A probabilistic model regularizes hidden layers across multiple depths of two CNNs to learn feature-level transformations for unsupervised 3D brain image registration and outperforms prior methods on benchmarks.
In: Advances in neural information processing systems
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2019 3verdicts
UNVERDICTED 3representative citing papers
Cycle-consistent CNN enables unsupervised 3D deformable registration of medical images, shown on liver CT for more accurate cancer size estimation.
Two training mechanisms for unsupervised deep registration networks reduce the number of locations with negative Jacobian determinants in predicted deformations.
citing papers explorer
-
Probabilistic Multilayer Regularization Network for Unsupervised 3D Brain Image Registration
A probabilistic model regularizes hidden layers across multiple depths of two CNNs to learn feature-level transformations for unsupervised 3D brain image registration and outperforms prior methods on benchmarks.
-
Unsupervised Deformable Image Registration Using Cycle-Consistent CNN
Cycle-consistent CNN enables unsupervised 3D deformable registration of medical images, shown on liver CT for more accurate cancer size estimation.
-
On Reducing Negative Jacobian Determinant of the Deformation Predicted by Deep Registration Networks
Two training mechanisms for unsupervised deep registration networks reduce the number of locations with negative Jacobian determinants in predicted deformations.