Technical Note: Deep learning based MRAC using rapid ultrashort echo time imaging.
Technical Note: Deep learning based MRAC using rapid ultrashort echo time imaging.
复制标题
DOI：
10.1002/mp.12964
复制
发表时间：
2018-05-15
期刊：
影响因子：
3.8
通讯作者：
McMillan AB
中科院分区：
文献类型：
--
作者：
Jang H;Liu F;Zhao G;Bradshaw T;McMillan AB
在这项研究中，我们探索了一种新的基于卷积神经网络深度学习的基于MR的PET/MR成像衰减校正框架的可行性，该框架能够基于快速MR采集获得的超短回波时间(UTE)、脂肪和水图像对伪CT图像进行全自动和稳健的估计。MRAC的MR图像是使用双回波斜坡混合编码(DRHE)采集的，其中UTE和异相回波图像在短的单次采集(35秒)内获得。UTE图像中空气、软组织和骨骼的组织标记是通过使用T1加权MR图像预先训练的深度学习网络完成的。UTE图像被用作网络的输入，该网络使用来自共同配准的CT图像的标签进行训练。通过基于条件随机场的校正来精炼通过深度学习估计的组织标签。使用两点Dixon法将软组织标记进一步分离为脂肪和水成分。然后，对估计的骨骼、空气、脂肪和水图像分配适当的Hounsfield单位，产生用于PET衰减校正的伪CT图像。为了评估所提出的MRAC方法，对8名受试者进行了头部的PET/MR成像，通过与配准的CT图像进行比较来评估估计的组织标签的Dice相似系数和相对的PET误差。空气(头部)、软组织和骨标签的骰子系数分别为0.76±0.03、0.96±0.006和0.88±0.01。在PET定量中，提出的MRAC方法在大多数脑区内的相对PET误差小于1%。所提出的MRAC方法利用带转移学习的深度学习和有效的dRHE采集，能够可靠地进行PET定量，并生成准确和快速的伪CT。
In this study, we explore the feasibility of a novel framework for MR-based attenuation correction for PET/MR imaging based on deep learning via convolutional neural networks, which enables fully automated and robust estimation of a pseudo CT image based on ultrashort echo time (UTE), fat, and water images obtained by a rapid MR acquisition. MR images for MRAC are acquired using dual echo ramped hybrid encoding (dRHE), where both UTE and out-of-phase echo images are obtained within a short single acquisition (35 sec). Tissue labeling of air, soft tissue, and bone in the UTE image is accomplished via a deep learning network that was pre-trained with T1-weighted MR images. UTE images are used as input to the network, which was trained using labels derived from co-registered CT images. The tissue labels estimated by deep learning are refined by a conditional random field based correction. The soft tissue labels are further separated into fat and water components using the two-point Dixon method. The estimated bone, air, fat, and water images are then assigned appropriate Hounsfield units, resulting in a pseudo CT image for PET attenuation correction. To evaluate the proposed MRAC method, PET/MR imaging of the head was performed on 8 human subjects, where Dice similarity coefficients of the estimated tissue labels and relative PET errors were evaluated through comparison to a registered CT image. Dice coefficients for air (within the head), soft tissue, and bone labels were 0.76±0.03, 0.96±0.006, and 0.88±0.01. In PET quantification, the proposed MRAC method produced relative PET errors less than 1% within most brain regions. The proposed MRAC method utilizing deep learning with transfer learning and an efficient dRHE acquisition enables reliable PET quantification with accurate and rapid pseudo CT generation.
登录
查看更多内容
影响因子：
3.3
作者：
Jang H;Liu F;Bradshaw T;McMillan AB
通讯作者：
McMillan AB
影响因子：
9.3
作者：
Hofmann, Matthias;Steinke, Florian;Pichler, Bernd J.
通讯作者：
Pichler, Bernd J.
影响因子：
10.9
作者：
Avendi, M. R.;Kheradvar, Arash;Jafarkhani, Hamid
通讯作者：
Jafarkhani, Hamid
影响因子：
9.3
作者：
Hofmann, Matthias;Bezrukov, Ilja;Schoelkopf, Bernhard
通讯作者：
Schoelkopf, Bernhard
影响因子：
9.3
作者：
Keereman, Vincent;Fierens, Yves;Vandenberghe, Stefaan
通讯作者：
Vandenberghe, Stefaan