Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX, USA.
Department of Radiation Oncology, University of Colorado Denver, Aurora, CO, USA.
Med Phys. 2019 May;46(5):2323-2329. doi: 10.1002/mp.13421. Epub 2019 Mar 12.
Ventilation images can be derived from four-dimensional computed tomography (4DCT) by analyzing the change in HU values and deformable vector fields between different respiration phases of computed tomography (CT). As deformable image registration (DIR) is involved, accuracy of 4DCT-derived ventilation image is sensitive to the choice of DIR algorithms. To overcome the uncertainty associated with DIR, we develop a method based on deep convolutional neural network (CNN) to derive ventilation images directly from the 4DCT without explicit image registration.
A total of 82 sets of 4DCT and ventilation images from patients with lung cancer were used in this study. In the proposed CNN architecture, the CT two-channel input data consist of CT at the end of exhale and the end of inhale phases. The first convolutional layer has 32 different kernels of size 5 × 5 × 5, followed by another eight convolutional layers each of which is equipped with an activation layer (ReLU). The loss function is the mean-squared-error (MSE) to measure the intensity difference between the predicted and reference ventilation images.
The predicted images were comparable to the label images of the test data. The similarity index, correlation coefficient, and Gamma index passing rate averaged over the tenfold cross validation were 0.880 ± 0.035, 0.874 ± 0.024, and 0.806 ± 0.014, respectively.
The results demonstrate that deep CNN can generate ventilation imaging from 4DCT without explicit deformable image registration, reducing the associated uncertainty.
通过分析 CT 不同呼吸相位之间的 HU 值变化和可变形矢量场，可以从四维 CT（4DCT）中得出通气图像。由于涉及可变形图像配准（DIR），因此 4DCT 衍生通气图像的准确性对 DIR 算法的选择很敏感。为了克服与 DIR 相关的不确定性，我们开发了一种基于深度卷积神经网络（CNN）的方法，无需显式图像配准即可直接从 4DCT 得出通气图像。
本研究共使用了 82 组来自肺癌患者的 4DCT 和通气图像。在提出的 CNN 架构中，CT 双通道输入数据由呼气末和吸气末的 CT 组成。第一个卷积层具有 32 个大小为 5×5×5 的不同核，其后是另外 8 个卷积层，每个卷积层都配备有激活层（ReLU）。损失函数是均方误差（MSE），用于测量预测和参考通气图像之间的强度差异。
预测图像与测试数据的标签图像相当。十折交叉验证的平均相似度指数、相关系数和 Gamma 指数通过率分别为 0.880±0.035、0.874±0.024 和 0.806±0.014。
结果表明，深度 CNN 可以在不进行显式可变形图像配准的情况下从 4DCT 生成通气图像，从而降低了相关的不确定性。
