Abstract
The segmentation of brain region contours in three dimensions is critical for the analysis of different brain structures, and advanced approaches are emerging continuously within the field of neurosciences. With the development of high-resolution micro-optical imaging, whole-brain images can be acquired at the cellular level. However, brain regions in microscopic images are aggregated by discrete neurons with blurry boundaries, the complex and variable features of brain regions make it challenging to accurately segment brain regions. Manual segmentation is a reliable method, but is unrealistic to apply on a large scale. Here, we propose an automated brain region segmentation framework, DeepBrainSeg, which is inspired by the principle of manual segmentation. DeepBrainSeg incorporates three feature levels to learn local and contextual features in different receptive fields through a dual-pathway convolutional neural network (CNN), and to provide global features of localization by image registration and domain-condition constraints. Validated on biological datasets, DeepBrainSeg can not only effectively segment brain-wide regions with high accuracy (Dice ratio > 0.9), but can also be applied to various types of datasets and to datasets with noises. It has the potential to automatically locate information in the brain space on the large scale.
Highlights
Complex structures in the brain have the specificity for brain regions, which correspond to varying brain functions
We propose a framework inspired by the principle of manual segmentation, DeepBrainSeg, which automatically locates and segments brain regions incorporating three level features: local, contextual, and global
The other four datasets are a Nissl-stained C57BL/6 adult mouse imaged using a MicroOptical Sectioning Tomography (MOST) system (Li et al, 2010), a C57BL/6 mouse with autofluorescent signal imaged with a serial two-photon (STP) system (Ragan et al, 2012), a C57BL/6 adult mouse imaged with MR image model T2∗ (Johnson et al, 2010), and the Allen mouse common coordinate framework (Allen CCF v3 brain atlas) containing an 3D average brain image and a labeled brain region space
Summary
Complex structures in the brain have the specificity for brain regions, which correspond to varying brain functions. The maturation of techniques for high-resolution micro-optical imaging (Li et al, 2010; Ragan et al, 2012; Gong et al, 2016) has allowed comprehensive measurements of the distributions of fine structures in three-dimensional (3D) brain space. This has led to better understanding of brain structures, such as whole-brain neuron projections (Economo et al, 2016; Li et al, 2018), cellular and vascular distributions (Peng et al, 2017; Xiong et al, 2017). Neuroscientists urgently require an automated and accurate method that can segment brain regions at the cellular level
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
