Share:
Share this content in WeChat
X
Technical Article
Clinical application of high resolution myocardial T2-weighted dark blood sequence based on artificial intelligence assisted compressed sensing technique in myocardial edema
YAN Xianghu  LUO Yi  RAN Lingping  ZHANG Shiyu  XIA Liming  HUANG Lu 

Cite this article as: Yan XH, Luo Y, Ran LP, et al. Clinical application of high resolution myocardial T2-weighted dark blood sequence based on artificial intelligence assisted compressed sensing technique in myocardial edema[J]. Chin J Magn Reson Imaging, 2022, 13(6): 76-80, 97. DOI:10.12015/issn.1674-8034.2022.06.015.


[Abstract] Objective To explore the feasibility of high spatial resolution T2-weighted dark blood imaging sequence using artificial intelligence assisted compressed sensing (ACS HR-T2W-DB) technique in evaluating myocardial edema in cardiovascular magnetic resonance (CMR) imaging, compared with conventional T2W-DB sequence.Materials and Methods A total of 38 patients who underwent cardiac magnetic resonance examination in our hospital from August to December 2021 were prospectively enrolled. All patients underwent short axial conventional T2W-DB and ACS HR-T2W-DB sequences. Subjective score and objective quantitative parameters were used to evaluate the image quality of conventional T2W-DB and ACS HR-T2W-DB sequences, respectively. Likert score scale was used to evaluate the overall image quality, blood pool inhibition effect, right ventricular free wall, left ventricular free wall and interventricular septum visibility. Objective quantitative parameters included peak signal-to-noise ratio (pSNR) and myocardial blood pool contrast-noise ratio (myocardial-CNR), and 14 patients with regional myocardial edema were evaluated by CNR (edema-CNR).Results Compared with conventional T2W-DB sequence, the spatial resolution of ACS HR-T2W-DB sequence was doubled (conventional 256×163 vs. ACS 336×269). Compared to ACS HR-T2W-DB sequences, the image quality scores of right ventricular wall and left ventricular free wall in ACS HR-T2W-DB sequence were significantly higher than those in conventional T2W-DB sequence, and the difference was statistically significant (P<0.05), but there was no significant difference in overall image quality, blood pool suppression effect and interventricular septum visibility (P>0.05). In the objective quantitative parameters of image quality, pSNR and edema-CNR based on ACS HR-T2W-DB sequence were significantly higher than those of conventional T2W-DB sequence, and the difference was statistically significant (P<0.05), but there was no significant difference in myocardial-CNR (P>0.05).Conclusions Compared with conventional T2W-DB sequence, ACS HR-T2W-DB sequence provides higher spatial resolution, higher image quality, edema-CNR and better left ventricular free wall visibility without longer scanning time, which is promising to become a routine sequence for patients with suspected myocardial edema.
[Keywords] cardiac magnetic resonance;artificial intelligence;compressed sensing;T2-weighted dark blood;spatial resolution;edema

YAN Xianghu1   LUO Yi1   RAN Lingping1   ZHANG Shiyu2   XIA Liming1   HUANG Lu1*  

1 Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430030, China

2 United Imaging Healthcare, Shanghai 201800, China

Huang L, E-mail: tj_lhuang@hust.edu.cn

Conflicts of interest   None.

Received  2022-01-20
Accepted  2022-05-18
DOI: 10.12015/issn.1674-8034.2022.06.015
Cite this article as: Yan XH, Luo Y, Ran LP, et al. Clinical application of high resolution myocardial T2-weighted dark blood sequence based on artificial intelligence assisted compressed sensing technique in myocardial edema[J]. Chin J Magn Reson Imaging, 2022, 13(6): 76-80, 97.DOI:10.12015/issn.1674-8034.2022.06.015

[1]
Abdel-Aty H, Simonetti O, Friedrich MG. T2-weighted cardiovascular magnetic resonance imaging[J]. J Magn Reson Imaging, 2007, 26(3): 452-459. DOI: 10.1002/jmri.21028.
[2]
Amano Y, Tachi M, Tani H, et al. T2-Weighted Cardiac Magnetic Resonance Imaging of Edema in Myocardial Diseases[J]. The Scientific World Journal, 2012, 2012: 1-7. DOI: 10.1100/2012/194069.
[3]
Liu X, Yang ZG, Li Y. Clinical application and current research status of cardiac magnetic resonance imaging of myocardial infarction[J]. Chin J Magn Reson Imaging, 2021, 12(8): 98-100, 107. DOI: 10.12015/issn.1674-8034.2021.08.022.
[4]
Busse A, Rajagopal R, Yücel S, et al. Cardiac MRI-Update 2020[J]. Radiologe, 2020, 60(S1): 33-40. DOI: 10.1007/s00117-020-00687-1.
[5]
Green JD, Clarke JR, Flewitt JA, et al. Single-shot steady-state free precession can detect myocardial edema in patients: A feasibility study[J]. J Magn Reson Imaging, 2009, 30(3): 690-695. DOI: 10.1002/jmri.21868.
[6]
Naßenstein K, Nensa F, Schlosser T, et al. Cardiac MRI: T2-Mapping Versus T2-Weighted Dark-Blood TSE Imaging for Myocardial Edema Visualization in Acute Myocardial Infarction[J]. Fortschr Röntgenstr, 2013, 186(2): 166-172. DOI: 10.1055/s-0033-1350516.
[7]
Steen H, Voss F, André F, et al. Clinical feasibility study for detection of myocardial oedema by a cine SSFP sequence in comparison to a conventional T2-weighted sequence[J]. Clin Res Cardiol, 2012, 101(2): 125-131. DOI: 10.1007/s00392-011-0373-5.
[8]
Wheen P, Armstrong R, Daly CA. Recent Advances in T1 and T2 Mapping in the Assessment of Fulminant Myocarditis by Cardiac Magnetic Resonance[J]. Curr Cardiol Rep, 2020, 22(7): 47. DOI: 10.1007/s11886-020-01295-0.
[9]
Hu C, Huber S, Nguyen V, et al. Fat-saturated dark-blood cardiac T2 mapping in a single breath-hold[J]. Magnetic Resonance Imaging, 2021, 81: 24-32. DOI: 10.1016/j.mri.2021.05.004.
[10]
Ogawa R, Kido T, Nakamura M, et al. Reconstruction of cardiovascular black-blood T2-weighted image by deep learning algorithm: A comparison with intensity filter[J]. Acta Radiologica Open, 2021, 10(9): 205846012110447. DOI: 10.1177/20584601211044779.
[11]
Hammernik K, Klatzer T, Kobler E, et al. Learning a variational network for reconstruction of accelerated MRI data[J]. Magn Reson Med, 2018, 79(6): 3055-3071. DOI: 10.1002/mrm.26977.
[12]
Zhu B, Liu JZ, Cauley SF, et al. Image reconstruction by domain-transform manifold learning[J]. Nature, 2018, 555(7697): 487-492. DOI: 10.1038/nature25988.
[13]
Mardani M, Gong E, Cheng JY, 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.
[14]
Johnson PM, Recht MP, Knoll F. Improving the Speed of MRI with Artificial Intelligence[J]. Semin Musculoskelet Radiol, 2020, 24(1): 12-20. DOI: 10.1055/s-0039-3400265.
[15]
Sheng R, Zheng L, Jin K, et al. Single-breath-hold T2WI liver MRI with deep learning-based reconstruction: A clinical feasibility study in comparison to conventional multi-breath-hold T2WI liver MRI[J]. Magnetic Resonance Imaging, 2021, 81: 75-81. DOI: 10.1016/j.mri.2021.06.014.
[16]
Wang S, Cao G, Wang Y, et al. Review and Prospect: Artificial Intelligence in Advanced Medical Imaging. Front Radio, 2021, 1: 781868. DOI: 10.3389/fradi.2021.781868.
[17]
Xie J, Xu L, Chen E. Image Denoising and Inpainting with Deep Neural Networks[J]. Advances in Neural Information Processing Systems, 2012, 341-349.
[18]
Edelman RR, Botelho M, Pursnani A, et al. Improved dark blood imaging of the heart using radial balanced steady-state free precession[J]. J Cardiovasc Magn Reson, 2017, 18(1): 69. DOI: 10.1186/s12968-016-0293-7.
[19]
Friedrich MG, Sechtem U, Schulz-Menger J, et al. Cardiovascular Magnetic Resonance in Myocarditis: A JACC White Paper[J]. J Am Coll Cardiol, 2009, 53(17): 1475-1487. DOI: 10.1016/j.jacc.2009.02.007.
[20]
Zhu Y, Yang D, Zou L, et al. T2STIR preparation for single-shot cardiovascular magnetic resonance myocardial edema imaging[J]. J Cardiovasc Magn Reson, 2019, 21(1): 72. DOI: 10.1186/s12968-019-0583-y.
[21]
Hu C, Huber S, Latif SR, et al. Reverse double inversion-recovery: Improving motion robustness of cardiac T2-weighted dark-blood turbo spin-echo sequence[J]. J Magn Reson Imaging, 2018, 47(6): 1498-1508. DOI: 10.1002/jmri.25886.
[22]
Mann LW, Higgins DM, Peters CN, et al. Accelerating MR Imaging Liver Steatosis Measurement Using Combined Compressed Sensing and Parallel Imaging: A Quantitative Evaluation[J]. Radiology, 2016, 278(1): 247-256. DOI: 10.1148/radiol.2015150320.
[23]
Siewert B, Müller MF, Foley M, et al. Fast MR imaging of the liver: quantitative comparison of techniques[J]. Radiology, 1994, 193(1): 37-42. DOI: 10.1148/radiology.193.1.8090918.
[24]
Mayr A, Reiter G, Beitzke D. Cardiac magnetic resonance imaging: Trends and developments[J]. Der Radiologe, 2020, 60(12): 1142-1152. DOI: 10.1007/s00117-020-00766-3.
[25]
Chen H, Zhang Y, Kalra MK, et al. Low-Dose CT With a Residual Encoder-Decoder Convolutional Neural Network[J]. IEEE Trans Med Imaging, 2017, 36(12): 2524-2535. DOI: 10.1109/TMI.2017.2715284.
[26]
Schlemper J, Caballero J, Hajnal JV, et al. A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction[J]. IEEE Trans Med Imaging, 2018, 37(2): 491-503. DOI: 10.1109/TMI.2017.2760978.
[27]
Kumar A, Beohar N, Arumana JM, et al. CMR Imaging of Edema in Myocardial Infarction Using Cine Balanced Steady-State Free Precession[J]. JACC: Cardiovascular Imaging, 2011, 4(12): 1265-1273. DOI: 10.1016/j.jcmg.2011.04.024.
[28]
Russo V, Lovato L, Ligabue G. Cardiac MRI: technical basis[J]. Radiol Med, 2020, 125(11): 1040-1055. DOI: 10.1007/s11547-020-01282-z.
[29]
Liu J, Jin H, Chen Y, et al. Free-breathing BLADE acquisition method improves T2-weighted cardiac MR image quality compared with conventional breath-hold turbo spin-echo cartesian acquisition[J]. Acta Radiol, 2021, 62(3): 341-347. DOI: 10.1177/0284185120924567.

PREV Resting-state functional magnetic resonance imaging in patients with nocturnal enuresis
NEXT Quantification of the impact of Gadolinium agent on amide-proton-transfer weighted MRI: An ex vivo and in vivo study
  



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