Deep learning based brain MRI registration driven by local-signed-distance fields of segmentation maps

Abstract

Background: Deep learning based unsupervised registration utilizes the intensity information to align images. To avoid the influence of intensity variation and improve the registration accuracy, unsupervised and weakly-supervised registration are combined, namely, dually-supervised registration. However, the estimated dense deformation fields (DDFs) will focus on the edges among adjacent tissues when the segmentation labels are directly used to drive the registration progress, which will decrease the plausibility of brain MRI registration.

Purpose: In order to increase the accuracy of registration and ensure the plausibility of registration at the same time, we combine the local-signed-distance fields (LSDFs) and intensity images to dually supervise the registration progress. The proposed method not only uses the intensity and segmentation information but also uses the voxelwise geometric distance information to the edges. Hence, the accurate voxelwise correspondence relationships are guaranteed both inside and outside the edges.

Methods: The proposed dually-supervised registration method mainly includes three enhancement strategies. Firstly, we leverage the segmentation labels to construct their LSDFs to provide more geometrical information for guiding the registration process. Secondly, to calculate LSDFs, we construct an LSDF-Net, which is composed of 3D dilation layers and erosion layers. Finally, we design the dually-supervised registration network (VM_LSDF ) by combining the unsupervised VoxelMorph (VM) registration network and the weakly-supervised LSDF-Net, to utilize intensity and LSDF information, respectively.

Results: In this paper, experiments were then carried out on four public brain image datasets: LPBA40, HBN, OASIS1, and OASIS3. The experimental results show that the Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD) of VM_LSDF are higher than those of the original unsupervised VM and the dually-supervised registration network (VM_seg ) using intensity images and segmentation labels. At the same time, the percentage of negative Jacobian determinant (NJD) of VM_LSDF is lower than VM_seg . Our code is freely available at https://github.com/1209684549/LSDF.

Conclusions: The experimental results show that LSDFs can improve the registration accuracy compared with VM and VM_seg , and enhance the plausibility of the DDFs compared with VM_seg .

Keywords: deep learning; local-signed-distance fields; medical image registration.