, Pusterla O, Scheffler K. Multi-parametric artificial neural network fitting of phase-cycled balanced steady-state free precession data. Magn Reson Med 2020;84:2981-2993 https://doi.org/10.1002/mrm.28325
  32. Karras T, Laine S, Aittala M, et al. Analyzing and improving the image quality of StyleGAN. Proc IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020:8110-8119
  33. Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL. DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell 2018;40:834-848 https://doi.org/10.1109/TPAMI.2017.2699184
  34. Johnson J, Alahi A, Fei-Fei L. Perceptual losses for realtime style transfer and super-resolution. Proc European Conference on Computer Vision, 2016:694-711
  35. Lee D, Yoo J, Ye JC. Deep residual learning for compressed sensing MRI. IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), 2017:15-18
  36. Lee D, Yoo J, Tak S, Ye JC. Deep residual learning for accelerated MRI using magnitude and phase networks. IEEE Trans Biomed Eng 2018;65:1985-1995 https://doi.org/10.1109/TBME.2018.2821699
  37. Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets. Advances in Neural Information Processing Systems, 2014:2672-2680
  38. Jung W, Yoon J, Choi JY, et al. Exploring linearity of deep neural network trained QSM: QSMnet+. arXiv preprint arXiv:1909.07716, 2019