基于深度学习的 QSM 磁共振成像对丘脑底核的影响。
The Effect of Deep Learning-Based QSM Magnetic Resonance Imaging on the Subthalamic Nucleus.
机构信息
Department of Neurosurgery, Shandong Provincial Qianfoshan Hospital, Cheeloo College of Medicine, Shandong University, Jinan, Shandong 250014, China.
Department of Special Examination, Shandong Provincial Third Hospital, Cheeloo College of Medicine, Shandong University, Jinan, Shandong 250031, China.
出版信息
J Healthc Eng. 2021 Sep 15;2021:8554182. doi: 10.1155/2021/8554182. eCollection 2021.
In order to study the influence of quantitative magnetic susceptibility mapping (QSM) on them. A 2.5D Attention U-Net Network based on multiple input and multiple output, a method for segmenting RN, SN, and STN regions in high-resolution QSM images is proposed, and deep learning realizes accurate segmentation of deep nuclei in brain QSM images. Experimental results show data first cuts each layer of 0 100 case data, based on the image center, from 384 × 288 to the size of 128 × 128. Image combination: each layer of the image in the layer direction combines with two adjacent images into a 2.5D image, i.e., ( - ; + ), where represents the layer image. At this time, the size of the image changes from 128 × 128 to 128 × 128 × 3, in which 3 represents three consecutive layers of images. The SNR of SWP I to STN is twice that of SWI. The small deep gray matter nuclei (RN, SN, and STN) in QSM images of the brain and the pancreas with irregular shape and large individual differences in abdominal CT images can be automatically segmented.
为了研究定量磁化率映射(QSM)对它们的影响。提出了一种基于多输入多输出的 2.5D 注意力 U-Net 网络，用于分割高分辨率 QSM 图像中的 RN、SN 和 STN 区域，并通过深度学习实现了脑 QSM 图像中深部核的精确分割。实验结果表明，数据首先将每一层的 0-100 例数据切割，基于图像中心，从 384×288 到 128×128 的大小。图像组合：在层方向上，每层图像与两个相邻图像组合成一个 2.5D 图像，即(−; +)，其中表示层图像。此时，图像的大小从 128×128 变为 128×128×3，其中 3 表示三个连续的图像层。SWP I 到 STN 的 SNR 是 SWI 的两倍。在脑 QSM 图像和腹部 CT 图像中具有不规则形状和个体差异较大的胰腺小深部灰质核（RN、SN 和 STN）可以自动分割。
Zotero 插件