Conversion of T2-Weighted Magnetic Resonance Images of Cervical Spine Trauma to Short T1 Inversion Recovery (STIR) Images by Generative Adversarial Network

被引：0

作者：

Yunde, Atsushi ^{[1
]}

Maki, Satoshi ^{[1
]}

Furuya, Takeo ^{[1
]}

Okimatsu, Sho ^{[1
]}

Inoue, Takaki ^{[1
]}

Miura, Masataka ^{[1
]}

Shiratani, Yuki ^{[1
]}

Nagashima, Yuki ^{[1
]}

Maruyama, Juntaro ^{[1
]}

Shiga, Yasuhiro ^{[1
]}

Inage, Kazuhide ^{[1
]}

Eguchi, Yawara ^{[1
]}

Orita, Sumihisa ^{[1
]}

Ohtori, Seiji ^{[1
]}

机构：

[1] Chiba Univ, Grad Sch Med, Dept Orthopaed Surg, Chiba, Japan

来源：

CUREUS JOURNAL OF MEDICAL SCIENCE | 2024年 / 16卷 / 05期

关键词：

t2-weighted magnetic resonance images; short t1 inversion recovery; image conversion; generated adversarial network; deep learning; cervical spine trauma; magnetic resonance imaging; INJURY; MRI; CLASSIFICATION; EFFICACY;

D O I：

暂无

中图分类号：

R5 [内科学];

学科分类号：

1002 ; 100201 ;

摘要：

Introduction: The short T1 inversion recovery (STIR) sequence is advantageous for visualizing ligamentous injuries, but the STIR sequence may be missing in some cases. The purpose of this study was to generate synthetic STIR images from MRI T2 -weighted images (T2WI) of patients with cervical spine trauma using a generative adversarial network (GAN). Methods: A total of 969 pairs of T2WI and STIR images were extracted from 79 patients with cervical spine trauma. The synthetic model was trained 100 times, and the performance of the model was evaluated with five -fold cross -validation. Results: As for quantitative validation, the structural similarity score was 0.519 +/- 0.1 and the peak signal-tonoise ratio score was 19.37 +/- 1.9 dB. As for qualitative validation, the incorporation of synthetic STIR images generated by a GAN alongside T2WI substantially enhances sensitivity in the detection of interspinous ligament injuries, outperforming assessments reliant solely on T2WI. Conclusion: The GAN model can generate synthetic STIRs from T2 images of cervical spine trauma using image -to -image conversion techniques. The use of a combination of synthetic STIR images generated by a GAN and T2WI improves sensitivity in detecting interspinous ligament injuries compared to assessments that use only T2WI.

引用

页数：8

共 20 条

[1] Time is spine: a review of translational advances in spinal cord injury [J].