Share：
Share this content in WeChat
X
[Chinese][PDF]563
• Special Focus •
Preliminary application of deep learning-based image reconstruction in improving temporomandibular joint MRI image quality
WANG Chunjie  SHAN Yi  ZHANG Yue  WU Chunxue  LIU Can  WANG Jingjuan  WU Tao  GE Xianpeng  LU Jie 

Cite this article as: WANG C J, SHAN Y, ZHANG Y, et al. Preliminary application of deep learning-based image reconstruction in improving temporomandibular joint MRI image quality[J]. Chin J Magn Reson Imaging, 2024, 15(10): 3-7, 21. DOI:10.12015/issn.1674-8034.2024.10.002.


[Abstract] Objective To explore the application value of deep learning reconstruction (DLR) technology in enhancing the image quality and reducing the scan time of fast-spin echo proton density weighted imaging (FSE-PD) in MRI of the temporomandibular joint (TMJ).Materials and Methods Recruit 40 healthy volunteers and undergo MRI scans of the TMJ. Each healthy volunteer underwent conventional FSE-PD MRI scans and accelerated FSE-PD scans using DLR, the original accelerated FSE-PD images without DLR were simultaneously preserved. Two radiologists qualitatively and quantitatively evaluated the image quality of the three FSE-PD image sets, individually. Qualitative assessments utilized a Likert scale (5-point) for subjective scoring of anatomical structure clarity and overall image quality. Quantitative assessments utilized signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) for objective evaluation of image quality. One-way ANOVA and Kruskal-Wallis test were used to compare the differences in subjective scores and objective indicators among the three groups. The intra-class correlation coefficient (ICC) was used to evaluate the consistency of the subjective scores of the two radiologists.Results Compared to the conventional FSE-PD group, the DLR-accelerated FSE-PD group demonstrated a 67% reduction in scan time. The two radiologists exhibited good consistency in subjective scores for anatomical structure clarity and overall image quality (ICC of 0.80 and 0.78, respectively). There were significant differences in anatomical clarity and overall image quality scores among the conventional FSE-PD group, accelerated FSE-PD group, and DLR-accelerated FSE-PD group (P<0.05). The differences in SNR and CNR among the three FSE-PD groups were statistically significant (P<0.05). Qualitative and quantitative evaluation results for the DLR-accelerated FSE-PD group were both significantly superior to the conventional FSE-PD group.Conclusions DLR technology could shorten the scanning time of conventional FSE-PD MRI of the TMJ, enhance image quality, and help patients complete the examination faster.
[Keywords] temporomandibular joint；deep learning；image reconstruction；magnetic resonance imaging；image quality

WANG Chunjie1, 2   SHAN Yi1, 2   ZHANG Yue1, 2   WU Chunxue1, 2   LIU Can1, 2   WANG Jingjuan1, 2   WU Tao3   GE Xianpeng4   LU Jie1, 2*  

1 Department of Radiology and Nuclear Medicine, Xuanwu Hospital, Capital Medical University, Beijing 100053, China

2 Beijing Key Laboratory of MRI and Brain Informatics, Beijing 100053, China

3 Clinical Marking Department of MR, General Electric Medical (China) Co., Ltd., Beijing 100176, China

4 Department of Stomatology, Xuanwu Hospital, Capital Medical University, Beijing 100053, China

Corresponding author: LU J, E-mail: imaginglu@hotmail.com

Conflicts of interest   None.

Received  2024-03-29
Accepted  2024-09-06
DOI: 10.12015/issn.1674-8034.2024.10.002
Cite this article as: WANG C J, SHAN Y, ZHANG Y, et al. Preliminary application of deep learning-based image reconstruction in improving temporomandibular joint MRI image quality[J]. Chin J Magn Reson Imaging, 2024, 15(10): 3-7, 21. DOI:10.12015/issn.1674-8034.2024.10.002.

[1]
XIONG X, YE Z, TANG H H, et al. MRI of temporomandibular joint disorders: recent advances and future directions[J]. J Magn Reson Imaging, 2021, 54(4): 1039-1052. DOI: 10.1002/jmri.27338.
[2]
YıLMAZ D, KAMBUROĞLU K. Comparison of the effectiveness of high resolution ultrasound with MRI in patients with temporomandibular joint dısorders[J/OL]. Dentomaxillofac Radiol, 2019, 48(5): 20180349 [2024-03-28]. https://pubmed.ncbi.nlm.nih.gov/30810356/. DOI: 10.1259/dmfr.20180349.
[3]
FU K Y, HU M, YU Q, et al. Experts consensus on MRI examination specification and diagnostic criteria of temporomandibular joint disc displacement[J]. Chin J Stomatol, 2020, 55(9): 608-612. DOI: 10.3760/cma.j.cn112144-20200514-00268.
[4]
GAO P, JIN C, WANG L, et al. Quality evaluation of temporomandibular joint images from 3 high-resolution dynamic sequences[J]. Acta Acad Med Sin, 2023, 45(1): 50-56. DOI: 10.3881/j.issn.1000-503X.15078.
[5]
JIN K H, LEE D, YE J C. A general framework for compressed sensing and parallel MRI using annihilating filter based low-rank Hankel matrix[J]. IEEE Trans Comput Imag, 2016, 2(4): 480-495. DOI: 10.1109/TCI.2016.2601296.
[6]
SHIN P J, LARSON P E, OHLIGER M A, et al. Calibrationless parallel imaging reconstruction based on structured low-rank matrix completion[J]. Magn Reson Med, 2014, 72(4): 959-970. DOI: 10.1002/mrm.24997.
[7]
JUNG H, SUNG K, NAYAK K S, et al. K-t FOCUSS: a general compressed sensing framework for high resolution dynamic MRI[J]. Magn Reson Med, 2009, 61(1): 103-116. DOI: 10.1002/mrm.21757.
[8]
IUGA A I, ABDULLAYEV N, WEISS K, et al. Accelerated MRI of the knee. Quality and efficiency of compressed sensing[J/OL]. Eur J Radiol, 2020, 132: 109273 [2024-03-28]. https://pubmed.ncbi.nlm.nih.gov/32957000/. DOI: 10.1016/j.ejrad.2020.109273.
[9]
BRATKE G, RAU R, WEISS K, et al. Accelerated MRI of the lumbar spine using compressed sensing: quality and efficiency[J/OL]. J Magn Reson Imaging, 2019, 49(7): e164-e175 [2024-03-28]. https://pubmed.ncbi.nlm.nih.gov/30267462/. DOI: 10.1002/jmri.26526.
[10]
LEBEL R M. Performance characterization of a novel deep learning-based MR image reconstruction pipeline[EB/OL]. 2020: arXiv: 2008.06559. http://arxiv.org/abs/2008.06559
[11]
KIRYU S, AKAI H, YASAKA K, et al. Clinical impact of deep learning reconstruction in MRI[J/OL]. Radiographics, 2023, 43(6): e220133 [2024-03-28]. https://pubmed.ncbi.nlm.nih.gov/37200221/. DOI: 10.1148/rg.220133.
[12]
YAN F H. The clinical application and development prospect of deep learning MRI reconstruction algorithm[J]. Chin J Magn Reson Imag, 2023, 14(5): 8-10. DOI: 10.12015/issn.1674-8034.2023.05.002.
[13]
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 [2024-03-28]. https://pubmed.ncbi.nlm.nih.gov/36318032/. DOI: 10.1148/radiol.212922.
[14]
SUN S, TAN E T, MINTZ D N, et al. Evaluation of deep learning reconstructed high-resolution 3D lumbar spine MRI[J]. Eur Radiol, 2022, 32(9): 6167-6177. DOI: 10.1007/s00330-022-08708-4.
[15]
JOHNSON P M, LIN D J, ZBONTAR J, et al. Deep learning reconstruction enables prospectively accelerated clinical knee MRI[J/OL]. Radiology, 2023, 307(2): e220425 [2024-03-28]. https://pubmed.ncbi.nlm.nih.gov/36648347/. DOI: 10.1148/radiol.220425.
[16]
WU X X, LU X F, LIU C S, et al. Clinical feasibility of 2D FSE sequences of the knee MRI protocol using deep-learning image reconstruction[J]. Chin J Magn Reson Imag, 2023, 14(5): 53-59. DOI: 10.12015/issn.1674-8034.2023.05.011.
[17]
YANG J, LI Q G, WU T, et al. A comparative study on the enhancement of high resolution coronal image quality by deep learning reconstruction[J]. Chin J Magn Reson Imag, 2023, 14(5): 21-24, 30. DOI: 10.12015/issn.1674-8034.2023.05.005.
[18]
ZHANG X X, WANG Y C, WANG S C, et al. Feasibility study of deep learning reconstruction in the clinical application of MRI in bladder cancer[J]. Chin J Magn Reson Imag, 2023, 14(5): 36-40. DOI: 10.12015/issn.1674-8034.2023.05.008.
[19]
PARK J C, PARK K J, PARK M Y, et al. Fast T2-weighted imaging with deep learning-based reconstruction: evaluation of image quality and diagnostic performance in patients undergoing radical prostatectomy[J]. J Magn Reson Imaging, 2022, 55(6): 1735-1744. DOI: 10.1002/jmri.27992.
[20]
KE Z, LI L, SONG X Y, et al. Novel deep learning-based T2-weighted imaging of the prostate provides superior image quality[J]. Chin J Magn Reson Imaging, 2023, 14(5): 41-47. DOI: 10.12015/issn.1674-8034.2023.05.009.
[21]
UEDA T, OHNO Y, YAMAMOTO K, et al. Deep learning reconstruction of diffusion-weighted MRI improves image quality for prostatic imaging[J]. Radiology, 2022, 303(2): 373-381. DOI: 10.1148/radiol.204097.
[22]
JOHNSON P M, TONG A, DONTHIREDDY A, et al. Deep learning reconstruction enables highly accelerated biparametric MR imaging of the prostate[J]. J Magn Reson Imaging, 2022, 56(1): 184-195. DOI: 10.1002/jmri.28024.
[23]
WANG Y C, ZHANG X X, HU M C, et al. Value of deep learning reconstruction in optimizing prostate MR T2-weighted imaging scanning time and imaging quality[J]. Chin J Magn Reson Imag, 2023, 14(5): 48-52, 59. DOI: 10.12015/issn.1674-8034.2023.05.010.
[24]
KIM E, CHO H H, CHO S H, et al. Accelerated synthetic MRI with deep learning-based reconstruction for pediatric neuroimaging[J]. AJNR Am J Neuroradiol, 2022, 43(11): 1653-1659. DOI: 10.3174/ajnr.A7664.
[25]
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.
[26]
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.
[27]
MUSCOGIURI G, MARTINI C, GATTI M, et al. Feasibility of late gadolinium enhancement (LGE) in ischemic cardiomyopathy using 2D-multisegment LGE combined with artificial intelligence reconstruction deep learning noise reduction algorithm[J/OL]. Int J Cardiol, 2021, 343: 164-170 [2024-03-28]. https://pubmed.ncbi.nlm.nih.gov/34517017/. DOI: 10.1016/j.ijcard.2021.09.012.
[28]
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.
[29]
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/OL]. Magn Reson Imaging, 2022, 93: 175-180 [2024-03-28]. https://pubmed.ncbi.nlm.nih.gov/35987419/. DOI: 10.1016/j.mri.2022.08.012.
[30]
YANG R J, ZOU Y J, LIU W V, et al. High-resolution single-shot fast spin-echo MR imaging with deep learning reconstruction algorithm can improve repeatability and reproducibility of follicle counting[J/OL]. J Clin Med, 2023, 12(9): 3234 [2024-03-28]. https://pubmed.ncbi.nlm.nih.gov/37176674/. DOI: 10.3390/jcm12093234.

PREV Editorial comment: the progress in clinical application of deep learning MRI reconstruction algorithm
NEXT Feasibility study of deep learning-based MRI image reconstruction algorithms for myocardial delayed enhancement in unrecognized myocardial infarction
  


LINK


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