FireANTs: Adaptive Riemannian Optimization for Multi-Scale Diffeomorphic Registration

arXiv:2404.01249v1 Announce Type: new
Abstract: Diffeomorphic Image Registration is a critical part of the analysis in various imaging modalities and downstream tasks like image translation, segmentation, and atlas building. Registration algorithms based on optimization have stood the test of time in terms of accuracy, reliability, and robustness across a wide spectrum of modalities and acquisition settings. However, these algorithms converge slowly, are prohibitively expensive to run, and their usage requires a steep learning curve, limiting their scalability to larger clinical …

abstract accuracy algorithms analysis arxiv atlas building cs.cv image imaging optimization part registration reliability robustness scale segmentation spectrum tasks terms test translation type