Deep Learning MR Imaging-based Attenuation Correction for PET/MR Imaging
Deep Learning MR Imaging-based Attenuation Correction for PET/MR Imaging
复制标题
DOI：
10.1148/radiol.2017170700
复制
发表时间：
2018-02-01
期刊：
影响因子：
19.7
通讯作者：
McMillan, Alan B.
中科院分区：
文献类型：
--
作者：
Liu, Fang;Jang, Hyungseok;McMillan, Alan B.
目的：开发并评估基于磁共振（MR）成像的衰减校正（AC）（称为深度MRAC）的深度学习方法在脑正电子发射断层扫描（PET）/MR成像中的可行性。
材料与方法：通过使用深度学习方法从MR图像生成伪计算机断层扫描（CT）来构建PET/MR成像AC流程。训练一个深度卷积自动编码器网络，以在与CT数据配准的头部容积MR图像中识别空气、骨骼和软组织用于训练。使用一组30幅回顾性三维T1加权头部图像来训练模型，然后通过将生成的伪CT扫描与获取的CT扫描进行比较，在10名患者中对其进行评估。通过使用所提出的方法对5名受试者进行同时PET/MR成像的前瞻性研究。使用协方差分析和配对样本t检验进行统计分析，以比较使用深度MRAC以及两种现有的基于MR成像的AC方法与基于CT的AC的PET重建误差。
结果：深度MRAC提供了准确的伪CT扫描，空气的平均迪氏系数为0.971±0.005，软组织为0.936±0.011，骨骼为0.803±0.021。此外，深度MRAC提供了良好的PET结果，在大多数脑区平均误差小于1%。与基于狄克逊的软组织和空气分割（-5.8%±3.1）以及基于解剖CT的模板配准（-4.8%±2.2）相比，深度MRAC实现了显著更低的PET重建误差（-0.7%±1.1）。
结论：作者开发了一种自动化方法，该方法允许从单个高空间分辨率的诊断质量三维MR图像生成离散值的伪CT扫描（软组织、骨骼和空气），并在脑PET/MR成像中对其进行了评估。这种基于MR成像的AC的深度学习方法与当前基于MR成像的AC方法相比，在脑内相对于基于CT的标准减少了PET重建误差。（C）美国放射学会，2017
Purpose: To develop and evaluate the feasibility of deep learning approaches for magnetic resonance (MR) imaging-based attenuation correction (AC) (termed deep MRAC) in brain positron emission tomography (PET)/MR imaging.Materials and Methods: A PET/MR imaging AC pipeline was built by using a deep learning approach to generate pseudo computed tomographic (CT) scans from MR images. A deep convolutional auto-encoder network was trained to identify air, bone, and soft tissue in volumetric head MR images co-registered to CT data for training. A set of 30 retrospective three-dimensional T1-weighted head images was used to train the model, which was then evaluated in 10 patients by comparing the generated pseudo CT scan to an acquired CT scan. A prospective study was carried out for utilizing simultaneous PET/MR imaging for five subjects by using the proposed approach. Analysis of covariance and paired-sample t tests were used for statistical analysis to compare PET reconstruction error with deep MRAC and two existing MR imaging-based AC approaches with CT-based AC.Results: Deep MRAC provides an accurate pseudo CT scan with a mean Dice coefficient of 0.971 +/- 0.005 for air, 0.936 +/- 0.011 for soft tissue, and 0.803 +/- 0.021 for bone. Furthermore, deep MRAC provides good PET results, with average errors of less than 1% in most brain regions. Significantly lower PET reconstruction errors were realized with deep MRAC (-0.7% +/- 1.1) compared with Dixon-based soft-tissue and air segmentation (-5.8% +/- 3.1) and anatomic CT-based template registration (-4.8% +/- 2.2).Conclusion: The authors developed an automated approach that allows generation of discrete-valued pseudo CT scans (soft tissue, bone, and air) from a single high-spatial-resolution diagnostic-quality three-dimensional MR image and evaluated it in brain PET/MR imaging. This deep learning approach for MR imaging-based AC provided reduced PET reconstruction error relative to a CT-based standard within the brain compared with current MR imaging-based AC approaches. (C) RSNA, 2017