End-to-End Unsupervised Deformable Image Registration with a Convolutional Neural Network
This work addresses the need for faster deformable image registration in medical imaging and computer vision, offering a non-iterative solution that is incremental in applying deep learning to an existing task.
The authors tackled the problem of deformable image registration by proposing an end-to-end unsupervised convolutional neural network (DIRNet) that registers image pairs in a single pass. The method achieved accuracy comparable to conventional methods while significantly reducing execution times, as demonstrated on MNIST and cardiac MRI datasets.
In this work we propose a deep learning network for deformable image registration (DIRNet). The DIRNet consists of a convolutional neural network (ConvNet) regressor, a spatial transformer, and a resampler. The ConvNet analyzes a pair of fixed and moving images and outputs parameters for the spatial transformer, which generates the displacement vector field that enables the resampler to warp the moving image to the fixed image. The DIRNet is trained end-to-end by unsupervised optimization of a similarity metric between input image pairs. A trained DIRNet can be applied to perform registration on unseen image pairs in one pass, thus non-iteratively. Evaluation was performed with registration of images of handwritten digits (MNIST) and cardiac cine MR scans (Sunnybrook Cardiac Data). The results demonstrate that registration with DIRNet is as accurate as a conventional deformable image registration method with substantially shorter execution times.