文献速递心血管MR

使用分辨率增强生成对抗内联神经网络的加速心脏MRI电影

Accelerated Cardiac MRI Cine with Use of Resolution Enhancement Generative Adversarial Inline Neural Network.
PubMed 文献 · Radiology · 2023-01-01

本研究开发并评估了一种基于增强超分辨率生成对抗内联神经网络的深度学习模型,可联合并行成像或压缩感知(CS)用于心脏电影成像。模型在1616例患者中训练,并在181名个体中评估;结果显示深度学习与GRAPPA在屏气ECG门控分段电影和自由呼吸实时电影中诊断质量评分相似,且每次屏气获得更多层面(3.1 vs 1,P < .001),左心室功能、容积和应变与GRAPPA一致性极好。

要点

  • 深度学习模型可在减少空间分辨率采集后恢复分辨率,与GRAPPA诊断质量评分相似(2.9 vs 2.9,P = .41)。
  • 屏气ECG门控分段电影中,深度学习每次屏气获得3.1个层面,GRAPPA为1个层面(P < .001)。
  • 自由呼吸实时电影中,深度学习伪影评分低于GRAPPA(3.9 vs 4.3,P < .001)。

核心结论

  • 深度学习加速的心脏电影成像在心脏功能、容积和应变的定量方面与标准化并行成像方法(GRAPPA)准确性相似。

研究设计与样本

  • 研究论文;深度学习模型基于增强超分辨率生成对抗内联神经网络构建,使用回顾性识别的电影图像训练,并在2021年9月至2022年9月前瞻性入组的参与者中评估;训练集1616例患者(平均年龄±标准差,56岁±16;920例男性),评估集181名个体,包括126例患者(平均年龄57岁±16;77例男性)和55名健康受试者(平均年龄27岁±10;15例男性);模型应用于采用GRAPPA或CS以降低空间分辨率采集的屏气ECG门控分段电影和自由呼吸实时电影图像,并与GRAPPA加速电影图像比较;诊断质量和伪影由两名读者使用Likert量表评估,采用Wilcoxon符号秩检验比较;左心室功能、容积和应变的一致性采用Bland-Altman分析评估。

关键影像表现/征象

  • 屏气ECG门控分段电影和自由呼吸实时电影中,深度学习与GRAPPA的诊断质量评分相似(2.9 vs 2.9,P = .41,深度学习 vs GRAPPA)。
  • 屏气ECG门控分段电影中,深度学习与GRAPPA的伪影评分相似(4.4 vs 4.3,P = .55,深度学习 vs GRAPPA)。
  • 自由呼吸实时电影中,深度学习与GRAPPA的诊断质量评分相似(2.9 vs 2.9,P = .21,深度学习 vs GRAPPA),深度学习伪影评分低于GRAPPA(3.9 vs 4.3,P < .001,深度学习 vs GRAPPA)。
  • 两种序列中,深度学习模型对左心室参数与GRAPPA相比显示极好的一致性,平均差异接近零且一致性界限窄。

诊断标准与关键数值

  • 诊断质量和伪影采用Likert量表评估。
  • 深度学习与GRAPPA诊断质量评分:屏气ECG门控分段电影2.9 vs 2.9(P = .41),自由呼吸实时电影2.9 vs 2.9(P = .21)。
  • 深度学习与GRAPPA伪影评分:屏气ECG门控分段电影4.4 vs 4.3(P = .55),自由呼吸实时电影3.9 vs 4.3(P < .001)。
  • 深度学习每次屏气获得层面数多于GRAPPA(3.1 vs 1,P < .001)。

临床应用与阅片要点

  • 深度学习模型可与并行成像或压缩感知联合使用,用于屏气ECG门控分段电影和自由呼吸实时电影采集后恢复空间分辨率。
  • 在屏气ECG门控分段电影中,深度学习可在每次屏气获得更多层面(3.1 vs 1,P < .001)。
  • 在自由呼吸实时电影中,深度学习伪影评分低于GRAPPA(3.9 vs 4.3,P < .001)。
  • 深度学习模型对左心室功能、容积和应变与GRAPPA一致性极好,平均差异接近零且一致性界限窄。

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

Background Cardiac cine can benefit from deep learning-based image reconstruction to reduce scan time and/or increase spatial and temporal resolution. Purpose To develop and evaluate a deep learning model that can be combined with parallel imaging or compressed sensing (CS). Materials and Methods The deep learning model was built on the enhanced super-resolution generative adversarial inline neural network, trained with use of retrospectively identified cine images and evaluated in participants prospectively enrolled from September 2021 to September 2022. The model was applied to breath-hold electrocardiography (ECG)-gated segmented and free-breathing real-time cine images collected with reduced spatial resolution with use of generalized autocalibrating partially parallel acquisitions (GRAPPA) or CS. The deep learning model subsequently restored spatial resolution. For comparison, GRAPPA-accelerated cine images were collected. Diagnostic quality and artifacts were evaluated by two readers with use of Likert scales and compared with use of Wilcoxon signed-rank tests. Agreement for left ventricle (LV) function, volume, and strain was assessed with Bland-Altman analysis. Results The deep learning model was trained on 1616 patients (mean age ± SD, 56 years ± 16; 920 men) and evaluated in 181 individuals, 126 patients (mean age, 57 years ± 16; 77 men) and 55 healthy subjects (mean age, 27 years ± 10; 15 men). In breath-hold ECG-gated segmented cine and free-breathing real-time cine, the deep learning model and GRAPPA showed similar diagnostic quality scores (2.9 vs 2.9, P = .41, deep learning vs GRAPPA) and artifact score (4.4 vs 4.3, P = .55, deep learning vs GRAPPA). Deep learning acquired more sections per breath-hold than GRAPPA (3.1 vs one section, P < .001). In free-breathing real-time cine, the deep learning showed a similar diagnostic quality score (2.9 vs 2.9, P = .21, deep learning vs GRAPPA) and lower artifact score (3.9 vs 4.3, P < .001, deep learning vs GRAPPA). For both sequences, the deep learning model showed excellent agreement for LV parameters, with near-zero mean differences and narrow limits of agreement compared with GRAPPA. Conclusion Deep learning-accelerated cardiac cine showed similarly accurate quantification of cardiac function, volume, and strain to a standardized parallel imaging method. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Vannier and Wang in this issue.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Yoon S, Nakamori S, Amyar A, et al. Accelerated Cardiac MRI Cine with Use of Resolution Enhancement Generative Adversarial Inline Neural Network. Radiology. 2023. PMID: 37249435. doi:10.1148/radiol.222878

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。