Privacy Preserving Image Registration

@article{Taiello2022PrivacyPI,
  title={Privacy Preserving Image Registration},
  author={Riccardo Taiello and Melek {\"O}nen and Olivier Humbert and Marco Lorenzi},
  journal={ArXiv},
  year={2022},
  volume={abs/2205.10120}
}
. Image registration is a key task in medical imaging applica-tions, allowing to represent medical images in a common spatial reference frame. Current literature on image registration is generally based on the assumption that images are usually accessible to the researcher, from which the spatial transformation is subsequently estimated. This common assumption may not be met in current practical applications, since the sensitive nature of medical images may ultimately require their analysis… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 30 REFERENCES
A Systematic Comparison of Encrypted Machine Learning Solutions for Image Classification
TLDR
This work designed three neural network architecture to obtain secure predictions via each of the four aforementioned frameworks, aiming to evaluate the suitability of these frameworks from a usability, runtime requirements and accuracy point of view.
ON DATA BANKS AND PRIVACY HOMOMORPHISMS
TLDR
It appears likely that there exist encryption functions which permit encrypted data to be operated on without preliminary decryption of the operands, for many sets of interesting operations.
Image Registration with Sparse Approximations in Parametric Dictionaries
TLDR
This paper proposes a registration algorithm that looks for an estimate of the global transformation between sparse images by examining the set of relative geometrical transformations between the respective features and derives performance guarantees based on two novel important properties of redundant dictionaries.
VoxelMorph: A Learning Framework for Deformable Medical Image Registration
TLDR
VoxelMorph promises to speed up medical image analysis and processing pipelines while facilitating novel directions in learning-based registration and its applications and demonstrates that the unsupervised model’s accuracy is comparable to the state-of-the-art methods while operating orders of magnitude faster.
Learning a Probabilistic Model for Diffeomorphic Registration
TLDR
The unsupervised method uses a conditional variational autoencoder network and constrain transformations to be symmetric and diffeomorphic by applying a differentiable exponentiation layer with a symmetric loss function and provides multi-scale velocity field estimations.
Non-local Shape Descriptor: A New Similarity Metric for Deformable Multi-modal Registration
TLDR
A new similarity metric for multi-modal registration, the non-local shape descriptor, that is robust against the most considerable differences between modalities, such as non-functional intensity relations, different amounts of noise and non-uniform bias fields is proposed.
A generic framework for privacy preserving deep learning
TLDR
A new framework for privacy preserving deep learning that allows one to implement complex privacy preserving constructs such as Federated Learning, Secure Multiparty Computation, and Differential Privacy while still exposing a familiar deep learning API to the end-user is detailed.
Alignment by Maximization of Mutual Information
TLDR
A new information-theoretic approach is presented for finding the pose of an object in an image that works well in domains where edge or gradient-magnitude based methods have difficulty, yet it is more robust than traditional correlation.
Multiparty Computation from Somewhat Homomorphic Encryption
We propose a general multiparty computation protocol secure against an active adversary corrupting up to $$n-1$$ of the n players. The protocol may be used to compute securely arithmetic circuits
...
...