Matsubara Keisuke, Ibaraki Masanobu, Kinoshita Toshibumi
Department of Management Science and Engineering, Faculty of System Science and Technology, Akita Prefectural University, 84-4 Aza Ebinokuchi Tsuchiya, Yurihonjo, 015-0055, Japan.
Department of Radiology and Nuclear Medicine, Research Institute for Brain and Blood Vessels, Akita Cerebrospinal and Cardiovascular Center, Akita, 010-0874, Japan.
EJNMMI Phys. 2022 Jul 30;9(1):50. doi: 10.1186/s40658-022-00478-8.
Partial volume correction with anatomical magnetic resonance (MR) images (MR-PVC) is useful for accurately quantifying tracer uptake on brain positron emission tomography (PET) images. However, MR segmentation processes for MR-PVC are time-consuming and prevent the widespread clinical use of MR-PVC. Here, we aimed to develop a deep learning model to directly predict PV-corrected maps from PET and MR images, ultimately improving the MR-PVC throughput.
We used MR T1-weighted and [C]PiB PET images as input data from 192 participants from the Alzheimer's Disease Neuroimaging Initiative database. We calculated PV-corrected maps as the training target using the region-based voxel-wise PVC method. Two-dimensional U-Net model was trained and validated by sixfold cross-validation with the dataset from the 156 participants, and then tested using MR T1-weighted and [C]PiB PET images from 36 participants acquired at sites other than the training dataset. We calculated the structural similarity index (SSIM) of the PV-corrected maps and intraclass correlation (ICC) of the PV-corrected standardized uptake value between the region-based voxel-wise (RBV) PVC and deepPVC as indicators for validation and testing.
A high SSIM (0.884 ± 0.021) and ICC (0.921 ± 0.042) were observed in the validation and test data (SSIM, 0.876 ± 0.028; ICC, 0.894 ± 0.051). The computation time required to predict a PV-corrected map for a participant (48 s without a graphics processing unit) was much shorter than that for the RBV PVC and MR segmentation processes.
These results suggest that the deepPVC model directly predicts PV-corrected maps from MR and PET images and improves the throughput of MR-PVC by skipping the MR segmentation processes.
利用解剖磁共振（MR）图像进行部分容积校正（MR-PVC）有助于在脑正电子发射断层扫描（PET）图像上准确量化示踪剂摄取。然而，MR-PVC的MR分割过程耗时，阻碍了MR-PVC在临床中的广泛应用。在此，我们旨在开发一种深度学习模型，直接从PET和MR图像预测经部分容积校正的图像，最终提高MR-PVC的通量。
我们使用来自阿尔茨海默病神经影像倡议数据库的192名参与者的MR T1加权图像和[C]PiB PET图像作为输入数据。我们使用基于区域的体素级PVC方法计算经部分容积校正的图像作为训练目标。二维U-Net模型通过对156名参与者的数据进行六重交叉验证进行训练和验证，然后使用来自训练数据集以外站点的36名参与者的MR T1加权图像和[C]PiB PET图像进行测试。我们计算经部分容积校正的图像的结构相似性指数（SSIM）以及基于区域的体素级（RBV）PVC和深度部分容积校正（deepPVC）之间经部分容积校正的标准化摄取值的组内相关系数（ICC），作为验证和测试的指标。
在验证和测试数据中观察到较高的SSIM（0.884±0.021）和ICC（0.921±0.042）（SSIM，0.876±0.028；ICC，0.894±0.051）。为一名参与者预测经部分容积校正的图像所需的计算时间（无图形处理单元时为48秒）比RBV PVC和MR分割过程所需的时间短得多。
这些结果表明，deepPVC模型可直接从MR和PET图像预测经部分容积校正的图像，并通过跳过MR分割过程提高MR-PVC的通量。
