NC-Reg : Neural Cortical Maps for Rigid Registration
This provides a robust pre-alignment strategy for cortical surfaces, which is critical in clinical settings, but it is incremental as it builds on existing registration techniques with a novel representation.
The paper tackled the problem of rigid registration of cortical surfaces by introducing neural cortical maps as a continuous neural representation, achieving runtimes up to 30 times faster than classic methods and sub-degree accuracy (<1° from the global optimum).
We introduce neural cortical maps, a continuous and compact neural representation for cortical feature maps, as an alternative to traditional discrete structures such as grids and meshes. It can learn from meshes of arbitrary size and provide learnt features at any resolution. Neural cortical maps enable efficient optimization on the sphere and achieve runtimes up to 30 times faster than classic barycentric interpolation (for the same number of iterations). As a proof of concept, we investigate rigid registration of cortical surfaces and propose NC-Reg, a novel iterative algorithm that involves the use of neural cortical feature maps, gradient descent optimization and a simulated annealing strategy. Through ablation studies and subject-to-template experiments, our method demonstrates sub-degree accuracy ($<1^\circ$ from the global optimum), and serves as a promising robust pre-alignment strategy, which is critical in clinical settings.