An Unsupervised Learning Model for Deformable Medical Image Registration
This work addresses the time-consuming nature of medical image registration for analysis pipelines, offering a significant speed-up, though it is incremental as it builds on existing learning-based approaches.
The paper tackles the problem of slow deformable 3D medical image registration by proposing an unsupervised learning-based algorithm that uses a convolutional neural network to learn registration parameters from a set of images, achieving accuracy comparable to state-of-the-art methods while operating orders of magnitude faster.
We present a fast learning-based algorithm for deformable, pairwise 3D medical image registration. Current registration methods optimize an objective function independently for each pair of images, which can be time-consuming for large data. We define registration as a parametric function, and optimize its parameters given a set of images from a collection of interest. Given a new pair of scans, we can quickly compute a registration field by directly evaluating the function using the learned parameters. We model this function using a convolutional neural network (CNN), and use a spatial transform layer to reconstruct one image from another while imposing smoothness constraints on the registration field. The proposed method does not require supervised information such as ground truth registration fields or anatomical landmarks. We demonstrate registration accuracy comparable to state-of-the-art 3D image registration, while operating orders of magnitude faster in practice. Our method promises to significantly speed up medical image analysis and processing pipelines, while facilitating novel directions in learning-based registration and its applications. Our code is available at https://github.com/balakg/voxelmorph .