Unsupervised End-to-end Learning for Deformable Medical Image Registration
share
We propose a registration algorithm for 2D CT/MRI medical images with a new unsupervised end-to-end strategy using convolutional neural networks. We also propose an effective way to introduce an ROI segmentation mask to our neural networks to improve performance. The contributions of our algorithm are threefold: (1) We transplant traditional image registration algorithms to an end-to-end convolutional neural network framework, while maintaining the unsupervised nature of image registration problems. The image-to-image integrated framework can simultaneously learn both image features and transformation matrix for registration. (2) An ROI segmentation mask is introduced to reduce background noise and hypothesize tissue locations, which leads to a significant boost in registration performance. (3) The registration speed is 100x faster than traditional methods. The proposed network is easy to implement and can be trained efficiently. Experiments demonstrate that our system achieves state-of-the-art results on 2D liver/brain registration. It can be extended to register other organs beyond liver and brain such as kidney, lung and heart.
READ FULL TEXT
