深度学习重建PROPELLER肩部MRI与常规重建的对比研究
该研究纳入了100例肩部MRI扫描,比较常规与加速PROPELLER序列分别结合常规重建(CR)和深度学习重建(DLR)的图像质量与观察者间一致性。结果显示,常规序列结合DLR的信噪比最高,且DLR序列的主观图像质量优于常规CR序列,对肩部病变的观察者间一致性达显著至几乎完美水平,加速序列结合DLR在缩短扫描时间45%的情况下仍能保持与常规CR相当的诊断一致性。
要点
- DLR可显著提升肩部PROPELLER MRI的信噪比和主观图像质量。
- 加速PROPELLER联合DLR可将扫描时间从8分钟缩短至4分24秒(减少45%)。
- DLR加速序列对肩部病变的观察者间一致性与常规CR序列相当。
关键影像表现/征象
- 常规序列联合DLR的信噪比最高,其次为加速序列联合DLR、常规序列联合CR、加速序列联合CR(P < .001)。
- 两名阅片者均评价常规序列联合DLR(P = .003和P < .001)及加速序列联合DLR(P = .016和P < .001)的图像质量优于常规序列联合CR。
- 不同图像集间检测肩部异常的观察者间一致性为显著至几乎完美(κ = 0.600-0.884),图像集之间的一致性也为显著至几乎完美(κ = 0.691-1)。
诊断标准与关键数值
- 以常规PROPELLER序列联合CR为参考标准,比较各图像集的图像质量和观察者间一致性。
- 图像质量主观评价和一致性分析采用加权/非加权kappa统计,观察者间一致性κ值为0.600-0.884,图像集间一致性κ值为0.691-1。
临床应用与阅片要点
- 在日常肩部MRI中,可考虑使用加速PROPELLER联合DLR以缩短扫描时间并维持或提升图像质量。
- DLR重建有助于提高信噪比,可能对显示细微肩部结构病变有利,但需注意与常规CR图像的一致性以保持诊断信心。
局限性
- 仅纳入接受3T MRI检查的患者,结果能否推广至其他场强设备尚不明确。
- 参考标准为常规PROPELLER联合CR,而非手术或临床最终诊断。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVE: To compare the image quality and agreement among conventional and accelerated periodically rotated overlapping parallel lines with enhanced reconstruction (PROPELLER) MRI with both conventional reconstruction (CR) and deep learning-based reconstruction (DLR) methods for evaluation of shoulder.
MATERIALS AND METHODS: We included patients who underwent conventional (acquisition time, 8 min) and accelerated (acquisition time, 4 min and 24 s; 45% reduction) PROPELLER shoulder MRI using both CR and DLR methods between February 2021 and February 2022 on a 3 T MRI system. Quantitative evaluation was performed by calculating the signal-to-noise ratio (SNR). Two musculoskeletal radiologists compared the image quality using conventional sequence with CR as the reference standard. Interobserver agreement between image sets for evaluating shoulder was analyzed using weighted/unweighted kappa statistics.
RESULTS: Ninety-two patients with 100 shoulder MRI scans were included. Conventional sequence with DLR had the highest SNR (P < .001), followed by accelerated sequence with DLR, conventional sequence with CR, and accelerated sequence with CR. Comparison of image quality by both readers revealed that conventional sequence with DLR (P = .003 and P < .001) and accelerated sequence with DLR (P = .016 and P < .001) had better image quality than the conventional sequence with CR. Interobserver agreement was substantial to almost perfect for detecting shoulder abnormalities (κ = 0.600-0.884). Agreement between the image sets was substantial to almost perfect (κ = 0.691-1).
CONCLUSION: Accelerated PROPELLER with DLR showed even better image quality than conventional PROPELLER with CR and interobserver agreement for shoulder pathologies comparable to that of conventional PROPELLER with CR, despite the shorter scan time.
引用
- Hahn, Yi, Lee, et al. Comparison of deep learning-based reconstruction of PROPELLER Shoulder MRI with conventional reconstruction. Skeletal Radiol. 2023. PMID: 36943429. doi:10.1007/s00256-023-04321-8
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。