Implicit neural representations for joint decomposition and registration of gene expression images in the marmoset brain

TL;DR

This paper introduces a novel implicit neural representation method for joint image registration and decomposition, effectively aligning gene expression images of the marmoset brain despite artifacts and structural variations.

Contribution

It presents a new registration approach combining implicit neural networks with an image exclusion loss to improve alignment and decomposition of complex brain images.

Findings

Outperforms existing registration techniques.

Successfully decomposes images into support and residual components.

Demonstrates effectiveness on 2D gene expression images of marmoset brains.

Abstract

We propose a novel image registration method based on implicit neural representations that addresses the challenging problem of registering a pair of brain images with similar anatomical structures, but where one image contains additional features or artifacts that are not present in the other image. To demonstrate its effectiveness, we use 2D microscopy $\textit{in situ}$ hybridization gene expression images of the marmoset brain. Accurately quantifying gene expression requires image registration to a brain template, which is difficult due to the diversity of patterns causing variations in visible anatomical brain structures. Our approach uses implicit networks in combination with an image exclusion loss to jointly perform the registration and decompose the image into a support and residual image. The support image aligns well with the template, while the residual image captures individual image characteristics that diverge from the template. In experiments, our method provided excellent results and outperformed other registration techniques.