Generating anthropomorphic phantoms using fully unsupervised deformable image registration with convolutional neural networks.
Generating anthropomorphic phantoms using fully unsupervised deformable image registration with convolutional neural networks.
复制标题
使用完全无监督的可变形图像与卷积神经网络配准来生成拟人化模型。
作者：
计算机体模已广泛应用于核医学成像中，用于成像系统的优化和验证。尽管现有的计算机化体模可以通过器官和体模缩放来模拟解剖变化，但是它们没有提供完全再现在人体中看到的解剖变化和细节的方法。在这项工作中，我们提出了一种新的基于配准的方法，用于创建高度解剖细节的计算机化体模。我们在实验中显示，所生成的体模与患者图像的图像相似性显著提高。我们提出了一种基于深度学习的无监督配准方法，通过将XCAT体模扭曲到患者CT扫描来生成高度解剖细节的计算机化体模。我们使用基于NURBS的XCAT体模和来自TCIA的公开可用低剂量CT数据集实施并评估了所提出的方法。在图像相似性和变形正则化之间进行了严格的权衡分析，确定了该方法的损失函数和正则化项。提出了一种新的基于SSIM的无监督目标函数。最后，通过烧蚀实验对所提方法（使用最优正则化和损失函数）和当前最新的无监督配准方法的性能进行了评估。与现有的配准方法（如SyN和VoxelMorph）相比，所提出的方法在SSIM和MSE两个方面的性能分别提高了8%和30%。通过所提出的方法生成的体模非常详细，并且在外观上几乎与患者图像相同。开发了一种基于深度学习的无监督配准方法，用于创建带有解剖标记的拟人体模，该拟人体模可用作器官属性建模的基础。通过仿真和实测数据处理验证了所提方法的有效性。由此产生的拟人体模是高度逼真的。结合对成像过程的真实模拟，所生成的体模可用于医学成像研究的许多应用。
Computerized phantoms have been widely used in nuclear medicine imaging for imaging system optimization and validation. Although the existing computerized phantoms can model anatomical variations through organ and phantom scaling, they do not provide a way to fully reproduce the anatomical variations and details seen in humans. In this work, we present a novel registration-based method for creating highly anatomically detailed computerized phantoms. We experimentally show substantially improved image similarity of the generated phantom to a patient image. We propose a deep-learning-based unsupervised registration method to generate a highly anatomically detailed computerized phantom by warping an XCAT phantom to a patient CT scan. We implemented and evaluated the proposed method using the NURBS-based XCAT phantom and a publicly available low-dose CT dataset from TCIA. A rigorous trade-off analysis between image similarity and deformation regularization was conducted to select the loss function and regularization term for the proposed method. A novel SSIM-based unsupervised objective function was proposed. Finally, ablation studies were conducted to evaluate the performance of the proposed method (using the optimal regularization and loss function) and the current state-of-the-art unsupervised registration methods. The proposed method outperformed the state-of-the-art registration methods, such as SyN and VoxelMorph, by more than 8%, measured by the SSIM and less than 30%, by the MSE. The phantom generated by the proposed method was highly detailed and was almost identical in appearance to a patient image. A deep-learning-based unsupervised registration method was developed to create anthropomorphic phantoms with anatomies labels that can be used as the basis for modeling organ properties. Experimental results demonstrate the effectiveness of the proposed method. The resulting anthropomorphic phantom is highly realistic. Combined with realistic simulations of the image formation process, the generated phantoms could serve in many applications of medical imaging research.
登录
查看更多内容
DOI：
10.1023/b:visi.0000043755.93987.aa
发表时间：
2005-02-01
影响因子：
19.5
作者：
Beg, MF;Miller, MI;Younes, L
通讯作者：
Younes, L
影响因子：
10.9
作者：
de Vos, Bob D.;Berendsen, Floris F.;Isgum, Ivana
通讯作者：
Isgum, Ivana
影响因子：
3.5
作者：
Jan, S.;Benoit, D.;Buvat, I.
通讯作者：
Buvat, I.
影响因子：
3.5
作者：
He, B;Du, Y;Frey, EC
通讯作者：
Frey, EC
影响因子：
4.4
作者：
Clark, Kenneth;Vendt, Bruce;Prior, Fred
通讯作者：
Prior, Fred