使用分辨率增强生成对抗神经网络的加速相位对比磁共振成像
Accelerated phase-contrast magnetic resonance imaging with use of resolution enhancement generative adversarial neural network.
作者信息
Morales Manuel A, Ghanbari Fahime, Demirel Ömer Burak, Street Jordan A, Wallace Tess E, Davids Rachel, Rodriguez Jennifer, Johnson Scott, Pierce Patrick, Manning Warren J, Nezafat Reza
机构信息
Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts, USA.
Siemens Medical Solutions USA, Inc., Boston, Massachusetts, USA.
出版信息
J Cardiovasc Magn Reson. 2024 Nov 28;27(1):101128. doi: 10.1016/j.jocmr.2024.101128.
BACKGROUND
Cardiovascular magnetic resonance (CMR) phase contrast is used to quantify blood flow. We sought to develop a complex-difference reconstruction for inline super-resolution of phase-contrast flow (CRISPFlow) to accelerate phase-contrast imaging.
METHODS
CRISPFlow was built on the super-resolution generative adversarial network. The model was trained and tested (4:1 ratio) using retrospectively identified phase-contrast images from 2020 patients (56 ± 16 years; 1131 men) referred for clinical 3T CMR at a single center from 2018 to 2023. For testing, ascending aortic flow images collected with 2.5 × 1.9 mm resolution using generalized autocalibrating partially parallel acquisitions (GRAPPA) were used to synthesize images with 7.5 × 1.9 mm resolution. CRISPFlow subsequently restored spatial resolution. In a prospective validation study of 38 participants (57 ± 15 years; 14 men) and 16 healthy individuals (42 ± 16 years; 6 men), CRISPFlow was applied to phase-contrast images collected with 7.5 × 1.9 mm resolution with use of GRAPPA and was compared to GRAPPA-accelerated images collected with 2.3 × 1.9 mm resolution. A blur metric was used to quantify sharpness. Aortic flow measurements were obtained semi-automatically. Statistical evaluation included analysis of variance, Bland-Altman analysis, and Pearson correlation coefficient (r).
RESULTS
CRISPFlow reconstruction was successful in all cases. CRISPFlow reduced blurring in retrospective (0.35 vs 0.47, P < 0.001) and prospective (0.34 vs 0.48, P < 0.001) images with 7.5 × 1.9 mm resolution. Blurring in CRISPFlow images was similar to blurring in images with 2.5 × 1.9 mm (0.35 vs 0.35, P = 0.4082) and 2.3 × 1.9 mm (0.34 vs 0.32, P < 0.001) resolution. Bland-Altman differences in forward volume (-2 mL [-8 to 3 mL]), regurgitant volume (0 mL [-3 to 2 mL]), and a fraction (0% [-5 to 4%]) showed good agreement between the two techniques in a retrospective cohort. Differences in forward volume (1 mL [-11 to 14 ml]) also showed good agreement in the prospective cohort. There was a strong correlation (all r > 0.90) between GRAPPA and CRISPFlow measurements of flow in both studies.
CONCLUSION
We demonstrated the potential of CRISPFlow to accelerate phase contrast CMR.
背景
心血管磁共振（CMR）相位对比用于量化血流。我们试图开发一种用于相位对比血流在线超分辨率的复差分重建（CRISPFlow），以加速相位对比成像。
方法
CRISPFlow基于超分辨率生成对抗网络构建。使用2018年至2023年在单个中心接受临床3T CMR检查的2020例患者（56±16岁；1131名男性）回顾性确定的相位对比图像对模型进行训练和测试（比例为4:1）。为了进行测试，使用广义自校准部分并行采集（GRAPPA）以2.5×1.9mm分辨率采集的升主动脉血流图像来合成7.5×1.9mm分辨率的图像。随后，CRISPFlow恢复空间分辨率。在一项针对38名参与者（57±15岁；14名男性）和16名健康个体（42±16岁；6名男性）的前瞻性验证研究中，将CRISPFlow应用于使用GRAPPA以7.5×1.9mm分辨率采集的相位对比图像，并与以2.3×1.9mm分辨率采集的GRAPPA加速图像进行比较。使用模糊度量来量化清晰度。半自动获得主动脉血流测量值。统计评估包括方差分析、Bland-Altman分析和Pearson相关系数（r）。
结果
CRISPFlow重建在所有病例中均成功。CRISPFlow减少了回顾性（0.35对0.47，P<0.001）和前瞻性（0.34对0.48，P<0.001）7.5×1.9mm分辨率图像中的模糊。CRISPFlow图像中的模糊与2.5×1.9mm（0.35对0.35，P=0.4082）和2.3×1.9mm（0.34对0.32，P<0.001）分辨率图像中的模糊相似。在回顾性队列中，两种技术在前向容积（-2mL[-8至3mL]）、反流容积（0mL[-3至2mL]）和分数（0%[-5至4%]）方面的Bland-Altman差异显示出良好的一致性。在前瞻性队列中，前向容积差异（1mL[-11至14mL]）也显示出良好的一致性。在两项研究中，GRAPPA与CRISPFlow血流测量值之间均存在强相关性（所有r>0.90）。
结论
我们证明了CRISPFlow在加速相位对比CMR方面的潜力。
Zotero 插件