Clinical efficacy of motion-insensitive imaging technique with deep learning reconstruction to improve image quality in cervical spine MR imaging

You Seon Song; In Sook Lee; Moonjung Hwang; Kyoungeun Jang; Xinzeng Wang; Maggie Fung

doi:10.1093/bjr/tqae026

Clinical efficacy of motion-insensitive imaging technique with deep learning reconstruction to improve image quality in cervical spine MR imaging

Br J Radiol. 2024 Mar 28;97(1156):812-819. doi: 10.1093/bjr/tqae026.

Authors

You Seon Song^{1

2}, In Sook Lee^{1

2}, Moonjung Hwang³, Kyoungeun Jang⁴, Xinzeng Wang⁵, Maggie Fung⁶

Affiliations

¹ Pusan National University School of Medicine, Busan, Korea.
² Department of Radiology, Pusan National University Hospital, Biomedical Research Institute, Busan 49241, Korea.
³ GE Healthcare, 15F Seoul Square 416, Seoul, Seoul 04367, Korea.
⁴ AIRS Medical, 13-14F, Keungil Tower, Seoul, Seoul 06142, Korea.
⁵ GE Healthcare, MR Clinical Solutions & Research Collaborations, Houston, Texas 77081, United States.
⁶ GE Healthcare, MR Clinical Solutions & Research Collaborations, New York, NY 10032, United States.

PMID: 38366622
PMCID: PMC11027290 (available on 2025-02-15)
DOI: 10.1093/bjr/tqae026

Abstract

Objective: To demonstrate that a T2 periodically rotated overlapping parallel lines with enhanced reconstruction (PROPELLER) technique using deep learning reconstruction (DLR) will provide better image quality and decrease image noise.

Methods: From December 2020 to March 2021, 35 patients examined cervical spine MRI were included in this study. Four sets of images including fast spin echo (FSE), original PROPELLER, PROPELLER DLR50%, and DLR75% were quantitatively and qualitatively reviewed. We calculated the signal-to-noise ratio (SNR) of the spinal cord and sternocleidomastoid (SCM) muscle and the contrast-to-noise ratio (CNR) of the spinal cord by applying region-of-interest at the spinal cord, SCM muscle, and background air. We evaluated image noise with regard to the spinal cord, SCM, and back muscles at each level from C2-3 to C6-7 in the 4 sets.

Results: At all disc levels, the mean SNR values for the spinal cord and SCM muscles were significantly higher in PROPELLER DLR50% and DLR75% compared to FSE and original PROPELLER images (P < .0083). The mean CNR values of the spinal cord were significantly higher in PROPELLER DLR50% and DLR75% compared to FSE at the C3-4 and 4-5 levels and PROPELLER DLR75% compared to FSE at the C6-7 level (P < .0083). Qualitative analysis of image noise on the spinal cord, SCM, and back muscles showed that PROPELLER DLR50% and PROPELLER DLR75% images showed a significant denoising effect compared to the FSE and original PROPELLER images.

Conclusion: The combination of PROPELLER and DLR improved image quality with a high SNR and CNR and reduced noise.

Advances in knowledge: Motion-insensitive imaging technique (PROPELLER) increased the image quality compared to conventional FSE images. PROPELLER technique with a DLR reduced image noise and improved image quality.

Keywords: PROPELLER; deep learning reconstruction; magnetic resonance imaging; noise reduction.

MeSH terms

Artifacts
Cervical Vertebrae / diagnostic imaging
Deep Learning*
Humans
Image Enhancement / methods
Magnetic Resonance Imaging / methods
Treatment Outcome