Feasibility of Deep Learning-Based PET/MR Attenuation Correction in the Pelvis Using Only Diagnostic MR Images.
Feasibility of Deep Learning-Based PET/MR Attenuation Correction in the Pelvis Using Only Diagnostic MR Images.
复制标题
DOI：
10.18383/j.tom.2018.00016
复制
发表时间：
2018-09
期刊：
影响因子：
--
通讯作者：
McMillan AB
中科院分区：
文献类型：
--
作者：
Bradshaw TJ;Zhao G;Jang H;Liu F;McMillan AB
本研究评估了仅使用诊断相关的磁共振（MR）图像与深度学习一起用于骨盆正电子发射断层扫描(PET)/磁共振衰减校正（deepMRAC）的可行性。这种方法可以消除专用的MRAC序列，这些序列的诊断效用有限，但可以大大延长多床位置扫描的采集时间。我们使用轴向T2和T1的LAVA Flex磁共振成像图像作为诊断目的的输入到3D深度卷积神经网络。该网络被训练产生离散化（空气、水、脂肪和骨骼）替代计算机断层扫描（CT） （CTsub）。创建离散化（CTref-discrete）和连续值（CTref）参考CT图像，分别作为网络训练和衰减校正的基础真值。使用来自12名受试者的数据进行训练。采用CTsub、CTref和系统MRAC进行PET/MR衰减校正，比较6名被试的定量PET值。总的来说，与ctref离散相比，该网络产生的CTsub对皮质骨的Dice系数为0.79±0.03，对软组织的Dice系数为0.98±0.01（脂肪：0.94±0.0；水：0.88±0.02），对肠气的Dice系数为0.49±0.17。使用deepMRAC和系统MRAC对整个PET图像的均方根误差分别为4.9%和11.6%。在评估16个软组织病变时，根据Brown-Forsy检验，deepMRAC法最大标准化摄取值的误差分布（- 1.0%±1.3%）明显小于系统MRAC法（0.0%±6.4%）（P < 0.05）。这些结果表明，仅使用诊断相关的MR图像就可以在骨盆中实现改进的PET/MR衰减校正。
This study evaluated the feasibility of using only diagnostically relevant magnetic resonance (MR) images together with deep learning for positron emission tomography (PET)/MR attenuation correction (deepMRAC) in the pelvis. Such an approach could eliminate dedicated MRAC sequences that have limited diagnostic utility but can substantially lengthen acquisition times for multibed position scans. We used axial T2 and T1 LAVA Flex magnetic resonance imaging images that were acquired for diagnostic purposes as inputs to a 3D deep convolutional neural network. The network was trained to produce a discretized (air, water, fat, and bone) substitute computed tomography (CT) (CTsub). Discretized (CTref-discrete) and continuously valued (CTref) reference CT images were created to serve as ground truth for network training and attenuation correction, respectively. Training was performed with data from 12 subjects. CTsub, CTref, and the system MRAC were used for PET/MR attenuation correction, and quantitative PET values of the resulting images were compared in 6 test subjects. Overall, the network produced CTsub with Dice coefficients of 0.79 ± 0.03 for cortical bone, 0.98 ± 0.01 for soft tissue (fat: 0.94 ± 0.0; water: 0.88 ± 0.02), and 0.49 ± 0.17 for bowel gas when compared with CTref-discrete. The root mean square error of the whole PET image was 4.9% by using deepMRAC and 11.6% by using the system MRAC. In evaluating 16 soft tissue lesions, the distribution of errors for maximum standardized uptake value was significantly narrower using deepMRAC (−1.0% ± 1.3%) than using system MRAC method (0.0% ± 6.4%) according to the Brown–Forsy the test (P < .05). These results indicate that improved PET/MR attenuation correction can be achieved in the pelvis using only diagnostically relevant MR images.
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
DOI：
10.1007/s00259-012-2113-0
发表时间：
2012-07-01
影响因子：
9.1
作者：
Samarin, Andrei;Burger, Cyrill;Kuhn, Felix P.
通讯作者：
Kuhn, Felix P.
影响因子：
9.3
作者：
Leynes, Andrew P.;Yang, Jaewon;Larson, Peder E. Z.
通讯作者：
Larson, Peder E. Z.
影响因子：
3.8
作者：
Mehranian, Abolfazl;Arabi, Hossein;Zaidi, Habib
通讯作者：
Zaidi, Habib
影响因子：
9.3
作者：
Martinez-Moeller, Axel;Souvatzoglou, Michael;Nekolla, Stephan G.
通讯作者：
Nekolla, Stephan G.