Cross-modal registration using point clouds and graph-matching in the context of correlative microscopies

TL;DR

This paper introduces a novel point cloud registration method using graph matching for correlative microscopy, addressing challenges of large, incomplete, and biased data sets, improving registration accuracy and efficiency.

Contribution

It proposes a graph-based registration approach for point clouds derived from biological images, handling density variations and outliers, advancing correlative microscopy workflows.

Findings

Graph matching outperforms ICP in accuracy.

Method effectively handles missing data and outliers.

Improves registration speed for large biological datasets.

Abstract

Correlative microscopy aims at combining two or more modalities to gain more information than the one provided by one modality on the same biological structure. Registration is needed at different steps of correlative microscopies workflows. Biologists want to select the image content used for registration not to introduce bias in the correlation of unknown structures. Intensity-based methods might not allow this selection and might be too slow when the images are very large. We propose an approach based on point clouds created from selected content by the biologist. These point clouds may be prone to big differences in densities but also missing parts and outliers. In this paper we present a method of registration for point clouds based on graph building and graph matching, and compare the method to iterative closest point based methods.