Learning Multi-Modal Image Registration without Real Data
share
We introduce a learning-based strategy for multi-modal registration of images acquired with any modality, without requiring real data during training. While classical registration methods can accurately align multi-modal image pairs, they solve a costly optimization problem for every new pair of images. Learning-based techniques are fast at test time, but can only register images of the specific anatomy and modalities they were trained on. In contrast, our approach leverages a generative model to synthesize label maps and gray-scale images that expose a network to a wide range of anatomy and contrast during training. We demonstrate that this strategy enables robust registration of arbitrary modalities, without the need to retrain for a new modality. Critically, we show that input labels need not be of actual anatomy: training on randomly synthesized shapes, or supervoxels, results in competitive registration performance and makes the network agnostic to anatomy and contrast, all while eradicating the need for real data. We present extensive experiments demonstrating that this strategy enables registration of modalities not seen during training and surpasses the state of art in cross-contrast registration. Our code is integrated with the VoxelMorph library at: http://voxelmorph.csail.mit.edu
READ FULL TEXT
