深度学习重建实现约一分钟三维T1加权MRI:加速与图像质量权衡及运动伪影减少的定量评估
研究在6名健康志愿者中用3D MPRAGE评估2至16倍加速的深度学习重建,并在40例临床队列中比较11倍加速DL-Speed(1分10秒)与常规成像(4分59秒)。结果显示DL-Speed显著降低头动(TVC 52.3±9.4 mm vs. 140.4±32.8 mm,p<0.001),图像质量可接受,皮质厚度与灰质体积下降近线性,数据支持6至11倍加速的实用工作范围。
要点
- DL-Speed 11倍加速将3D T1加权成像采集时间从4分59秒缩短至1分10秒,同时显著降低头动。
- 加速倍数增加时图像质量评分呈二次趋势,全局皮质厚度和总灰质体积则近线性下降,需权衡选择加速倍数。
- 临床队列中DL-Speed与常规图像在皮质厚度(r=0.97)和灰质体积(r=0.99)上显著相关。
核心结论
- DL-Speed可实现约一分钟的3D T1加权成像,在明显减少头动的同时保持适合形态学定量分析的图像完整性;由于图像质量评分呈非线性(二次)依赖而皮质厚度和灰质体积近线性下降,数据支持6至11倍加速的实用工作范围而非单一最佳加速倍数。
研究设计与样本
- 研究纳入6名健康志愿者进行3D MPRAGE扫描,加速倍数范围为2至16;另在40例临床患者队列中比较11倍加速DL-Speed(1分10秒)与常规成像(4分59秒),以CAT12图像质量评分和形态学测量为参考。
诊断标准与关键数值
- 健康志愿者中所有加速级别图像质量均保持在CAT12 Rank A,IQR随加速倍数呈二次趋势(R²=0.98)。
- 全局皮质厚度随加速近似线性下降:DLS2至DLS11为-0.068 mm(-2.8%),DLS2至DLS16为-0.140 mm(-5.7%)。
- 总灰质体积呈浅度单调下降:组均值DLS2为748.8 mL,DLS11为729.5 mL(-2.6%),DLS16为726.3 mL(-3.0%)。
- 临床队列中IQR为DL-Speed 93.9±1.0% vs. 常规94.8±1.2%(p<0.001),Bland-Altman一致性界限为-2.49%至+0.75%。
- 常规图像与DL-Speed的皮质厚度相关系数r=0.97,灰质体积r=0.99(均p<0.001)。
临床应用与阅片要点
- 临床阅片及形态学定量分析中可采用6至11倍加速的DL-Speed方案,以在约一分钟采集时间内获得可接受的图像质量和定量完整性。
- 头动定量显示DL-Speed的TVC为52.3±9.4 mm,常规成像为140.4±32.8 mm(p<0.001),DL-Speed较常规成像降低头动。
- 加速倍数超过11倍时全局皮质厚度和总灰质体积进一步下降,需在图像质量与定量准确性之间权衡选择加速倍数。
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
PURPOSE: Deep learning-based reconstruction techniques, such as the prototype DL-Speed, have been developed to accelerate 3D T1-weighted imaging, but their clinical utility and impact on quantitative analysis have not been systematically validated. The purpose of this study is to evaluate the utility of a deep learning-based reconstruction method for substantially accelerating image acquisition without compromising quantitative image quality and morphometry.
METHODS: Six healthy volunteers were scanned with 3D MPRAGE using acceleration factors ranging from 2 to 16. Image quality was assessed using the CAT12 Image Quality Rating (IQR), and morphometry with CAT12 global cortical thickness and total gray matter (GM) volume. In a clinical cohort of 40 patients, DL-Speed with 11-fold acceleration (1 min 10 s) was compared to conventional imaging (4 min 59 s). Head motion was quantified via total vector change (TVC) using volumetric navigators.
RESULTS: In healthy volunteers, image quality remained within CAT12 Rank A at all acceleration levels; IQR followed a quadratic trend (R² = 0.98). Global cortical thickness decreased approximately linearly with acceleration (e.g., DLS2→DLS11: -0.068 mm [- 2.8%]; DLS2→DLS16: -0.140 mm [- 5.7%]). Total GM volume showed a shallow, monotonic decline (group means: 748.8 mL at DLS2 → 729.5 mL at DLS11 [- 2.6%] → 726.3 mL at DLS16 [- 3.0%]). In clinical cohort, DL-Speed significantly reduced head motion (TVC: 52.3 ± 9.4 mm vs. 140.4 ± 32.8 mm, p < 0.001) while maintaining acceptable image quality (IQR: 93.9 ± 1.0% vs. 94.8 ± 1.2%, p < 0.001). Bland-Altman analysis showed narrow limits of agreement (-2.49% to + 0.75%). Regarding cortical thickness and GM volume, we found significant correlations between conventional images and DL-Speed (thickness r = 0.97; GM r = 0.99; both p < 0.001).
CONCLUSION: DL-Speed enables about-one-minute 3D T1-weighted imaging that markedly reduces motion while preserving quantitative image integrity suitable for morphometry. Because image quality (IQR) follows a non-linear (quadratic) dependency whereas cortical thickness and GM volume decline nearly linearly, the data support a practical operating range (e.g., 6-11-fold acceleration) rather than a single optimal factor.
TRIAL REGISTRATION: Not applicable.
引用
- Watanabe K, Oyu K, Kasai S, et al. Deep-learning reconstruction enables about one minute 3D T1-weighted MRI: quantitative evaluation of Acceleration-quality Trade-offs and motion reduction. Neuroradiology. 2025. PMID: 41273361. doi:10.1007/s00234-025-03846-0
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。