Division of Image Processing, Department of Radiology, Leiden University Medical Center, Leiden, The Netherlands.
Leeds Institute of Cardiovascular and Metabolic Medicine, University of Leeds, Leeds, UK.
Int J Cardiovasc Imaging. 2023 May;39(5):1045-1053. doi: 10.1007/s10554-023-02804-2. Epub 2023 Feb 10.
We aimed to design and evaluate a deep learning-based method to automatically predict the time-varying in-plane blood flow velocity within the cardiac cavities in long-axis cine MRI, validated against 4D flow.
A convolutional neural network (CNN) was implemented, taking cine MRI as the input and the in-plane velocity derived from the 4D flow acquisition as the ground truth. The method was evaluated using velocity vector end-point error (EPE) and angle error. Additionally, the E/A ratio and diastolic function classification derived from the predicted velocities were compared to those derived from 4D flow.
For intra-cardiac pixels with a velocity > 5 cm/s, our method achieved an EPE of 8.65 cm/s and angle error of 41.27°. For pixels with a velocity > 25 cm/s, the angle error significantly degraded to 19.26°. Although the averaged blood flow velocity prediction was under-estimated by 26.69%, the high correlation (PCC = 0.95) of global time-varying velocity and the visual evaluation demonstrate a good agreement between our prediction and 4D flow data. The E/A ratio was derived with minimal bias, but with considerable mean absolute error of 0.39 and wide limits of agreement. The diastolic function classification showed a high accuracy of 86.9%.
Using a deep learning-based algorithm, intra-cardiac blood flow velocities can be predicted from long-axis cine MRI with high correlation with 4D flow derived velocities. Visualization of the derived velocities provides adjunct functional information and may potentially be used to derive the E/A ratio from conventional CMR exams.
我们旨在设计并评估一种基于深度学习的方法，以自动预测心脏长轴电影 MRI 中的时变腔内平面血流速度，该方法通过与 4D 流对比进行验证。
我们实施了一种卷积神经网络（CNN），以电影 MRI 作为输入，以 4D 流采集获得的平面速度作为基准。该方法通过速度矢量端点误差（EPE）和角度误差进行评估。此外，还比较了从预测速度得出的 E/A 比值和舒张功能分类与从 4D 流得出的结果。
对于速度大于 5cm/s 的心内像素，我们的方法的 EPE 为 8.65cm/s，角度误差为 41.27°。对于速度大于 25cm/s 的像素，角度误差显著恶化至 19.26°。虽然平均血流速度预测值低估了 26.69%，但全局时变速度的高度相关性（PCC=0.95）和直观评估表明，我们的预测与 4D 流数据之间具有良好的一致性。E/A 比值的偏差最小，但平均绝对误差为 0.39，且一致性界限较宽。舒张功能分类的准确率高达 86.9%。
使用基于深度学习的算法，可以从心脏长轴电影 MRI 中预测心内血流速度，与 4D 流衍生的速度具有高度相关性。衍生速度的可视化提供了附加的功能信息，并且可能有潜力从常规 CMR 检查中得出 E/A 比值。
