Conditional Deformable Image Registration with Convolutional Neural Network
This addresses the efficiency problem for researchers and practitioners in medical imaging by reducing the computational burden of hyperparameter search in image registration.
The paper tackles the prohibitive cost of hyperparameter tuning in deep learning-based deformable image registration by proposing a conditional method that captures optimal solutions with arbitrary regularization parameters in a single network, enabling precise control of deformation field smoothness without sacrificing runtime or accuracy on a large-scale brain MRI dataset.
Recent deep learning-based methods have shown promising results and runtime advantages in deformable image registration. However, analyzing the effects of hyperparameters and searching for optimal regularization parameters prove to be too prohibitive in deep learning-based methods. This is because it involves training a substantial number of separate models with distinct hyperparameter values. In this paper, we propose a conditional image registration method and a new self-supervised learning paradigm for deep deformable image registration. By learning the conditional features that are correlated with the regularization hyperparameter, we demonstrate that optimal solutions with arbitrary hyperparameters can be captured by a single deep convolutional neural network. In addition, the smoothness of the resulting deformation field can be manipulated with arbitrary strength of smoothness regularization during inference. Extensive experiments on a large-scale brain MRI dataset show that our proposed method enables the precise control of the smoothness of the deformation field without sacrificing the runtime advantage or registration accuracy.