Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, 21287, USA.
Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins Medical Institutes, Baltimore, MD, 21287, USA.
Med Phys. 2020 Dec;47(12):6366-6380. doi: 10.1002/mp.14545. Epub 2020 Nov 9.
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 computed tomography (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 tradeoff 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.
计算机化体模已广泛应用于核医学成像，用于成像系统优化和验证。虽然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学变异，但它们无法完全复制在人体中看到的解剖学变异和细节。在这项工作中，我们提出了一种基于配准的新方法来创建高度解剖详细的计算机化体模。我们通过实验证明，生成的体模与患者图像的图像相似度有了显著提高。
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 体模变形到患者 CT 扫描上来生成高度解剖详细的计算机化体模。我们使用基于 NURBS 的 XCAT 体模和来自 TCIA 的公开的低剂量 CT 数据集来实现和评估所提出的方法。进行了严格的图像相似性和变形正则化之间的折衷分析，以选择所提出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，进行了消融研究，以评估所提出方法（使用最优正则化和损失函数）和当前最先进的无监督配准方法的性能。
所提出的方法在 SSIM 方面优于最先进的配准方法（如 SyN 和 VoxelMorph），超过 8%，在 MSE 方面则超过 30%。所提出的方法生成的体模非常详细，外观几乎与患者图像完全相同。
开发了一种基于深度学习的无监督配准方法，用于创建具有解剖学标签的拟人化体模，这些体模可以用作器官特性建模的基础。实验结果证明了所提出方法的有效性。生成的拟人化体模非常逼真。与图像形成过程的真实模拟相结合，生成的体模可以用于许多医学成像研究应用。
