Using neural networks to extend cropped medical images for deformable registration among images with differing scan extents.
Using neural networks to extend cropped medical images for deformable registration among images with differing scan extents.
复制标题
DOI：
10.1002/mp.15039
复制
发表时间：
2021-08
期刊：
影响因子：
3.8
通讯作者：
Sheng K
中科院分区：
文献类型：
--
作者：
McKenzie EM;Tong N;Ruan D;Cao M;Chin RK;Sheng K
缺失或差异成像量是可变形图像登记（DIR）的常见挑战，我们可以训练神经元网络，以合成头颈CT的裁剪部分，然后测试其在DIR中的使用。
使用409头和颈部CT的训练数据集，我们训练了一个通用的对抗网络，以摄入裁剪的3D图像，并在裁切区域输出带有合成的解剖图像的图像。为了测试我们的技术，对于53次测试，我们使用Elastix进行了畸形，以随机裁剪，完整和合成的全卷为单一的裁剪，完整，合成的目标量。我们还通过逐步增加了我们的网络，并使用95％的Hausdorff距离在16个轮廓中测量了相同的登记组合，从而逐步研究了我们方法对作物范围的鲁棒性。
我们成功地训练了一个网络，以综合上裁剪的图像和下属的图像中缺少解剖结构。 。相比方法很难构成综合注册，在统计上独立于农作物范围，直到综合杂种几乎是独立的，每千分钟的裁剪每增加一个平均轮廓误差的平均轮廓误差为-0.04mm。
在扫描范围内，不同的或不足的是，我们通过训练神经网络来完成这一挑战的主要原因。不同的作物范围。
Missing or discrepant imaging volumes is a common challenge in deformable image registration (DIR). To minimize the adverse impact, we train a neural network to synthesize cropped portions of head and neck CT’s and then test its use in DIR. Using a training dataset of 409 head and neck CT’s, we trained a generative adversarial network to take in a cropped 3D image and output an image with synthesized anatomy in the cropped region. The network used a 3D U-Net generator along with VGG deep feature losses. To test our technique, for each of the 53 test volumes, we used Elastix to deformably register combinations of a randomly cropped, full, and synthetically full volume to a single cropped, full, and synthetically full target volume. We additionally tested our method’s robustness to crop extent by progressively increasing the amount of cropping, synthesizing the missing anatomy using our network, then performing the same registration combinations. Registration performance was measured using 95% Hausdorff distance across 16 contours. We successfully trained a network to synthesize missing anatomy in superiorly and inferiorly cropped images. The network can estimate large regions in an incomplete image, far from the cropping boundary. Registration using our estimated full images was not significantly different from registration using the original full images. The average contour matching error for full image registration was 9.9mm, while our method was 11.6mm, 12.1mm, and 13.6mm for synthesized-to-full, full-to-synthesized, and synthesized-to-synthesized registrations, respectively. In comparison, registration using the cropped images had errors of 31.7mm and higher. Plotting the registered image contour error as a function of initial pre-registered error shows that our method is robust to registration difficulty. Synthesized-to-full registration was statistically independent of cropping extent up to 18.7cm superiorly cropped. Synthesized-to-synthesized registration was nearly independent, with a −0.04mm change in average contour error for every additional millimeter of cropping. Different or inadequate in scan extent is a major cause of DIR inaccuracies. We address this challenge by training a neural network to complete cropped 3D images. We show that with image completion, the source of DIR inaccuracy is eliminated, and the method is robust to varying crop extent.
登录
查看更多内容
影响因子：
3.8
作者：
Tong N;Gou S;Yang S;Ruan D;Sheng K
通讯作者：
Sheng K
影响因子：
3.5
作者：
Shamonin DP;Bron EE;Lelieveldt BP;Smits M;Klein S;Staring M;Alzheimer's Disease Neuroimaging Initiative
通讯作者：
Alzheimer's Disease Neuroimaging Initiative
影响因子：
3.8
作者：
McKenzie, Elizabeth M.;Santhanam, Anand;Sheng, Ke
通讯作者：
Sheng, Ke
影响因子：
3.8
作者：
Brock, Kristy K.;Mutic, Sasa;Kessler, Marc L.
通讯作者：
Kessler, Marc L.
影响因子：
4.4
作者：
Clark, Kenneth;Vendt, Bruce;Prior, Fred
通讯作者：
Prior, Fred