KLDivNet: An unsupervised neural network for multi-modality image registration
This addresses the challenge of accurate deformable registration for medical images without ground truth, though it appears incremental as it builds on existing CNN-based registration approaches.
The paper tackled the lack of voxel-wise ground truth in multi-modality image registration by proposing KLDivNet, an unsupervised neural network using a KL-divergence-based similarity metric, which achieved superior performance on three medical datasets compared to state-of-the-art methods.
Multi-modality image registration is one of the most underlined processes in medical image analysis. Recently, convolutional neural networks (CNNs) have shown significant potential in deformable registration. However, the lack of voxel-wise ground truth challenges the training of CNNs for an accurate registration. In this work, we propose a cross-modality similarity metric, based on the KL-divergence of image variables, and implement an efficient estimation method using a CNN. This estimation network, referred to as KLDivNet, can be trained unsupervisedly. We then embed the KLDivNet into a registration network to achieve the unsupervised deformable registration for multi-modality images. We employed three datasets, i.e., AAL Brain, LiTS Liver and Hospital Liver, with both the intra- and inter-modality image registration tasks for validation. Results showed that our similarity metric was effective, and the proposed registration network delivered superior performance compared to the state-of-the-art methods.