Meta-initialization speeds up deformable medical image registration
Meta-Initialization of Implicit Neural Representations to Accelerate Deformable Medical Image Registration
Computer Vision and Pattern RecognitionMachine Learning
Summary
Registering medical images, like matching one brain scan to another, often requires slow tuning for each new image pair. The authors study ways to start this tuning process faster by learning from many past registrations. They try two techniques that prepare the neural network before seeing new images, helping it adapt quicker. Their tests show both methods improve early results, with one being faster to train than the other.
What this means in practice
- •For medical imaging teams: Speed up image alignment tasks in brain scans by using pretrained network initializations to reduce time needed for pair-specific tuning.
- •For biomedical software developers: Develop faster software tools for deformable image registration by integrating learned initialization methods that improve early registration quality.
Tested on one dataset.
Authors
Marat O. Zinovev, Dmitry V. Sorokin
Abstract
Implicit neural representation (INR) methods for deformable medical image registration require the network parameters to be optimized for each new image pair, making adaptation speed a practical limitation. This work investigates whether early adaptation can be accelerated using an initialization learned from a collection of previously solved registration tasks. We examine two schemes: Reptile meta-initialization and STRAINER transfer of the shared component of a coordinate network. KAN-IDIR is used as the base INR displacement-field model. Experiments are conducted on OASIS-1, with 364 consecutive pairs used for training and 49 pairs for test-time adaptation. Registration quality is evaluated using mean Dice and HD95, together with the fraction of voxels with a negative Jacobian determinant at iteration 1500. In the configurations studied, both schemes yield higher Dice and lower HD95 at early iterations than random initialization. Reptile numerically outperforms STRAINER under a small iteration budget, although their pretraining budgets are not matched. As the number of iterations increases, the differences between the schemes shrink. STRAINER pretraining takes 39-40 minutes, compared with 44.98 hours for Reptile.