Deformable Registration of Whole Brain Zebrafish Microscopy Using an Implementation of the Flash Algorithm Within Ants

Abstract

Recent advancements in microscopy, protein engineering, and genetics have rendered the larval zerbrafish a powerful model system for which whole brain, real time, functional neuroimaging at cellular resolution is accessible. Supplementing functional data with additional modalities in the same fish such as structural connectivity and transcriptomics will enable interpretation of structure-function relationships across the entire brains of individual animals. However, proper identification of corresponding cells in the large image volumes produced depends on accurate and efficient deformable registration. To address this challenge, we implemented the Fourier-approximated Lie Algebras for Shooting (FLASH) algorithm within the well-known Advanced Normalization Tools (ANTs) package. This combines the speed of FLASH with the extensive set of image matching functionals and multi-staging multi-resolution capabilities of ANTs. We registered longitudinal data from nine fish, using a line that uniquely identifies subsets of neurons in an independent channel. We validate our approach by demonstrating accurate cell-to-cell correspondence while requiring significantly less time and memory than the Symmetric Normalization (SyN) implementation in ANTs, and without compromising the theoretical foundations of the Large Deformation Diffeomorphic Metric Mapping (LDDMM) model.