Share：
Share this content in WeChat
X
[Chinese][PDF]10809
• Special Focus •
Research status and development prospect of magnetic resonance imaging artificial intelligence
WANG Meiyun 

Cite this article as: WANG M Y. Research status and development prospect of magnetic resonance imaging artificial intelligence[J]. Chin J Magn Reson Imaging, 2023, 14(3): 1-5. DOI:10.12015/issn.1674-8034.2023.03.001.


[Abstract] The rapid development of MRI technology, the clinical application of more advanced high-performance MRI scanner, and the continuous development of various image post-processing software together improve the imaging performance and image quality of MRI. More importantly, the abnormal tissue structure and organ morphology, function and metabolism, especially some minor pathological changes, can be clearly displayed, which significantly improves the imaging diagnostic level and expands the application field. With the rapid development of artificial intelligence (AI) technology and the deepening of its research in MRI field, applications such as tumor detection, qualitative diagnosis, gene phenotype and prognosis prediction are rapidly transiting from the experimental stage to the clinical trial stage. This paper summarizes the research status of MRI AI at home and abroad in recent years, and looks into the future development direction, aiming to provide a reference for MRI technology research and clinical transformation.
[Keywords] magnetic resonance imaging；artificial intelligence；fast reconstruction；image postprocessing；diagnosis；staging；follow up；prediction

WANG Meiyun*  

Department of Medical Imaging, Henan Provincial People's Hospital, Zhengzhou 450003, China

Corresponding author: Wang MY, E-mail: mywang@zzu.edu.cn

Conflicts of interest   None.

ACKNOWLEDGMENTS Medical Science and Technology Project of Henan Province (No. SBGJ202101002).
Received  2022-12-15
Accepted  2023-03-13
DOI: 10.12015/issn.1674-8034.2023.03.001
Cite this article as: WANG M Y. Research status and development prospect of magnetic resonance imaging artificial intelligence[J]. Chin J Magn Reson Imaging, 2023, 14(3): 1-5. DOI:10.12015/issn.1674-8034.2023.03.001.

[1]
GUIOT J, VAIDYANATHAN A, DEPREZ L, et al. A review in radiomics: making personalized medicine a reality via routine imaging[J]. Med Res Rev, 2022, 42(1): 426-440. DOI: 10.1002/med.21846.
[2]
LAMBIN P, LEIJENAAR R T H, DEIST T M, et al. Radiomics: the bridge between medical imaging and personalized medicine[J]. Nat Rev Clin Oncol, 2017, 14(12): 749-762. DOI: 10.1038/nrclinonc.2017.141.
[3]
BI W L, HOSNY A, SCHABATH M B, et al. Artificial intelligence in cancer imaging: clinical challenges and applications[J]. CA Cancer J Clin, 2019, 69(2): 127-157. DOI: 10.3322/caac.21552.
[4]
KLEPPE A, SKREDE O J, DE RAEDT S, et al. Designing deep learning studies in cancer diagnostics[J]. Nat Rev Cancer, 2021, 21(3): 199-211. DOI: 10.1038/s41568-020-00327-9.
[5]
CHANDRA S S, BRAN LORENZANA M, LIU X W, et al. Deep learning in magnetic resonance image reconstruction[J]. J Med Imaging Radiat Oncol, 2021, 65(5): 564-577. DOI: 10.1111/1754-9485.13276.
[6]
MARDANI M, GONG E H, CHENG J Y, et al. Deep generative adversarial neural networks for compressive sensing MRI[J]. IEEE Trans Med Imaging, 2019, 38(1): 167-179. DOI: 10.1109/TMI.2018.2858752.
[7]
WANG G H, LUO T R, NIELSEN J F, et al. B-spline parameterized joint optimization of reconstruction and K-space trajectories (BJORK) for accelerated 2D MRI[J]. IEEE Trans Med Imaging, 2022, 41(9): 2318-2330. DOI: 10.1109/TMI.2022.3161875.
[8]
XUAN K, XIANG L, HUANG X Q, et al. Multimodal MRI reconstruction assisted with spatial alignment network[J]. IEEE Trans Med Imaging, 2022, 41(9): 2499-2509. DOI: 10.1109/TMI.2022.3164050.
[9]
ZHOU B, SCHLEMPER J, DEY N, et al. Dual-domain self-supervised learning for accelerated non-Cartesian MRI reconstruction[J/OL]. Med Image Anal, 2022, 81: 102538 [2022-12-30]. https://doi.org/10.1016/j.media.2022.102538. DOI: 10.1016/j.media.2022.102538.
[10]
WANG F, DONG Z J, REESE T G, et al. 3D Echo Planar Time-resolved Imaging (3D-EPTI) for ultrafast multi-parametric quantitative MRI[J/OL]. Neuroimage, 2022, 250: 118963 [2022-12-30]. https://www.sciencedirect.com/science/article/pii/S1053811922000921. DOI: 10.1016/j.neuroimage.2022.118963.
[11]
COHEN O, YU V Y, TRINGALE K R, et al. CEST MR fingerprinting (CEST-MRF) for brain tumor quantification using EPI readout and deep learning reconstruction[J]. Magn Reson Med, 2023, 89(1): 233-249. DOI: 10.1002/mrm.29448.
[12]
YAN Y X, DAHMANI L, REN J X, et al. Reconstructing lost BOLD signal in individual participants using deep machine learning[J/OL]. Nat Commun, 2020, 11(1): 5046 [2022-12-30]. https://www.nature.com/articles/s41467-020-18823-9. DOI: 10.1038/s41467-020-18823-9.
[13]
TIAN Q Y, BILGIC B, FAN Q Y, et al. DeepDTI: High-fidelity six-direction diffusion tensor imaging using deep learning[J/OL]. Neuroimage, 2020, 219: 117017 [2022-12-30]. https://www.sciencedirect.com/science/article/pii/S1053811920305036. DOI: 10.1016/j.neuroimage.2020.117017.
[14]
QIN Y, LI Y X, ZHUO Z Z, et al. Multimodal super-resolved q-space deep learning[J/OL]. Med Image Anal, 2021, 71: 102085 [2022-12-30]. https://www.sciencedirect.com/science/article/abs/pii/S1361841521001316. DOI: 10.1016/j.media.2021.102085.
[15]
ALMANSOUR H, HERRMANN J, GASSENMAIER S, et al. Deep learning reconstruction for accelerated spine MRI: prospective analysis of interchangeability[J/OL]. Radiology, 2023, 306(3): e212922 [2022-12-30]. https://pubs.rsna.org/doi/epdf/10.1148/radiol.212922. DOI: 10.1148/radiol.212922.
[16]
XIAO Y, LIU S Y. Collaborations of industry, academia, research and application improve the healthy development of medical imaging artificial intelligence industry in China[J]. Chin Med Sci J, 2019, 34(2): 84-88. DOI: 10.24920/003619.
[17]
ZUCKER E J, SANDINO C M, KINO A, et al. Free-breathing accelerated cardiac MRI using deep learning: validation in children and young adults[J]. Radiology, 2021, 300(3): 539-548. DOI: 10.1148/radiol.2021202624.
[18]
MOHD SAGHEER S V, GEORGE S N. A review on medical image denoising algorithms[J/OL]. Biomed Signal Process Control, 2020, 61: 102036 [2022-12-30]. https://www.sciencedirect.com/science/article/abs/pii/S1746809420301920?via%3Dihub. DOI: 10.1016/j.bspc.2020.102036.
[19]
CHEN C, QIN C, OUYANG C, et al. Enhancing MR image segmentation with realistic adversarial data augmentation[J/OL]. Med Image Anal, 2022, 82: 102597 [2022-12-30]. https://www.sciencedirect.com/science/article/abs/pii/S1746809420301920. DOI: 10.1016/j.media.2022.102597.
[20]
TIAN Q, LI Z, FAN Q, et al. SDnDTI: Self-supervised deep learning-based denoising for diffusion tensor MRI[J/OL]. Neuroimage, 2022, 253: 119033 [2022-12-30]. https://www.sciencedirect.com/science/article/pii/S1053811922001628?via%3Dihub. DOI: 10.1016/j.neuroimage.2022.119033.
[21]
RAJESH C, KUMAR S. An evolutionary block based network for medical image denoising using Differential Evolution[J/OL]. Appl Soft Comput, 2022, 121: 108776 [2022-12-30]. https://www.sciencedirect.com/science/article/abs/pii/S1568494622002022. DOI: 10.1016/j.asoc.2022.108776.
[22]
RAWAT S, RANA K P S, KUMAR V. A novel complex-valued convolutional neural network for medical image denoising[J/OL]. Biomed Signal Process Control, 2021, 69: 102859 [2022-12-30]. https://www.sciencedirect.com/science/article/abs/pii/S1746809421004560. DOI: 10.1016/j.bspc.2021.102859.
[23]
BOVEIRI H R, KHAYAMI R, JAVIDAN R, et al. Medical image registration using deep neural networks: a comprehensive review[J/OL]. Comput Electr Eng, 2020, 87: 106767 [2022-12-30]. https://www.sciencedirect.com/science/article/abs/pii/S0045790620306224?via%3Dihub. DOI: 10.1016/j.compeleceng.2020.106767.
[24]
ZHANG F, WELLS W M, O'DONNELL L J. Deep diffusion MRI registration (DDMReg): a deep learning method for diffusion MRI registration[J]. IEEE Trans Med Imaging, 2022, 41(6): 1454-1467. DOI: 10.1109/TMI.2021.3139507.
[25]
LI B, NIESSEN W J, KLEIN S, et al. Longitudinal diffusion MRI analysis using Segis-Net: a single-step deep-learning framework for simultaneous segmentation and registration[J/OL]. NeuroImage, 2021, 235: 118004 [2022-12-30]. https://www.sciencedirect.com/science/article/pii/S1053811921002810. DOI: 10.1016/j.neuroimage.2021.118004.
[26]
SEDGHI A, O'DONNELL L J, KAPUR T, et al. Image registration: maximum likelihood, minimum entropy and deep learning[J/OL]. Med Image Anal, 2021, 69: 101939 [2022-12-30]. https://www.sciencedirect.com/science/article/abs/pii/S1361841520303030. DOI: 10.1016/j.media.2020.101939.
[27]
MAHAPATRA D, GE Z Y. Training data independent image registration using generative adversarial networks and domain adaptation[J/OL]. Pattern Recognit, 2020, 100: 107109 [2022-12-30]. https://www.sciencedirect.com/science/article/abs/pii/S0031320319304108. DOI: 10.1016/j.patcog.2019.107109.
[28]
CHENG J H, LIU J, KUANG H L, et al. A fully automated multimodal MRI-based multi-task learning for glioma segmentation and IDH genotyping[J]. IEEE Trans Med Imaging, 2022, 41(6): 1520-1532. DOI: 10.1109/TMI.2022.3142321.
[29]
TAO Q, WANG Y Y, XIA L M. Application of artificial intelligence in cardiac MRI analysis[J]. Chin J Radiol, 2020, 54(3): 177-180. DOI: 10.3760/cma.j.issn.1005-1201.2020.03.001.
[30]
WANG H Y, LI Q C, YUAN Y F, et al. Inter-subject registration-based one-shot segmentation with alternating union network for cardiac MRI images[J/OL]. Med Image Anal, 2022, 79: 102455 [2022-12-30]. https://www.sciencedirect.com/science/article/abs/pii/S1361841522001025?via%3Dihub. DOI: 10.1016/j.media.2022.102455.
[31]
KAMNITSAS K, LEDIG C, NEWCOMBE V F J, et al. Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation[J]. Med Image Anal, 2017, 36: 61-78. DOI: 10.1016/j.media.2016.10.004.
[32]
ZHANG F, BREGER A, CHO K I K, et al. Deep learning based segmentation of brain tissue from diffusion MRI[J/OL]. Neuroimage, 2021, 233: 117934 [2022-12-30]. https://www.sciencedirect.com/science/article/pii/S1053811921002111. DOI: 10.1016/j.neuroimage.2021.117934.
[33]
YANG Q S, GUO X Q, CHEN Z, et al. D2-net: dual disentanglement network for brain tumor segmentation with missing modalities[J]. IEEE Trans Med Imaging, 2022, 41(10): 2953-2964. DOI: 10.1109/TMI.2022.3175478.
[34]
MILARDI D, BASILE G A, FASKOWITZ J, et al. Effects of diffusion signal modeling and segmentation approaches on subthalamic nucleus parcellation[J/OL]. NeuroImage, 2022, 250: 118959 [2022-12-30]. https://doi.org/10.1016/j.neuroimage.2022.118959. DOI: 10.1016/j.neuroimage.2022.118959.
[35]
LI Y, DAN T T, LI H J, et al. NPCNet: jointly segment primary nasopharyngeal carcinoma tumors and metastatic lymph nodes in MR images[J]. IEEE Trans Med Imaging, 2022, 41(7): 1639-1650. DOI: 10.1109/TMI.2022.3144274.
[36]
WU Y P, FANG T, WEI H H, et al. Segmentation of core infarct in acute ischemic stroke in diffusion weighted imaging using cascaded VB-Net[J]. Chin J Radiol, 2022, 56(1): 25-29. DOI: 10.3760/cma.j.cn112149-20210415-00373.
[37]
CHEN X X, WANG X M, ZHANG K, et al. Recent advances and clinical applications of deep learning in medical image analysis[J/OL]. Med Image Anal, 2022, 79: 102444 [2022-12-30]. https://doi.org/10.1016/j.media.2022.102444. DOI: 10.1016/j.media.2022.102444.
[38]
WU Y P, LIU B, WU W G, et al. Grading glioma by radiomics with feature selection based on mutual information[J]. J Ambient Intell Human Comput, 2018, 9(5): 1671-1682. DOI: 10.1007/s12652-018-0883-3.
[39]
OUYANG H, LIU G Y, BAI Y P, et al. Clinical application progress of MRI-based radiomics in gliomas[J]. Chin J Magn Reson Imaging, 2020, 11(1): 74-76. DOI: 10.12015/issn.1674-8034.2020.01.017.
[40]
NASER M A, DEEN M J. Brain tumor segmentation and grading of lower-grade glioma using deep learning in MRI images[J/OL]. Comput Biol Med, 2020, 121: 103758 [2022-12-30]. https://www.sciencedirect.com/science/article/abs/pii/S0010482520301335. DOI: 10.1016/j.compbiomed.2020.103758.
[41]
ZHAO W W, SUN J, ZHU J Q. Research progress of artificial intelligence in MRI diagnosis of glioma[J]. Chin J Magn Reson Imaging, 2021, 12(8): 88-90. DOI: 10.12015/issn.1674-8034.2021.08.019.
[42]
ZEGERS C M L, POSCH J, TRAVERSO A, et al. Current applications of deep-learning in neuro-oncological MRI[J]. Phys Med, 2021, 83: 161-173. DOI: 10.1016/j.ejmp.2021.03.003.
[43]
YE Z Z, GEORGE A, WU A T, et al. Deep learning with diffusion basis spectrum imaging for classification of multiple sclerosis lesions[J]. Ann Clin Transl Neurol, 2020, 7(5): 695-706. DOI: 10.1002/acn3.51037.
[44]
ZHANG B Q, CHANG K, RAMKISSOON S, et al. Multimodal MRI features predict isocitrate dehydrogenase genotype in high-grade gliomas[J]. Neuro Oncol, 2017, 19(1): 109-117. DOI: 10.1093/neuonc/now121.
[45]
ZHANG S T, SONG G D, ZANG Y L, et al. Non-invasive radiomics approach potentially predicts non-functioning pituitary adenomas subtypes before surgery[J]. Eur Radiol, 2018, 28(9): 3692-3701. DOI: 10.1007/s00330-017-5180-6.
[46]
CHEN X, LIU J, LI P, et al. The application of artificial intelligence on the classification of benign and malignant breast tumors based on dynamic enhanced MR images[J]. Natl Med J China, 2021, 101(37): 3029-3032. DOI: 10.3760/cma.j.cn112137-20210128-00269.
[47]
CLUCERU J, INTERIAN Y, PHILLIPS J J, et al. Improving the noninvasive classification of glioma genetic subtype with deep learning and diffusion-weighted imaging[J]. Neuro Oncol, 2022, 24(4): 639-652. DOI: 10.1093/neuonc/noab238.
[48]
PARMAR C, BARRY J D, HOSNY A, et al. Data analysis strategies in medical imaging[J]. Clin Cancer Res, 2018, 24(15): 3492-3499. DOI: 10.1158/1078-0432.CCR-18-0385.
[49]
GROSSMANN P, NARAYAN V, CHANG K, et al. Quantitative imaging biomarkers for risk stratification of patients with recurrent glioblastoma treated with bevacizumab[J]. Neuro Oncol, 2017, 19(12): 1688-1697. DOI: 10.1093/neuonc/nox092.
[50]
ZHOU L Q, WU X L, HUANG S Y, et al. Lymph node metastasis prediction from primary breast cancer US images using deep learning[J]. Radiology, 2020, 294(1): 19-28. DOI: 10.1148/radiol.2019190372.
[51]
LI Y H, JIA W D. Research progress of radiomics with artificial intelligence in precise diagnosis and treatment of hepatocellular carcinoma[J]. Chin J Hepatol, 2020, 28(11): 905-909. DOI: 10.3760/cma.j.cn501113-20201022-00573.
[52]
HAN W, QIN L, BAY C, et al. Deep transfer learning and radiomics feature prediction of survival of patients with high-grade gliomas[J]. AJNR Am J Neuroradiol, 2020, 41(1): 40-48. DOI: 10.3174/ajnr.A6365.
[53]
YOON H G, CHEON W, JEONG S W, et al. Multi-parametric deep learning model for prediction of overall survival after postoperative concurrent chemoradiotherapy in glioblastoma patients[J/OL]. Cancers (Basel), 2020, 12(8): 2284 [2022-12-30]. https://www.mdpi.com/2072-6694/12/8/2284. DOI: 10.3390/cancers12082284.
[54]
YAN J, ZHAO Y S, CHEN Y S, et al. Deep learning features from diffusion tensor imaging improve glioma stratification and identify risk groups with distinct molecular pathway activities[J/OL]. EBioMedicine, 2021, 72: 103583 [2022-12-30]. https://www.thelancet.com/journals/ebiom/article/PIIS2352-3964(21)00376-5. DOI: 10.1016/j.ebiom.2021.103583.
[55]
ZHANG X Y, WANG L, ZHU H T, et al. Predicting rectal cancer response to neoadjuvant chemoradiotherapy using deep learning of diffusion kurtosis MRI[J]. Radiology, 2020, 296(1): 56-64. DOI: 10.1148/radiol.2020190936.
[56]
KICKINGEREDER P, ISENSEE F, TURSUNOVA I, et al. Automated quantitative tumour response assessment of MRI in neuro-oncology with artificial neural networks: a multicentre, retrospective study[J]. Lancet Oncol, 2019, 20(5): 728-740. DOI: 10.1016/S1470-2045(19)30098-1.
[57]
HYGINO DA CRUZ L C, RODRIGUEZ I, DOMINGUES R C, et al. Pseudoprogression and pseudoresponse: imaging challenges in the assessment of posttreatment glioma[J]. AJNR Am J Neuroradiol, 2011, 32(11): 1978-1985. DOI: 10.3174/ajnr.A2397.
[58]
PARK J E, HAM S, KIM H S, et al. Diffusion and perfusion MRI radiomics obtained from deep learning segmentation provides reproducible and comparable diagnostic model to human in post-treatment glioblastoma[J]. Eur Radiol, 2021, 31(5): 3127-3137. DOI: 10.1007/s00330-020-07414-3.
[59]
KATABATHULA S, WANG Q Y, XU R. Predict Alzheimer's disease using hippocampus MRI data: a lightweight 3D deep convolutional network model with visual and global shape representations[J/OL]. Alzheimers Res Ther, 2021, 13(1): 104 [2022-12-30]. https://alzres.biomedcentral.com/articles/10.1186/s13195-021-00837-0. DOI: 10.1186/s13195-021-00837-0.
[60]
AMOROSO N, LA ROCCA M, MONACO A, et al. Complex networks reveal early MRI markers of Parkinson's disease[J]. Med Image Anal, 2018, 48: 12-24. DOI: 10.1016/j.media.2018.05.004.
[61]
DUC N T, RYU S, QURESHI M N I, et al. 3D-deep learning based automatic diagnosis of Alzheimer's disease with joint MMSE prediction using resting-state fMRI[J]. Neuroinform, 2020, 18(1): 71-86. DOI: 10.1007/s12021-019-09419-w.
[62]
LIN Q H, NIU Y W, SUI J, et al. SSPNet: an interpretable 3D-CNN for classification of schizophrenia using phase maps of resting-state complex-valued fMRI data[J/OL]. Med Image Anal, 2022, 79: 102430 [2022-12-30]. https://www.sciencedirect.com/science/article/pii/S1361841522000810. DOI: 10.1016/j.media.2022.102430.
[63]
DAN T T, HUANG Z B, CAI H M, et al. Learning brain dynamics of evolving manifold functional MRI data using geometric-attention neural network[J]. IEEE Trans Med Imaging, 2022, 41(10): 2752-2763. DOI: 10.1109/TMI.2022.3169640.
[64]
AZEVEDO T, CAMPBELL A, ROMERO-GARCIA R, et al. A deep graph neural network architecture for modelling spatio-temporal dynamics in resting-state functional MRI data[J/OL]. Med Image Anal, 2022, 79: 102471 [2022-12-30]. https://www.sciencedirect.com/science/article/pii/S1361841522001189. DOI: 10.1016/j.media.2022.102471.
[65]
ZHAO Y, GAO Y R, LI M W, et al. Functional parcellation of human brain using localized topo-connectivity mapping[J]. IEEE Trans Med Imaging, 2022, 41(10): 2670-2680. DOI: 10.1109/TMI.2022.3168888.

PREV Advances in clinical research in urologic neoplasms with machine learning-based radiomics technology
NEXT Prediction of mixed ischemic stroke mechanism based on HR-MRI radiomics of intracranial arterial plaque
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn