A Deep Metric for Multimodal Registration
This addresses the challenge of aligning images from different modalities for medical applications, representing an incremental advance in learning-based similarity measures.
The paper tackles the problem of multimodal registration in medical imaging by introducing a convolutional neural network-based metric that can be trained from scratch with few aligned image pairs, achieving significant improvement over mutual information in intersubject deformable registration.
Multimodal registration is a challenging problem in medical imaging due the high variability of tissue appearance under different imaging modalities. The crucial component here is the choice of the right similarity measure. We make a step towards a general learning-based solution that can be adapted to specific situations and present a metric based on a convolutional neural network. Our network can be trained from scratch even from a few aligned image pairs. The metric is validated on intersubject deformable registration on a dataset different from the one used for training, demonstrating good generalization. In this task, we outperform mutual information by a significant margin.