Implicit Neural Representations for Deformable Image RegistrationDownload PDF

08 Dec 2021, 10:54 (edited 22 Jun 2022)MIDL 2022Readers: Everyone
  • Keywords: Image registration, neural networks, implicit neural representations, chest CT, regularization
  • TL;DR: We propose a deformable medical image registration approach in which the transformation function is represented as a differentiable neural network with periodic activation functions.
  • Abstract: Deformable medical image registration has in past years been revolutionized by deep learning with convolutional neural networks. These methods surpass conventional image registration techniques in speed but not in accuracy. Here, we present an alternative approach to leveraging neural networks for image registration. Instead of using a neural network to predict the transformation between images, we optimize a neural network to represent this continuous transformation. Using recent insights from differentiable rendering, we show how such an implicit deformable image registration (IDIR) model can be naturally combined with regularization terms based on standard automatic differentiation techniques. We demonstrate the effectiveness of this model on 4D chest CT registration in the DIR-LAB data set and find that a single three-layer multi-layer perceptron with periodic activation functions outperforms all published deep learning-based methods, without any folding and without the need for training data. The model is flexible enough to be extended to include different losses, regularizers, and optimization schemes and is implemented using standard deep learning libraries.
  • Registration: I acknowledge that publication of this at MIDL and in the proceedings requires at least one of the authors to register and present the work during the conference.
  • Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.
  • Paper Type: methodological development
  • Primary Subject Area: Image Registration
  • Secondary Subject Area: Application: Radiology
  • Confidentiality And Author Instructions: I read the call for papers and author instructions. I acknowledge that exceeding the page limit and/or altering the latex template can result in desk rejection.
  • Code And Data: Code: Data: Note that we do not have the right to provide this data, users will have to register on the DIRLAB website to obtain access to the data.
5 Replies