论著摘要 |【AI-CT】使用深度卷积神经网络方法对基于MR的综合CT进行生成(双语版)

2018-01-24 10:56:30 admin 0
标签:   人工智能 CT MRI 综合CT 卷积神经网络 深度学习 放疗

MR-based synthetic CT generation using a deep convolutional neural network method.

发表日期: 2017.03.21   来源:Med Phys. 2017 Apr;44(4):1408-1419.

作者:

Xiao Han1.

作者介绍:

1. Elekta Inc., Maryland Heights, MO, 63043, USA.

摘要

Abstact

目的

由于MRI所提供的优异的软组织对比度以及减少不必要的辐射剂量的特性,在放疗领域中磁共振成像(MRI)正在快速增长的速度代替CT。 仅MR放疗也简化了临床工作流程,避免了使用CT校准MR的不确定性。然而,需要从病人的MR图像中推导CT等效特征(通常称为综合CT(sCT)),以用于剂量计算和基于DRR的患者定位。综合CT估计对于混合PET-MR系统中的PET衰减校正也是重要的。我们在这项工作中提出了一种新的深度卷积神经网络(DCNN)方法,用于生成sCT并评估其在一组脑部肿瘤患者图像上的表现。

Purpose

Interests have been rapidly growing in the field of radiotherapy to replace CT with magnetic resonance imaging (MRI), due to superior soft tissue contrast offered by MRI and the desire to reduce unnecessary radiation dose. MR-only radiotherapy also simplifies clinical workflow and avoids uncertainties in aligning MR with CT. Methods, however, are needed to derive CT-equivalent representations, often known as synthetic CT (sCT), from patient MR images for dose calculation and DRR-based patient positioning. Synthetic CT estimation is also important for PET attenuation correction in hybrid PET-MR systems. We propose in this work a novel deep convolutional neural network (DCNN) method for sCT generation and evaluate its performance on a set of brain tumor patient images.

方法

所提出的方法建立在计算机视觉文献中深度学习和卷积神经网络的最新发展。所提出的DCNN模型具有27个卷积层,其与pooling和unpooling层交织,并且具有3500万个自由参数,可以被训练以学习从MR图像到它们对应的CT的直接端到端映射。在我们有限的数据上培训这样一个大型模型是通过转移学习的原理和初始化模型权重来实现的。使用18名脑肿瘤患者的CT和T1加权MR图像作为实验数据,并进行六倍交叉验证研究。将每个生成的sCT与同一患者的真实CT图像进行以体素为基础的比较。对于基于图谱的方法也进行了比较,该方法涉及可变形的图谱注册和基于子块的图谱融合。

Methods

The proposed method builds upon recent developments of deep learning and convolutional neural networks in the computer vision literature. The proposed DCNN model has 27 convolutional layers interleaved with pooling and unpooling layers and 35 million free parameters, which can be trained to learn a direct end-to-end mapping from MR images to their corresponding CTs. Training such a large model on our limited data is made possible through the principle of transfer learning and by initializing model weights from a pretrained model. Eighteen brain tumor patients with both CT and T1-weighted MR images are used as experimental data and a sixfold cross-validation study is performed. Each sCT generated is compared against the real CT image of the same patient on a voxel-by-voxel basis. Comparison is also made with respect to an atlas-based approach that involves deformable atlas registration and patch-based atlas fusion.

结果

所提出的DCNN方法为18个测试对象中的13个产生了低于85HU的平均绝对误差(MAE)。所有受试者的总体平均MAE为84.8±17.3HU,发现其明显优于基于图谱的方法的平均MAE(94.5±17.8HU)。当使用两个其他度量(均方差(188.6±33.7对198.3±33.0)和Pearson相关系数(0.906±0.03对0.896±0.03))评估DCNN方法时,也提供了显著更好的准确度。尽管训练DCNN模型可能会很慢,但只需要进行一次训练。应用训练有素的模型为每个新患者MR图像生成完整的sCT体积仅需要9 s,比基于图谱的方法快得多。

Results

The proposed DCNN method produced a mean absolute error (MAE) below 85 HU for 13 of the 18 test subjects. The overall average MAE was 84.8 ± 17.3 HU for all subjects, which was found to be significantly better than the average MAE of 94.5 ± 17.8 HU for the atlas-based method. The DCNN method also provided significantly better accuracy when being evaluated using two other metrics: the mean squared error (188.6 ± 33.7 versus 198.3 ± 33.0) and the Pearson correlation coefficient(0.906 ± 0.03 versus 0.896 ± 0.03). Although training a DCNN model can be slow, training only need be done once. Applying a trained model to generate a complete sCT volume for each new patient MR image only took 9 s, which was much faster than the atlas-based approach.

结论

开发了一种DCNN模型方法,并能够近乎实时地从传统的单序列MR图像产生高度准确的sCT估计。定量结果还表明,所提出的方法在测试时间的准确性和计算速度方面与基于图谱的方法相比具有很好的竞争性。有必要在更大的患者组中进一步验证剂量计算的准确性。该方法的扩展也可以为进一步提高准确性或处理多序列MR图像提供了可能。

Conclusions

A DCNN model method was developed, and shown to be able to produce highly accurate sCT estimations from conventional, single-sequence MR images in near real time. Quantitative results also showed that the proposed method competed favorably with an atlas-based method, in terms of both accuracy and computation speed at test time. Further validation on dose computation accuracy and on a larger patient cohort is warranted. Extensions of the method are also possible to further improve accuracy or to handle multi-sequence MR images.

关键词:

MRI;卷积神经网络;深度学习;放疗;综合CT

Keywords:

MRI ; convolutional neural network; deep learning; radiation therapy; synthetic CT

阅读原文:PMID: 28192624  DOI: 10.1002/mp.12155


慧影医疗科技(北京)有限公司

地点:北京市海淀区中关村东升科技园B2-C103

电话:400-890-9020

邮箱:radcloud@huiyihuiying.com

关闭
图片
图片