Performance of Image Registration Tools on High-Resolution 3D Brain Images

TL;DR

This study evaluates five free image registration tools on high-resolution 3D brain images, highlighting their accuracy and efficiency, and emphasizes the need for developing specialized methods for such large-scale data.

Contribution

It provides a comprehensive performance comparison of existing registration tools on large-scale 3D brain images, revealing their strengths and limitations.

Findings

ANTS offers the best accuracy.

Elastix is the most efficient with acceptable accuracy.

Current methods need optimization for high-resolution 3D images.

Abstract

Recent progress in tissue clearing has allowed for the imaging of entire organs at single-cell resolution. These methods produce very large 3D images (several gigabytes for a whole mouse brain). A necessary step in analysing these images is registration across samples. Existing methods of registration were developed for lower resolution image modalities (e.g. MRI) and it is unclear whether their performance and accuracy is satisfactory at this larger scale. In this study, we used data from different mouse brains cleared with the CUBIC protocol to evaluate five freely available image registration tools. We used several performance metrics to assess accuracy, and completion time as a measure of efficiency. The results of this evaluation suggest that the ANTS registration tool provides the best registration accuracy while Elastix has the highest computational efficiency among the methods with an acceptable accuracy. The results also highlight the need to develop new registration methods optimised for these high-resolution 3D images.