Share：
Share this content in WeChat
X
[Chinese][PDF]10402
• Special Focus •
Clinical feasibility of breath-hold fat-suppressed T2-weighted sequence with deep learning reconstruction for liver imaging
FANG Shu  WU Mengxiong  CHEN Qian  LIU Fangtao  DONG Haipeng  FU Guifeng  YAN Fuhua  LIN Huimin 

Cite this article as: FANG S, WU M X, CHEN Q, et al. Clinical feasibility of breath-hold fat-suppressed T2-weighted sequence with deep learning reconstruction for liver imaging[J]. Chin J Magn Reson Imaging, 2023, 14(5): 31-35, 40. DOI:10.12015/issn.1674-8034.2023.05.007.


[Abstract] Objective To assess the feasibility of the breath-hold fat-suppressed T2-weighted sequence with deep learning reconstruction technique (BH fs T2 DLR) and compare its image quality and acquisition time with those of the respiratory-gated propeller fat-saturated T2-weighted sequence (RTr fs T2 Propeller).Materials and Methods A total of 46 patients who underwent liver MRI in our hospital (23 patients with hepatic lesions and 23 without obvious lesions) were prospectively enrolled in this study from January to June 2022. Two sequences of BH fs T2 DLR and RTr fs T2 Propeller were performed with a 3.0 T scanner. Qualitative image quality was evaluated using a 5-point Likert scale. Quantitative image quality parameters included signal-to-noise ratio (SNR), lesion to liver contrast-to-noise ratio (CNR_Lesion) for patients with liver lesions, and spleen to liver contrast-to-noise ratio (CNR_Spleen) for patients without liver lesions. Wilcoxon matched-pairs signed-ranks test was performed for comparison analysis at a significance level of P＜0.05.Results BH fs T2 DLR showed significantly shorter scan time (38 s vs. 162 s, P＜0.01). BH fs T2 DLR sequence achieved higher scores for all qualitative image quality parameters (P＜0.01). BH fs T2 DLR also showed significantly higher SNR [290.30 (220.63, 383.80)] vs. [166.85 (131.40, 224.83)], CNR_Lesion [602.60 (372.40, 708.50)] vs. [259.20 (217.90, 367.90)] and CNR_Spleen [267.70 (146.70, 432.80)] vs. [206.20 (104.40, 293.70)] than RTr fs T2 Propeller, respectively (P＜0.01).Conclusions The BH fs T2 DLR sequence can provide improved image quality and simultaneously significant reduction in scanning time, and may replace the RTr fs T2 Propeller sequence in certain scenarios, as a promising alternative in clinical practice.
[Keywords] liver；magnetic resonance imaging；T2 weighted imaging；deep learning

FANG Shu   WU Mengxiong   CHEN Qian   LIU Fangtao   DONG Haipeng   FU Guifeng   YAN Fuhua   LIN Huimin*  

Department of Radiology, Ruijin Hospital, Shanghai Jiaotong University of Medicine, Shanghai 200025, China

Corresponding author: Lin HM, E-mail: lhm12362@rjh.com.cn

Conflicts of interest   None.

Received  2023-02-10
Accepted  2023-05-06
DOI: 10.12015/issn.1674-8034.2023.05.007
Cite this article as: FANG S, WU M X, CHEN Q, et al. Clinical feasibility of breath-hold fat-suppressed T2-weighted sequence with deep learning reconstruction for liver imaging[J]. Chin J Magn Reson Imaging, 2023, 14(5): 31-35, 40. DOI:10.12015/issn.1674-8034.2023.05.007.

[1]
LI L, LIU G H, ZHAO G D, et al. Comparative analysis of different pulse sequences in the detection of hepatic lesions[J]. Mod Med J China, 2018, 20(5): 33-36. DOI: 10.3969/j.issn.1672-9463.2018.05.009">10.3969/j.issn.1672-9463.2018.05.009">10.3969/j.issn.1672-9463.2018.05.009.
[2]
JIANG C F. Application value of BLADE technique in upper abdominal free breathing navigation T2WI[J]. World J Complex Med, 2022, 8(2): 80-82, 86. DOI: 10.11966/j.issn.2095-994X.2022.08.02.20">10.11966/j.issn.2095-994X.2022.08.02.20">10.11966/j.issn.2095-994X.2022.08.02.20.
[3]
SCHREIBER-ZINAMAN J, ROSENKRANTZ A B. Frequency and reasons for extra sequences in clinical abdominal MRI examinations[J]. Abdom Radiol (NY), 2017, 42(1): 306-311. DOI: 10.1007/s00261-016-0877-6">10.1007/s00261-016-0877-6">10.1007/s00261-016-0877-6.
[4]
SHANBHOGUE K, TONG A, SMEREKA P, et al. Accelerated single-shot T2-weighted fat-suppressed (FS) MRI of the liver with deep learning-based image reconstruction: qualitative and quantitative comparison of image quality with conventional T2-weighted FS sequence[J]. Eur Radiol, 2021, 31(11): 8447-8457. DOI: 10.1007/s00330-021-08008-3">10.1007/s00330-021-08008-3">10.1007/s00330-021-08008-3.
[5]
CHARTRAND G, CHENG P M, VORONTSOV E, et al. Deep learning: a primer for radiologists[J]. Radiographics, 2017, 37(7): 2113-2131. DOI: 10.1148/rg.2017170077">10.1148/rg.2017170077">10.1148/rg.2017170077.
[6]
YU Y Z, SHI D J, MA J C, et al. Advances in application of artificial intelligence in medical image analysis[J]. Chin J Med Imaging Technol, 2019, 35(12): 1808-1812. DOI: 10.13929/j.1003-3289.201909150">10.13929/j.1003-3289.201909150">10.13929/j.1003-3289.201909150.
[7]
YU K Y, ZHANG X D. Research progresses of deep learning in imaging diagnosis of knee joint lesions[J]. Chin J Med Imaging Technol, 2021, 37(10): 1563-1566. DOI: 10.13929/j.issn.1003-3289.2021.10.030">10.13929/j.issn.1003-3289.2021.10.030">10.13929/j.issn.1003-3289.2021.10.030.
[8]
XU Q, HE Y S, LUO X, et al. The application of multiple number of excitation(NEX)free breathing T1 VIBE sequence in liver MR[J]. Chin J CT MRI, 2020, 18(4): 89-90, 152. DOI: 10.3969/j.issn.1672-5131.2020.04.027">10.3969/j.issn.1672-5131.2020.04.027">10.3969/j.issn.1672-5131.2020.04.027.
[9]
SHI Z, ZHAO X M, SONG J F, et al. Comparison of breath-hold, respiratory-triggered and free-breathing techniques for diffusion-weighted imaging acquisitions of the upper abdomen at 1.5 T and 3.0 T[J]. Radiol Pract, 2015, 30(6): 686-690. DOI: 10.13609/j.cnki.1000-0313.2015.06.020">10.13609/j.cnki.1000-0313.2015.06.020">10.13609/j.cnki.1000-0313.2015.06.020.
[10]
CANELLAS R, ROSENKRANTZ A B, TAOULI B, et al. Abbreviated MRI protocols for the abdomen[J]. RadioGraphics, 2019, 39(3): 744-758. DOI: 10.1148/rg.2019180123">10.1148/rg.2019180123">10.1148/rg.2019180123.
[11]
MULÉ S, KHARRAT R, ZERBIB P, et al. Fast T2-weighted liver MRI: image quality and solid focal lesions conspicuity using a deep learning accelerated single breath-hold HASTE fat-suppressed sequence[J]. Diagn Interv Imaging, 2022, 103(10): 479-485. DOI: 10.1016/j.diii.2022.05.001">10.1016/j.diii.2022.05.001">10.1016/j.diii.2022.05.001.
[12]
BAYRAMOGLU S, KILICKESMEZ O, CIMILLI T, et al. T2-weighted MRI of the upper abdomen: comparison of four fat-suppressed T2-weighted sequences including PROPELLER (BLADE) technique[J]. Acad Radiol, 2010, 17(3): 368-374. DOI: 10.1016/j.acra.2009.10.015">10.1016/j.acra.2009.10.015">10.1016/j.acra.2009.10.015.
[13]
KIDOH M, SHINODA K, KITAJIMA M, et al. Deep learning based noise reduction for brain MR imaging: tests on phantoms and healthy volunteers[J]. Magn Reson Med Sci, 2020, 19(3): 195-206. DOI: 10.2463/mrms.mp.2019-0018">10.2463/mrms.mp.2019-0018">10.2463/mrms.mp.2019-0018.
[14]
GASSENMAIER S, AFAT S, NICKEL M D, et al. Accelerated T2-weighted TSE imaging of the prostate using deep learning image reconstruction: a prospective comparison with standard T2-weighted TSE imaging[J/OL]. Cancers, 2021, 13(14): 3593 [2022-10-18]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8303682/pdf/cancers-13-03593.pdf. DOI: 10.3390/cancers13143593">10.3390/cancers13143593">10.3390/cancers13143593.
[15]
VAN DER VELDE N, HASSING H C, BAKKER B J, et al. Improvement of late gadolinium enhancement image quality using a deep learning-based reconstruction algorithm and its influence on myocardial scar quantification[J]. Eur Radiol, 2021, 31(6): 3846-3855. DOI: 10.1007/s00330-020-07461-w">10.1007/s00330-020-07461-w">10.1007/s00330-020-07461-w.
[16]
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 [2022-10-18]. https://pubs.rsna.org/doi/10.1148/radiol.212922. DOI: 10.1148/radiol.212922">10.1148/radiol.212922">10.1148/radiol.212922.
[17]
GINOCCHIO L A, SMEREKA P N, TONG A, et al. Accelerated T2-weighted MRI of the liver at 3 T using a single-shot technique with deep learning-based image reconstruction: impact on the image quality and lesion detection[J].Abdom Radiol, 2023, 48(1): 282-290. DOI: 10.1007/s00261-022-03687-y">10.1007/s00261-022-03687-y">10.1007/s00261-022-03687-y.
[18]
SHENG R F, ZHENG L Y, JIN K P, 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]. Magn Reson Imaging, 2021, 81: 75-81. DOI: 10.1016/j.mri.2021.06.014">10.1016/j.mri.2021.06.014">10.1016/j.mri.2021.06.014.
[19]
KANIEWSKA M, DEININGER-CZERMAK E, GETZMANN J M, et al. Application of deep learning-based image reconstruction in MR imaging of the shoulder joint to improve image quality and reduce scan time[J]. Eur Radiol, 2023, 33(3): 1513-1525. DOI: 10.1007/s00330-022-09151-1">10.1007/s00330-022-09151-1">10.1007/s00330-022-09151-1.
[20]
YU R L, LIU X S. Feasibility of compressed sensing techniques in liver's contrast-enhanced MRI examination[J]. Chin Med Equip J, 2020, 41(12): 72-75. DOI: 10.19745/j.1003-8868.2020279">10.19745/j.1003-8868.2020279">10.19745/j.1003-8868.2020279.
[21]
LI H L, HU C L, YANG Y, et al. Single-breath-hold T2WI MRI with artificial intelligence-assisted technique in liver imaging: As compared with conventional respiratory-triggered T2WI[J]. Magn Reson Imaging, 2022, 93: 175-180. DOI: 10.1016/j.mri.2022.08.012">10.1016/j.mri.2022.08.012">10.1016/j.mri.2022.08.012.
[22]
XU H, DU F, WEN X X, et al. Comparison of ACS and BLADE T2WI sequences in upper abdomen study[J]. Chin J Clin Med, 2022, 29(1): 92-96. DOI: 10.12025/j.issn.1008-6358.2022.20211448">10.12025/j.issn.1008-6358.2022.20211448">10.12025/j.issn.1008-6358.2022.20211448.
[23]
LI L, LI N, SUN Y M, et al. Study on differences of breath-holds applied in MRI detection of both chest and abdomen[J]. China Med Devices, 2021, 36(10): 48-51, 55. DOI: 10.3969/j.issn.1674-1633.2021.10.011">10.3969/j.issn.1674-1633.2021.10.011">10.3969/j.issn.1674-1633.2021.10.011.
[24]
YANG P, ZHANG G M, LI S. Application of respiratory training on nursing of patients with liver MRI examination[J]. Nurs J Chin People's Liberation Army, 2014, 31(15): 44-45, 48. DOI: 10.3969/j.issn.1008-9993.2014.15.014.
[25]
HAMILTON J, FRANSON D, SEIBERLICH N. Recent advances in parallel imaging for MRI[J]. Prog Nucl Magn Reson Spectrosc, 2017, 101: 71-95. DOI: 10.1016/j.pnmrs.2017.04.002.
[26]
PETERS R. The clinical benefits of AIR™ Recon DL for MR image reconstruction[EB/OL]. [2022-11-07]. https://www.gehealthcare.com/ensg/-/jssmedia/c943df5927a049bb9ac95a9 f0349ad8c.pdf.
[27]
KIM M, KIM H S, KIM H J, et al. Thin-slice pituitary MRI with deep learning-based reconstruction: diagnostic performance in a postoperative setting[J]. Radiology, 2021, 298(1): 114-122. DOI: 10.1148/radiol.2020200723.
[28]
SCHLEMPER J, CABALLERO J, HAJNAL J V, 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.
[29]
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.
[30]
HERRMANN J, NICKEL D, MUGLER J P, et al. Development and evaluation of deep learning-accelerated single-breath-hold abdominal HASTE at 3 T using variable refocusing flip angles[J]. Invest Radiol, 2021, 56(10): 645-652. DOI: 10.1097/RLI.0000000000000785.

PREV The MRI-based 3D-ResNet101 deep learning model for predicting preoperative grading of gliomas: A multicenter study
NEXT Feasibility study of deep learning reconstruction in the clinical application of MRI in bladder cancer
  


LINK


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