Deformable Registration of Brain MR Images via a Hybrid Loss

2021/10/28 by Han, Luyi, Dou, Haoran, Huang, Yunzhi +1
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2110.15027

Abstract

Unsupervised learning strategy is widely adopted by the deformable registration models due to the lack of ground truth of deformation fields. These models typically depend on the intensity-based similarity loss to obtain the learning convergence. Despite the success, such dependence is insufficient. For the deformable registration of mono-modality image, well-aligned two images not only have indistinguishable intensity differences, but also are close in the statistical distribution and the boundary areas. Considering that well-designed loss functions can facilitate a learning model into a desirable convergence, we learn a deformable registration model for T1-weighted MR images by integrating multiple image characteristics via a hybrid loss. Our method registers the OASIS dataset with high accuracy while preserving deformation smoothness.

Related

• Deform-GAN:An Unsupervised Learning Model for Deformable Registration
• Correlation Ratio for Unsupervised Learning of Multi-modal Deformable Registration
• Unsupervised Deep-Learning Based Deformable Image Registration: A Bayesian Framework
• Conditional Deformable Image Registration with Convolutional Neural\n Network
• MsMorph: An Unsupervised pyramid learning network for brain image registration