Medical Image Synthesis with Deep Convolutional Adversarial Networks
We propose a generative adversarial approach to address the medical image synthesis problem. Specifically, we train a fully convolutional network (FCN) to generate a target image given a source image. To produce more realistic image, we propose to use adversarial learning strategy to better model the FCN. Moreover, an image-gradient-difference based loss function is proposed to avoid generating blurry images. Also, a long-term residual unit is explored to help the training of the network. We further apply auto-context model to implement a context-aware framework. Experimental results show the robustness and accuracy of our method in synthesizing various medical images.
Deformable Image Registration Using Cue-aware Deep Regression Network
We propose a novel deformable registration method of using the deep neural network to directly learn the mapping from an image pair to the corresponding deformation field. This highly non-linear mapping is modeled by the novel cue-aware deep regression network, in which we adopt contextual cue to better guide the learning process…
Structured Learning for 3D Perivascular Spaces Segmentation Using Vascular Features
In this study, we propose a structured-learning-based segmentation framework to extract the perivascular spaces (PVSs) from high-resolution 7T MR images. Specifically, we integrate three types of vascular filter responses into a structured random forest for classifying each voxel into two categories.