Share：
Share this content in WeChat
X
[Chinese] [PDF] 526 1
• Clinical Article •
Application value of deep learning-based accelerated T1WI and T2WI sequences in head and neck tumors
WANG Tianjiao  WANG Yun  CHEN Yu  SU Tong  QU Jiangming  XU Zhentan  WANG Xiao  ZHANG Zhuhua  XUE Huadan  FU Haihong  FENG Feng  JIN Zhengyu 

Cite this article as: WANG T J, WANG Y, CHEN Y, et al. Application value of deep learning-based accelerated T1WI and T2WI sequences in head and neck tumors[J]. Chin J Magn Reson Imaging, 2025, 16(9): 60-65. DOI:10.12015/issn.1674-8034.2025.09.010.


[Abstract] Objective To evaluate the application value of deep learning (DL)-based accelerated T1-weighted imaging (T1WI) and T2-weighted imaging (T2WI) in head and neck tumors.Materials and Methods Thirty-five untreated patients with head and neck tumors were prospectively enrolled and underwent head and neck MRI standard (T1WI, T2WI-Dixon) and DL sequences (DL-T1WI, DL-T2WI-Dixon). Image quality was subjectively rated by two radiologists using a five-point scale for overall image quality, artifacts and lesion conspicuity. Objective image quality was assessed by calculation of signal-to-noise ratio (SNR) of muscle, fat and tumor and contrast-to-noise ratio (CNR) of tumor in standard and DL sequences by one radiologist. Scan time and image quality scores were compared between standard and DL sequences using Kruskal-Wallis test.Results DL-T1WI (89 s) and DL-T2WI-Dixon (101 s) sequences reduced 46% scan time compared to standard T1WI (164 s) and T2WI-Dixon (188 s) sequences, respectively. There were no significant difference in overall image quality, artifacts and lesion conspicuity between DL-T1WI, DL-T2WI-Dixon sequences and standard T1WI and T2WI-Dixon sequences (all P > 0.05). SNR of fat and tumor and CNR of tumor in DL-T1WI sequence were comparable with that in standard T1WI sequence (all P > 0.05), SNR of muscle, fat and tumor and CNR of tumor in DL-T2WI-Dixon sequence were comparable with that in standard T2WI-Dixon sequence (all P > 0.05).Conclusions DL-based accelerated MRI sequences could effectively reduce scanning time in patients with head and neck tumors. Except for the SNR of muscle in DL-T1WI sequence, the remaining objective image quality metrics of DL sequences are comparable to those in standard sequences. Moreover, compared to standard T1WI and T2WI-Dixon sequences, DL-T1WI and DL-T2WI-Dixon sequences could maintain excellent subjective image quality.
[Keywords] head and neck tumors；deep learning reconstruction；magnetic resonance imaging；signal-to-noise ratio；contrast-to-noise ratio

WANG Tianjiao   WANG Yun   CHEN Yu*   SU Tong   QU Jiangming   XU Zhentan   WANG Xiao   ZHANG Zhuhua   XUE Huadan   FU Haihong   FENG Feng   JIN Zhengyu  

Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100730, China

Corresponding author: CHEN Y, E-mail: bjchenyu@126.com

Conflicts of interest   None.

Received  2025-06-23
Accepted  2025-08-22
DOI: 10.12015/issn.1674-8034.2025.09.010
Cite this article as: WANG T J, WANG Y, CHEN Y, et al. Application value of deep learning-based accelerated T1WI and T2WI sequences in head and neck tumors[J]. Chin J Magn Reson Imaging, 2025, 16(9): 60-65. DOI:10.12015/issn.1674-8034.2025.09.010.

[1]
BRAY F, FERLAY J, SOERJOMATARAM I, et al. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2018, 68(6): 394-424. DOI: 10.3322/caac.21492.
[2]
SUNG H, FERLAY J, SIEGEL R L, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA A Cancer J Clin, 2021, 71(3): 209-249. DOI: 10.3322/caac.21660.
[3]
KITAMURA N, SENTO S, YOSHIZAWA Y, et al. Current trends and future prospects of molecular targeted therapy in head and neck squamous cell carcinoma[J/OL]. Int J Mol Sci, 2020, 22(1): 240 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/33383632/. DOI: 10.3390/ijms22010240.
[4]
YOO M C, SOH Y, CHON J, et al. Evaluation of factors associated with favorable outcomes in adults with bell palsy[J]. JAMA Otolaryngol Head Neck Surg, 2020, 146(3): 256-263. DOI: 10.1001/jamaoto.2019.4312.
[5]
CHEN W Q, ZHENG R S, ZHANG S W, et al. Cancer incidence and mortality in China, 2013[J/OL]. Cancer Lett, 2017, 401: 63-71 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/28476483/. DOI: 10.1016/j.canlet.2017.04.024.
[6]
LEI B M, LI Z, XIE C N, et al. Evidence summary for strategies to promote swallowing function in patients with head and neck tumors[J]. Chin J Nurs, 2023, 58(1): 85-91. DOI: 10.3761/j.issn.0254-1769.2023.01.012.
[7]
ROMERO A, LYNCH D, JOHNSON E, et al. MRI order appropriateness for chronic neck pain: Comparison of ordering practices and treatment outcomes for primary care physicians and specialists[J]. J Orthop Res, 2024, 42(2): 425-433. DOI: 10.1002/jor.25669.
[8]
DONG W X, VOLK A, DJAROUM M, et al. Influence of different measurement methods of arterial input function on quantitative dynamic contrast-enhanced MRI parameters in head and neck cancer[J]. J Magn Reson Imag, 2023, 58(1): 122-132. DOI: 10.1002/jmri.28486.
[9]
CHEN W, XU H M, ZHANG L N, et al. The value of MRI in the diagnosis of pediatric head and neck lymphatic malformations: a study of 46 surgical cases[J/OL]. Eur J Radiol, 2024, 170: 111260 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/38086161/. DOI: 10.1016/j.ejrad.2023.111260.
[10]
KANG T S, LIN L J, WU J, et al. Feasibility of a novel MR angiography sequence based on mDixon for cervical artery imaging[J]. Chin J Med Imag Technol, 2023, 39(4): 592-596. DOI: 10.13929/j.issn.1003-3289.2023.04.024.
[11]
LI M L, LIN Q Q, LIU Y T, et al. The clinical value of head-neck joint high-resolution vessel wall imaging in ischemic stroke[J/OL]. J Stroke Cerebrovasc Dis, 2020, 29(9): 105062 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/32807467/. DOI: 10.1016/j.jstrokecerebrovasdis.2020.105062.
[12]
FUJIMA N, SHIMIZU Y, IKEBE Y, et al. Dual-type deep learning-based image reconstruction for advanced denoising and super-resolution processing in head and neck T2-weighted imaging[J]. Jpn J Radiol, 2025, 43(7): 1097-1105. DOI: 10.1007/s11604-025-01756-y.
[13]
SU T, CHEN Y, ZHANG Z H, et al. Optimization of simultaneous multislice, readout-segmented echo planar imaging for accelerated diffusion-weighted imaging of the head and neck: a preliminary study[J/OL]. Acad Radiol, 2020, 27(11): e245-e253 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/32005557/. DOI: 10.1016/j.acra.2019.12.008.
[14]
SARTORETTI E, SARTORETTI-SCHEFER S, VAN SMOORENBURG L, et al. Contrast-enhanced T1-weighted head and neck MRI: prospective intraindividual image quality comparison of spiral GRE, Cartesian GRE, and Cartesian TSE sequences[J]. AJR Am J Roentgenol, 2022, 218(1): 132-139. DOI: 10.2214/AJR.21.26413.
[15]
KATAOKA M, UEDA H, KOYAMA T, et al. Contrast-enhanced volumetric interpolated breath-hold examination compared with spin-echo T1-weighted imaging of head and neck tumors[J]. AJR Am J Roentgenol, 2005, 184(1): 313-319. DOI: 10.2214/ajr.184.1.01840313.
[16]
KATO H, KAWAGUCHI M, ANDO T, et al. Hypointense head and neck lesions on T2-weighted images: correlation with histopathologic findings[J]. Neuroradiology, 2020, 62(10): 1207-1217. DOI: 10.1007/s00234-020-02483-z.
[17]
KORTE J C, HARDCASTLE N, NG S P, et al. Cascaded deep learning-based auto-segmentation for head and neck cancer patients: Organs at risk on T2-weighted magnetic resonance imaging[J]. Med Phys, 2021, 48(12): 7757-7772. DOI: 10.1002/mp.15290.
[18]
BISCHOFF L M, PEETERS J M, WEINHOLD L, et al. Deep learning super-resolution reconstruction for fast and motion-robust T2-weighted prostate MRI[J/OL]. Radiology, 2023, 308(3): e230427 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/37750774/. DOI: 10.1148/radiol.230427.
[19]
PONSIGLIONE A, MCGUIRE W, PETRALIA G, et al. Image quality of whole-body diffusion MR images comparing deep-learning accelerated and conventional sequences[J]. Eur Radiol, 2024, 34(12): 7985-7993. DOI: 10.1007/s00330-024-10883-5.
[20]
SLAVKOVA K P, DICARLO J C, WADHWA V, et al. An untrained deep learning method for reconstructing dynamic MR images from accelerated model-based data[J]. Magn Reson Med, 2023, 89(4): 1617-1633. DOI: 10.1002/mrm.29547.
[21]
KIM J, NICKEL M D, KNOLL F. Deep learning-based accelerated MR cholangiopancreatography without fully-sampled data[J/OL]. NMR Biomed, 2025, 38(3): e70002 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/39907193/. DOI: 10.1002/nbm.70002.
[22]
ALTMANN S, GRAUHAN N F, BROCKSTEDT L, et al. Ultrafast brain MRI with deep learning reconstruction for suspected acute ischemic stroke[J/OL]. Radiology, 2024, 310(2): e231938 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/38376403/. DOI: 10.1148/radiol.231938.
[23]
XIE Y X, TAO H Y, LI X W, et al. Prospective comparison of standard and deep learning-reconstructed turbo spin-echo MRI of the shoulder[J/OL]. Radiology, 2024, 310(1): e231405 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/38193842/. DOI: 10.1148/radiol.231405.
[24]
HERRMANN J, KELLER G, GASSENMAIER S, et al. Feasibility of an accelerated 2D-multi-contrast knee MRI protocol using deep-learning image reconstruction: a prospective intraindividual comparison with a standard MRI protocol[J]. Eur Radiol, 2022, 32(9): 6215-6229. DOI: 10.1007/s00330-022-08753-z.
[25]
RECHT M P, ZBONTAR J, SODICKSON D K, et al. Using deep learning to accelerate knee MRI at 3 T: results of an interchangeability study[J]. AJR Am J Roentgenol, 2020, 215(6): 1421-1429. DOI: 10.2214/AJR.20.23313.
[26]
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 (Basel), 2021, 13(14): 3593 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/34298806/. DOI: 10.3390/cancers13143593.
[27]
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 (NY), 2023, 48(1): 282-290. DOI: 10.1007/s00261-022-03687-y.
[28]
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.
[29]
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 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/36318032/. DOI: 10.1148/radiol.212922.
[30]
HERRMANN J, BENKERT T, BRENDLIN A, et al. Shortening acquisition time and improving image quality for pelvic MRI using deep learning reconstruction for diffusion-weighted imaging at 1.5 T[J]. Acad Radiol, 2024, 31(3): 921-928. DOI: 10.1016/j.acra.2023.06.035.
[31]
ESTLER A, HAUSER T K, BRUNNÉE M, et al. Deep learning-accelerated image reconstruction in back pain-MRI imaging: reduction of acquisition time and improvement of image quality[J]. Radiol Med, 2024, 129(3): 478-487. DOI: 10.1007/s11547-024-01787-x.
[32]
NEPAL P, BAGGA B, FENG L, et al. Respiratory motion management in abdominal MRI: Radiology in training[J]. Radiology, 2023, 306(1): 47-53. DOI: 10.1148/radiol.220448.
[33]
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 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/36648347/. DOI: 10.1148/radiol.220425.
[34]
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.
[35]
LI Q G, YIN Y Y, ZHAO C, et al. Application of deep learning in intravoxel incoherent motion brain magnetic resonance imaging quality[J]. Chin J Magn Reson Imag, 2023, 14(5): 16-20. DOI: 10.12015/issn.1674-8034.2023.05.004.
[36]
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.
[37]
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.

PREV The value of MRI histogram analysis in predicting the long-term therapeutic effect after surgery for growth hormone-secreting pituitary neuroendocrine tumors
NEXT Biventricular strain in dilated cardiomyopathy: A comparative study between heart failure with mildly reduced ejection fraction and heart failure with preserved ejection fraction
  


LINK


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