RESUMEN

Deformable medical image registration plays an essential role in clinical diagnosis and treatment. However, due to the large difference in image deformation, unsupervised convolutional neural network (CNN)-based methods cannot extract global features and local features simultaneously and cannot capture long-distance dependencies to solve the problem of excessive deformation. In this paper, an unsupervised end-to-end registration network is proposed for 3D MRI medical image registration, named AEAU-Net, which includes two-stage operations, i.e., an affine transformation and a deformable registration. These two operations are implemented by an affine transformation subnetwork and a deformable registration subnetwork, respectively. In the deformable registration subnetwork, termed as EAU-Net, we designed an efficient attention mechanism (EAM) module and a recursive residual path (RSP) module. The EAM module is embedded in the bottom layer of the EAU-Net to capture long-distance dependencies. The RSP model is used to obtain effective features by fusing deep and shallow features. Extensive experiments on two datasets, LPBA40 and Mindboggle101, were conducted to verify the effectiveness of the proposed method. Compared with baseline methods, this proposed method could obtain better registration performance. The ablation study further demonstrated the reasonability and validity of the designed architecture of the proposed method.

Asunto(s)

RESUMEN

The neural stem cells (NSCs) in the ventricular-subventricular zone of the adult mammalian spinal cord may be of great benefit for repairing spinal cord injuries. However, the sources of NSCs remain unclear. Previously, we have confirmed that cerebrospinal fluid-contacting neurons (CSF-cNs) have NSC potential in vitro. In this study, we verified the NSC properties of CSF-cNs in vivo. In mouse spinal cords, Pkd2l1+ CSF-cNs localized around the central canal express NSC markers. In vitro, Pkd2l1+ CSF-cNs form a neurosphere and express NSC markers. Activation and proliferation of CSF-cNs can be induced by injection of the neurotrophic factors basic fibroblast growth factor (bFGF) and vascular endothelial growth factor (VEGF) into the lateral ventricle. Spinal cord injury (SCI) also induces NSC activation and proliferation of CSF-cNs. Collectively, our results demonstrate that Pkd2l1+ CSF-cNs have NSC properties in vivo and may be involved in SCI recovery.