基于深度学习去噪重建改善肌肉骨骼磁共振成像的分辨率和图像质量:一项前瞻性临床研究
前瞻性纳入40例肌肉骨骼MRI患者的137个对比加权序列,每个序列分别用常规参数和常规重建滤波(REF)与更高分辨率和深度学习去噪重建(DLR)及三种常规重建滤波(NL2、GA43、GA53)重建。DLR较REF分辨率改善47.61%(0.39±0.15 mm² vs 0.20±0.06 mm²,p<0.001),平均扫描时间缩短7.93%(165.58±21.86 s vs 152.45±25.65 s,p<0.001),所有图像质量评分及强制排序均显著更高(p<0.001)。
要点
- DLR较常规REF分辨率改善47.61%(0.39±0.15 mm² vs 0.20±0.06 mm²,p<0.001)。
- DLR较REF平均扫描时间缩短7.93%(165.58±21.86 s vs 152.45±25.65 s,p<0.001)。
- DLR在所有图像质量标准及强制排序中评分均显著高于REF、NL2、GA43和GA53(p<0.001)。
核心结论
- 这项前瞻性临床评估显示,与标准诊疗图像相比,DLR可获得约两倍更精细的分辨率并改善图像质量。
研究设计与样本
- 前瞻性临床研究,纳入40例肌肉骨骼MRI患者,共评估137个对比加权序列。
- 每个序列均扫描两次:第一次用常规参数并以常规重建滤波(REF)重建,第二次用更高分辨率并以DLR及三种常规重建滤波(NL2、GA43、GA53)重建。
- 五种重建图像(REF、DLR、NL2、GA43、GA53)去标识化、随机化后由三名肌肉骨骼放射科医生采用八项评分标准和强制排序进行盲法阅片。
- 定量测量SNR、CNR及用于分辨率评估的结构半高全宽(FWHM),并采用广义估计方程(GEE)结合Bonferroni校正比较DLR与NL2、GA43、GA53及REF的读者评分、SNR、CNR和FWHM。
诊断标准与关键数值
- 与常规REF图像相比,DLR分辨率改善47.61%,从0.39±0.15 mm²降至0.20±0.06 mm²(p<0.001)。
- 与REF相比,DLR平均每序列扫描时间缩短7.93%,从165.58±21.86 s降至152.45±25.65 s(p<0.001)。
- 基于平均评分,DLR图像在所有图像质量标准及强制排序中评分均显著更高(p<0.001)。
局限性
- 原文未报告局限性。
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 prospectively evaluate a deep learning-based denoising reconstruction (DLR) for improved resolution and image quality in musculoskeletal (MSK) magnetic resonance imaging (MRI).
METHODS: Images from 137 contrast-weighted sequences in 40 MSK patients were evaluated. Each sequence was performed twice, first with the routine parameters and reconstructed with a routine reconstruction filter (REF), then with higher resolution and reconstructed with DLR, and with three conventional reconstruction filters (NL2, GA43, GA53). The five reconstructions (REF, DLR, NL2, GA43, and GA53) were de-identified, randomized, and blindly reviewed by three MSK radiologists using eight scoring criteria and a forced ranking. Quantitative SNR, CNR, and structure's full width at half maximum (FWHM) for resolution assessment were measured and compared. To account for repeated measures, Generalized Estimating Equations (GEE) with Bonferroni adjustment was used to compare the reader's scores, SNR, CNR, and FWHM between DLR vs. NL2, GA43, GA53, and REF.
RESULTS: Compared to the routine REF images, the resolution was improved by 47.61% with DLR from 0.39 ± 0.15 mm2 to 0.20 ± 0.06 mm2 (p < 0.001). Per-sequence average scan time was shortened by 7.93% with DLR from 165.58 ± 21.86 s to 152.45 ± 25.65 s (p < 0.001). Based on the average scores, DLR images were rated significantly higher in all image quality criteria and the forced ranking (p < 0.001).
CONCLUSION: This prospective clinical evaluation demonstrated that DLR allows approximately two times finer resolution and improved image quality compared to the standard-of-care images.
引用
- Do HP, Lockard CA, Berkeley D, et al. Improved Resolution and Image Quality of Musculoskeletal Magnetic Resonance Imaging using Deep Learning-based Denoising Reconstruction: A Prospective Clinical Study. Skeletal Radiol. 2024. PMID: 38653786. doi:10.1007/s00256-024-04679-3
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。