Share：
Share this content in WeChat
X
[Chinese] [PDF] 48 3
• Clinical Article •
The value of deep learning reconstruction combined with small field-of-view high-resolution scanning in improving the quality of finger magnetic resonance images
LU Aqin  XU Lulu  XU Lei  HAO Shaowei  ZOU Yuefen 

Cite this article as: LU A Q, XU L L, XU L, et al. The value of deep learning reconstruction combined with small field-of-view high-resolution scanning in improving the quality of finger magnetic resonance images[J]. Chin J Magn Reson Imaging, 2025, 16(7): 52-57. DOI:10.12015/issn.1674-8034.2025.07.008.


[Abstract] Objective To explore the value of small field-of-view (sFOV) high-resolution scanning based on deep-learning reconstruction (DLR) algorithm in improving the imaging quality of finger magnetic resonance imaging (MRI).Materials and Methods Thirty-three healthy volunteers and 24 patients with hand diseases were prospectively recruited. Both the small field-of-view high-resolution T2-weighted spin-echo sequence (TSE-sFOV) and DLR combined with TSE-sFOV (TSEDL-sFOV), were conducted on the subjects. A 4-point scale was used to subjectively evaluate the overall image quality (based on image contrast, edge sharpness, noise and artifact) and the clarity of anatomical structures (including bone, articular cartilage, tendon and ligament) in the two sets of images from 57 samples; Additionally, The lesion display (including lesion contrast and edge sharpness, lesion location and internal morphology) and diagnostic confidence were scored for 24 samples. The disease detection capabilities (including bone changes, joint space changes, tendon abnormalities, and soft tissue abnormalities) of the two groups of images from 57 samples were assessed as either 0 or 1. The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of the two sets of images were compared.Results In the subjective evaluation, the TSEDL-sFOV group of images scored higher than the TSE-sFOV in overall image quality, bone and articular cartilage (P < 0.05), while there was no statistical difference in tendon and ligament scores. For lesion display and diagnostic confidence in the 24 samples, the TSEDL-sFOV group of images scored higher than the TSE-sFOV group, with statistical difference (P < 0.05). In terms of disease detection capabilities, there was no statistical difference between the two groups of images (P > 0.05), and the consistency between the two sets of images was excellent (Kappa > 0.84). In the objective evaluation, the SNR and CNR of the TSEDL-sFOV group of images were higher than those of the TSE-sFOV group (P < 0.05).Conclusions DLR combined with sFOV finger MRI can reduce the noise and improve the image quality under the premise of shortening scanning time. This provides more precise images for clinic.
[Keywords] finger；magnetic resonance imaging；deep learning；high resolution；image quality

LU Aqin1   XU Lulu1   XU Lei1   HAO Shaowei2   ZOU Yuefen1*  

1 Department of Radiology, the First Affiliated Hospital of Nanjing Medical University, Nanjing 210029, China

2 Siemens Healthineers Digital Technology (Shanghai) Co., Ltd., Shanghai 200000, China

Corresponding author: ZOU Y F, E-mail: zou_yf@163.com

Conflicts of interest   None.

Received  2025-03-19
Accepted  2025-07-07
DOI: 10.12015/issn.1674-8034.2025.07.008
Cite this article as: LU A Q, XU L L, XU L, et al. The value of deep learning reconstruction combined with small field-of-view high-resolution scanning in improving the quality of finger magnetic resonance images[J]. Chin J Magn Reson Imaging, 2025, 16(7): 52-57. DOI:10.12015/issn.1674-8034.2025.07.008.

[1]
HASHEM A, KALAAWY B AL. The feasibility of high-resolution ultrasonography and MRI in diagnosing finger lesions[J]. J Ultrasound, 2022, 25(2): 133-144. DOI: 10.1007/s40477-021-00593-9.
[2]
RATASVUORI M S, LINDFORS N C, SORMAALA M J. The clinical significance of magnetic resonance imaging of the hand: an analysis of 318 hand and wrist images referred by hand surgeons[J]. J Plast Surg Hand Surg, 2022, 56(2): 69-73. DOI: 10.1080/2000656X.2021.1933993.
[3]
KIJOWSKI R, GOLD G E. Routine 3D magnetic resonance imaging of joints[J]. J Magn Reson Imaging, 2011, 33(4): 758-771. DOI: 10.1002/jmri.22342.
[4]
SCHREIBMAN K L, FREELAND A, GILULA L A, et al. Imaging of the hand and wrist[J]. Orthop Clin N Am, 1997, 28(4): 537-582. DOI: 10.1016/S0030-5898(05)70308-4.
[5]
SCHMITT R, HESSE N, GRUNZ J P. Tendons and tendon sheaths of the hand-an update on MRI[J]. Rofo, 2022, 194(12): 1307-1321. DOI: 10.1055/a-1826-1007.
[6]
PETCHPRAPA C N, VASWANI D. MRI of the fingers: an update[J]. Am J Roentgenol, 2019, 213(3): 534-548. DOI: 10.2214/ajr.19.21217.
[7]
ZBOJNIEWICZ A M. MRI anatomy and injuries of the fingers[J]. Pediatr Radiol, 2023, 53(8): 1562-1575. DOI: 10.1007/s00247-023-05624-7.
[8]
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.
[9]
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]
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.
[11]
LIU J, LI W, LI Z Y, et al. Magnetic resonance shoulder imaging using deep learning-based algorithm[J]. Eur Radiol, 2023, 33(7): 4864-4874. DOI: 10.1007/s00330-023-09470-x.
[12]
MICHAELY H J, ARINGHIERI G, CIONI D, et al. Current value of biparametric prostate MRI with machine-learning or deep-learning in the detection, grading, and characterization of prostate cancer: a systematic review[J]. Diagnostics (Basel), 2022, 12(4): 799 [2025-03-15]. https://pmc.ncbi.nlm.nih.gov/articles/PMC9027206/. DOI: 10.3390/diagnostics12040799.
[13]
DO W J, SEO S, HAN Y, et al. Reconstruction of multicontrast MR images through deep learning[J]. Med Phys, 2020, 47(3): 983-997. DOI: 10.1002/mp.14006.
[14]
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.
[15]
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.
[16]
MAN C, LAU V, SU S, et al. Deep learning enabled fast 3D brain MRI at 0.055 tesla[J/OL]. Sci Adv, 2023, 9(38): eadi9327 [2025-03-15]. https://pmc.ncbi.nlm.nih.gov/articles/PMC10516503/. DOI: 10.1126/sciadv.adi9327.
[17]
RUDIE J D, GLEASON T, BARKOVICH M J, et al. Clinical assessment of deep learning-based super-resolution for 3D volumetric brain MRI[J/OL]. Radiol Artif Intell, 2022, 4(2): e210059 [2025-03-15]. https://pmc.ncbi.nlm.nih.gov/articles/PMC8980882/. DOI: 10.1148/ryai.210059.
[18]
CHOI Y, KO J S, PARK J E, et al. Beyond the conventional structural MRI: clinical application of deep learning image reconstruction and synthetic MRI of the brain[J]. Invest Radiol, 2025, 60(1): 27-42. DOI: 10.1097/RLI.0000000000001114.
[19]
WILPERT C, NEUBAUER C, RAU A, et al. Accelerated diffusion-weighted imaging in 3 T breast MRI using a deep learning reconstruction algorithm with superresolution processing: a prospective comparative study[J]. Invest Radiol, 2023, 58(12): 842-852. DOI: 10.1097/RLI.0000000000000997.
[20]
HAHN S, YI J, LEE H J, et al. Image quality and diagnostic performance of accelerated shoulder MRI with deep learning-based reconstruction[J]. AJR Am J Roentgenol, 2022, 218(3): 506-516. DOI: 10.2214/AJR.21.26577.
[21]
KOCH K M, SHERAFATI M, ARPINAR V E, et al. Analysis and evaluation of a deep learning reconstruction approach with denoising for orthopedic MRI[J/OL]. Radiol Artif Intell, 2021, 3(6): e200278 [2024-11-07]. https://pmc.ncbi.nlm.nih.gov/articles/PMC8637471/. DOI: 10.1148/ryai.2021200278.
[22]
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.
[23]
YASAKA K, TANISHIMA T, OHTAKE Y, et al. Deep learning reconstruction for 1.5 T cervical spine MRI: effect on interobserver agreement in the evaluation of degenerative changes[J]. Eur Radiol, 2022, 32(9): 6118-6125. DOI: 10.1007/s00330-022-08729-z.
[24]
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 [2025-01-13]. https://pmc.ncbi.nlm.nih.gov/articles/PMC10102623/. DOI: 10.1148/radiol.220425.
[25]
HALLINAN J T P D. Deep learning for spine MRI: reducing time not quality[J/OL]. Radiology, 2023, 306(3): e222410 [2025-01-13]. https://pubs.rsna.org/doi/10.1148/radiol.222410. DOI: 10.1148/radiol.222410.
[26]
HERRMANN J, KOERZDOERFER G, NICKEL D, et al. Feasibility and implementation of a deep learning MR reconstruction for TSE sequences in musculoskeletal imaging[J/OL]. Diagnostics (Basel), 2021, 11(8): 1484 [2024-12-12]. https://pmc.ncbi.nlm.nih.gov/articles/PMC8394583/. DOI: 10.3390/diagnostics11081484.
[27]
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.
[28]
LIU M L, DENG X J, ZHANG J, et al. Image quality assessment of SMS-RESOLVE diffusion weighted imaging in cervical cancer[J]. J Clin Radiol, 2022, 41(4): 729-735. DOI: 10.13437/j.cnki.jcr.2022.04.030.
[29]
HOU B W, LI Y T, XIONG Y, et al. Comparison of caipirinha-accelerated 3d fat-saturated-space MRI with 2d MRI sequences for the assessment of shoulder pathology[J]. Eur Radiol, 2022, 32(1): 593-601. DOI: 10.1007/s00330-021-08183-3.
[30]
YARACH U, CHATNUNTAWECH I, SETSOMPOP K, et al. Improved reconstruction for highly accelerated propeller diffusion 1.5 T clinical MRI[J]. Magn Reson Mater Phys Biol Med, 2024, 37(2): 283-294. DOI: 10.1007/s10334-023-01142-7.
[31]
KIRYU S, AKAI H, YASAKA K, et al. Clinical impact of deep learning reconstruction in MRI[J/OL]. Radiographics, 2023, 43(6): e220133 [2025-03-12]. https://pubs.rsna.org/doi/10.1148/rg.220133. DOI: 10.1148/rg.220133.
[32]
QIU D F, ZHANG S X, LIU Y, et al. Super-resolution reconstruction of knee magnetic resonance imaging based on deep learning[J/OL]. Comput Meth Programs Biomed, 2020, 187: 105059 [2025-01-16]. https://www.sciencedirect.com/science/article/abs/pii/S0169260719312416. DOI: 10.1016/j.cmpb.2019.105059.
[33]
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.
[34]
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.
[35]
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.
[36]
LIU Z J, WEN B H, WANG Z Y, et al. Deep learning-based reconstruction enhances image quality and improves diagnosis in magnetic resonance imaging of the shoulder joint[J]. Quant Imaging Med Surg, 2024, 14(4): 2840-2856. DOI: 10.21037/qims-23-1412.

PREV Clinical utility of cinematic volume rendering technique in lumbosacral plexus nerve sheath tumors: A comparative study with maximum intensity projection
NEXT The feasibility study of quantitative assessment of lumbar paravertebral muscles by synthetic magnetic resonance technique
  


LINK


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