Developing Brain Atlas through Deep Learning

TL;DR

This paper introduces SeBRe, a deep learning method for automated brain region segmentation that addresses variability in brain size and form, enabling efficient registration across different species and developmental stages.

Contribution

The paper presents a novel deep neural network approach for brain registration that requires minimal supervision and works across multiple imaging modalities and species.

Findings

Validated on mouse developmental brain images with various markers

Successfully applied to human MR brain images

Outperforms traditional registration methods in speed and accuracy

Abstract

Neuroscientists have devoted significant effort into the creation of standard brain reference atlases for high-throughput registration of anatomical regions of interest. However, variability in brain size and form across individuals poses a significant challenge for such reference atlases. To overcome these limitations, we introduce a fully automated deep neural network-based method (SeBRe) for registration through Segmenting Brain Regions of interest with minimal human supervision. We demonstrate the validity of our method on brain images from different mouse developmental time points, across a range of neuronal markers and imaging modalities. We further assess the performance of our method on images from MR-scanned human brains. Our registration method can accelerate brain-wide exploration of region-specific changes in brain development and, by simply segmenting brain regions of interest for high-throughput brain-wide analysis, provides an alternative to existing complex brain registration techniques.