대한영상의학회지 (Journal of the Korean Society of Radiology)

  • 제83권6호
  • /
  • Pages.1229-1239
  • /
  • 2022
  • /
  • 1738-2637(pISSN)
  • /
  • 2288-2928(eISSN)
대한영상의학회 (The Korean Society of Radiology)
권호 표지
DOI QR코드

DOI QR Code

MRI 신호획득과 영상재구성에서의 인공지능 적용

Applications of Artificial Intelligence in MR Image Acquisition and Reconstruction

  • 강정화 (한국외국어대학교 바이오메디컬공학부) ;
  • 남윤호 (한국외국어대학교 바이오메디컬공학부)
  • Junghwa Kang (Division of Biomedical Engineering, Hankuk University of Foreign Studies) ;
  • Yoonho Nam (Division of Biomedical Engineering, Hankuk University of Foreign Studies)
  • 투고 : 2022.11.14
  • 심사 : 2022.11.23
  • 발행 : 2022.11.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

최근 인공지능기술은 자기공명영상(이하 MRI)의 폭넓은 분야에서 임상적 활용가치를 보여주고 있다. 특히, MRI에서 영상획득과정의 효율성 및 복원된 영상의 품질을 향상시키기 위한 목적으로 인공지능모델의 개발이 활발하다. 임상에서 활용되는 다양한 MRI 프로토콜에서 인공지능은 병렬영상기법과 같은 기존 가속화 방법 대비 추가적인 영상획득시간을 가능하게 해줄 수 것으로 기대된다. 또한, 펄스시퀀스 디자인, 영상의 인공물 감소, 자동화된 품질평가와 같은 영역에서도 인공지능모델은 도움을 줄 수 있는 연구 결과들이 소개되고 있다. 또한, 영상분석 과정에서 중요한 장비 및 프로토콜의 영향을 줄여줄 수 있는 방법으로도 인공지능 기반의 접근이 이루어지고 있다. 본 종설에서는 MRI 영상의 획득 과정에서 최근 인공지능기술들이 적용되고 있는 분야 및 해당 분야에서의 인공지능기술의 개발 및 적용과 관련된 현안들을 소개하고자 한다.

Recently, artificial intelligence (AI) technology has shown potential clinical utility in a wide range of MRI fields. In particular, AI models for improving the efficiency of the image acquisition process and the quality of reconstructed images are being actively developed by the MR research community. AI is expected to further reduce acquisition times in various MRI protocols used in clinical practice when compared to current parallel imaging techniques. Additionally, AI can help with tasks such as planning, parameter optimization, artifact reduction, and quality assessment. Furthermore, AI is being actively applied to automate MR image analysis such as image registration, segmentation, and object detection. For this reason, it is important to consider the effects of protocols or devices in MR image analysis. In this review article, we briefly introduced issues related to AI application of MR image acquisition and reconstruction.

키워드

과제정보

Thanks to Dr. Woojin Jung and Gawon Lee for providing images related to acceleration and harmonization, respectively.

참고문헌

  1. Bloch F. Nuclear induction. Phys Rev 1946;70:460-474 
  2. Purcell EM, Torrey HC, Pound RV. Resonance absorption by nuclear magnetic moments in a solid. Phys Rev 1946;69:37-38 
  3. Lauterbur PC. Image formation by induced local interactions. Examples employing nuclear magnetic resonance. Nature 1973;242:190-191 
  4. Mansfield P, Maudsley AA. Medical imaging by NMR. Br J Radiol 1977;50:188-194 
  5. Bernstein MA, King KF, Zhou XJ. Handbook of MRI pulse sequences. Burlington, MA: Elsevier 2004 
  6. Liang ZP, Lauterbur PC. Principles of magnetic resonance imaging. Bellingham: SPIE Optical Engineering Press Bellingham 2000 
  7. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015;521:436-444 
  8. Lin DJ, Johnson PM, Knoll F, Lui YW. Artificial intelligence for MR image reconstruction: an overview for clinicians. J Magn Reson Imaging 2021;53:1015-1028 
  9. Wang T, Lei Y, Fu Y, Wynne JF, Curran WJ, Liu T, et al. A review on medical imaging synthesis using deep learning and its clinical applications. J Appl Clin Med Phys 2021;22:11-36 
  10. Choi KS, Sunwoo L. Artificial intelligence in neuroimaging: clinical applications. Investig Magn Reson Imaging 2022;26:1-9 
  11. Lundervold AS, Lundervold A. An overview of deep learning in medical imaging focusing on MRI. Z Med Phys 2019;29:102-127 
  12. Wang G, Ye JC, De Man B. Deep learning for tomographic image reconstruction. Nat Mach Intell 2020;2:737-748 
  13. Brown RW, Cheng YCN, Haacke EM, Thompson MR, Venkatesan R. Magnetic resonance imaging: physical principles and sequence design. 2nd ed. Hoboken, NJ: John Wiley & Sons 2014 
  14. Griswold MA, Jakob PM, Heidemann RM, Nittka M, Jellus V, Wang J, et al. Generalized autocalibrating partially parallel acquisitions (GRAPPA). Magn Reson Med 2002;47:1202-1210 
  15. Pruessmann KP, Weiger M, Scheidegger MB, Boesiger P. SENSE: sensitivity encoding for fast MRI. Magn Reson Med 1999;42:952-962 
  16. Deshmane A, Gulani V, Griswold MA, Seiberlich N. Parallel MR imaging. J Magn Reson Imaging 2012;36:55-72 
  17. Blaimer M, Breuer F, Mueller M, Heidemann RM, Griswold MA, Jakob PM. SMASH, SENSE, PILS, GRAPPA: how to choose the optimal method. Top Magn Reson Imaging 2004;15:223-236 
  18. Sodickson DK, Manning WJ. Simultaneous acquisition of spatial harmonics (SMASH): fast imaging with radiofrequency coil arrays. Magn Reson Med 1997;38:591-603 
  19. Wang G, Ye JC, Mueller K, Fessler JA. Image reconstruction is a new frontier of machine learning. IEEE Trans Med Imaging 2018;37:1289-1296 
  20. Razzak MI, Naz S, Zaib A. Deep learning for medical image processing: overview, challenges and the future. In Dey N, Ashour A, Borra S, eds. Classification in BioApps. Cham: Springer 2018:323-350 
  21. Jin KH, McCann MT, Froustey E, Unser M. Deep convolutional neural network for inverse problems in imaging. IEEE Trans Image Process 2017;26:4509-4522 
  22. Zhu B, Liu JZ, Cauley SF, Rosen BR, Rosen MS. Image reconstruction by domain-transform manifold learning. Nature 2018;555:487-492 
  23. 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 
  24. Wang S, Su Z, Ying L, Peng X, Zhu S, Liang F, et al. Accelerating magnetic resonance imaging via deep learning. Proceedings of the 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI 2016); 2016 Apr 13-16; Prague, Czech Republic: IEEE; 2016:514-517 
  25. 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 
  26. Knoll F, Hammernik K, Zhang C, Moeller S, Pock T, Sodickson DK, et al. Deep-learning methods for parallel magnetic resonance imaging reconstruction: a survey of the current approaches, trends, and issues. IEEE Signal Process Mag 2020;37:128-140 
  27. Jung W, Kim J, Ko J, Jeong G, Kim HG. Highly accelerated 3D MPRAGE using deep neural network-based reconstruction for brain imaging in children and young adults. Eur Radiol 2022;32:5468-5479 
  28. Eo T, Jun Y, Kim T, Jang J, Lee HJ, Hwang D. KIKI-net: cross-domain convolutional neural networks for reconstructing undersampled magnetic resonance images. Magn Reson Med 2018;80:2188-2201 
  29. Hammernik K, Klatzer T, Kobler E, Recht MP, Sodickson DK, Pock T, et al. Learning a variational network for reconstruction of accelerated MRI data. Magn Reson Med 2018;79:3055-3071 
  30. Han Y, Sunwoo L, Ye JC. k-space deep learning for accelerated MRI. IEEE Trans Med Imaging 2020;39:377-386 
  31. Knoll F, Murrell T, Sriram A, Yakubova N, Zbontar J, Rabbat M, et al. Advancing machine learning for MR image reconstruction with an open competition: overview of the 2019 fastMRI challenge. Magn Reson Med 2020;84:3054-3070 
  32. Muckley MJ, Riemenschneider B, Radmanesh A, Kim S, Jeong G, Ko J, et al. Results of the 2020 fastMRI challenge for machine learning MR image reconstruction. IEEE Trans Med Imaging 2021;40:2306-2317 
  33. Park J, Jung W, Choi EJ, Oh SH, Jang J, Shin D, et al. DIFFnet: diffusion parameter mapping network generalized for input diffusion gradient schemes and b-value. IEEE Trans Med Imaging 2022;41:491-499 
  34. Haskell MW, Cauley SF, Bilgic B, Hossbach J, Splitthoff DN, Pfeuffer J, et al. Network accelerated motion estimation and reduction (NAMER): convolutional neural network guided retrospective motion correction using a separable motion model. Magn Reson Med 2019;82:1452-1461 
  35. Feng L, Ma D, Liu F. Rapid MR relaxometry using deep learning: an overview of current techniques and emerging trends. NMR Biomed 2022;35:e4416 
  36. Lee D, Moon WJ, Ye JC. Assessing the importance of magnetic resonance contrasts using collaborative generative adversarial networks. Nat Mach Intell 2020;2:34-42 
  37. Ryu K, Nam Y, Gho SM, Jang J, Lee HJ, Cha J, et al. Data-driven synthetic MRI FLAIR artifact correction via deep neural network. J Magn Reson Imaging 2019;50:1413-1423 
  38. Ryu KH, Baek HJ, Gho SM, Ryu K, Kim DH, Park SE, et al. Validation of deep learning-based artifact correction on synthetic FLAIR images in a different scanning environment. J Clin Med 2020;9:364 
  39. Gong E, Pauly JM, Wintermark M, Zaharchuk G. Deep learning enables reduced gadolinium dose for contrast-enhanced brain MRI. J Magn Reson Imaging 2018;48:330-340 
  40. Pasumarthi S, Tamir JI, Christensen S, Zaharchuk G, Zhang T, Gong E. A generic deep learning model for reduced gadolinium dose in contrast-enhanced brain MRI. Magn Reson Med 2021;86:1687-1700 
  41. Liu F, Jang H, Kijowski R, Bradshaw T, McMillan AB. Deep learning MR imaging-based attenuation correction for PET/MR imaging. Radiology 2018;286:676-684 
  42. Leynes AP, Yang J, Wiesinger F, Kaushik SS, Shanbhag DD, Seo Y, et al. Zero-echo-time and Dixon deep pseudo-CT (ZeDD CT): direct generation of pseudo-CT images for pelvic PET/MRI attenuation correction using deep convolutional neural networks with multiparametric MRI. J Nucl Med 2018;59:852-858 
  43. Shin D, Kim Y, Oh C, An H, Park J, Kim J, et al. Deep reinforcement learning-designed radiofrequency waveform in MRI. Nat Mach Intell 2021;3:985-994 
  44. Gezelter JD, Freeman R. Use of neural networks to design shaped radiofrequency pulses. J Magn Reson (1969) 1990;90:397-404 
  45. Vinding MS, Skyum B, Sangill R, Lund TE. Ultrafast (milliseconds), multidimensional RF pulse design with deep learning. Magn Reson Med 2019;82:586-599 
  46. Ma D, Gulani V, Seiberlich N, Liu K, Sunshine JL, Duerk JL, et al. Magnetic resonance fingerprinting. Nature 2013;495:187-192 
  47. Bipin Mehta B, Coppo S, Frances McGivney D, Ian Hamilton J, Chen Y, Jiang Y, et al. Magnetic resonance fingerprinting: a technical review. Magn Reson Med 2019;81:25-46 
  48. Hoppe E, Korzdorfer G, Wurfl T, Wetzl J, Lugauer F, Pfeuffer J, et al. Deep learning for magnetic resonance fingerprinting: a new approach for predicting quantitative parameter values from time series. Stud Health Technol Inform 2017;243:202-206 
  49. Fang Z, Chen Y, Liu M, Xiang L, Zhang Q, Wang Q, et al. Deep learning for fast and spatially constrained tissue quantification from highly accelerated data in magnetic resonance fingerprinting. IEEE Trans Med Imaging 2019;38:2364-2374 
  50. Moyer D, Ver Steeg G, Tax CMW, Thompson PM. Scanner invariant representations for diffusion MRI harmonization. Magn Reson Med 2020;84:2174-2189 
  51. Guan H, Liu Y, Yang E, Yap PT, Shen D, Liu M. Multi-site MRI harmonization via attention-guided deep domain adaptation for brain disorder identification. Med Image Anal 2021;71:102076 
  52. Dewey BE, Zhao C, Reinhold JC, Carass A, Fitzgerald KC, Sotirchos ES, et al. DeepHarmony: a deep learning approach to contrast harmonization across scanner changes. Magn Reson Imaging 2019;64:160-170 
  53. Kustner T, Gatidis S, Liebgott A, Schwartz M, Mauch L, Martirosian P, et al. A machine-learning framework for automatic reference-free quality assessment in MRI. Magn Reson Imaging 2018;53:134-147 
  54. Largent A, Kapse K, Barnett SD, De Asis-Cruz J, Whitehead M, Murnick J, et al. Image quality assessment of fetal brain MRI using multi-instance deep learning methods. J Magn Reson Imaging 2021;54:818-829 
  55. Piccini D, Demesmaeker R, Heerfordt J, Yerly J, Di Sopra L, Masci PG, et al. Deep learning to automate reference-free image quality assessment of whole-heart MR images. Radiol Artif Intell 2020;2:e190123 
  56. Ma X, Niu Y, Gu L, Wang Y, Zhao Y, Bailey J, et al. Understanding adversarial attacks on deep learning based medical image analysis systems. Pattern Recognit 2021;110:107332 
  57. Madry A, Makelov A, Schmidt L, Tsipras D, Vladu A. Towards deep learning models resistant to adversarial attacks. arXiv [Preprint]. 2017 [cited October 30, 2022]. Available at: https://doi.org/10.48550/arXiv.1706.06083 
  58. Antun V, Renna F, Poon C, Adcock B, Hansen AC. On instabilities of deep learning in image reconstruction and the potential costs of AI. Proc Natl Acad Sci U S A 2020;117:30088-30095 
  59. Edupuganti V, Mardani M, Vasanawala S, Pauly J. Uncertainty quantification in deep MRI reconstruction. IEEE Trans Med Imaging 2021;40:239-250 
  60. Knoll F, Zbontar J, Sriram A, Muckley MJ, Bruno M, Defazio A, et al. fastMRI: a publicly available raw k-space and DICOM dataset of knee images for accelerated MR image reconstruction using machine learning. Radiol Artif Intell 2020;2:e190007 
  61. Akcakaya M, Moeller S, Weingartner S, Ug˘urbil K. Scan-specific robust artificial-neural-networks for k-space interpolation (RAKI) reconstruction: database-free deep learning for fast imaging. Magn Reson Med 2019;81:439-453 
  62. Ulyanov D, Vedaldi A, Lempitsky V. Deep image prior. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2018 Jun 18-23; Salt Lake City, UT, USA: IEEE; 2018:9446- 9454 
  63. Yaman B, Hosseini SAH, Moeller S, Ellermann J, Ug˘urbil K, Akcakaya M. Self-supervised learning of physicsguided reconstruction neural networks without fully sampled reference data. Magn Reson Med 2020;84:3172-3191 
  64. Kim TH, Garg P, Haldar JP. LORAKI: autocalibrated recurrent neural networks for autoregressive MRI reconstruction in k-space. arXiv [Preprint]. 2019 [cited October 30, 2022]. Available at: https://doi.org/10.48550/arXiv.1904.09390