NeuroNet: Fast and Robust Reproduction of Multiple Brain Image Segmentation Pipelines

TL;DR

NeuroNet is a deep learning model that efficiently reproduces multiple brain segmentation pipelines, significantly reducing processing time and increasing robustness, thus facilitating large-scale neuroimaging studies.

Contribution

It introduces a multi-output neural network trained on diverse segmentation labels, serving as an all-in-one tool that mimics several neuroimaging software packages.

Findings

Reduces processing time by an order of magnitude.

Maintains high reproducibility of original segmentation outputs.

Increases robustness to input data variations.

Abstract

NeuroNet is a deep convolutional neural network mimicking multiple popular and state-of-the-art brain segmentation tools including FSL, SPM, and MALPEM. The network is trained on 5,000 T1-weighted brain MRI scans from the UK Biobank Imaging Study that have been automatically segmented into brain tissue and cortical and sub-cortical structures using the standard neuroimaging pipelines. Training a single model from these complementary and partially overlapping label maps yields a new powerful "all-in-one", multi-output segmentation tool. The processing time for a single subject is reduced by an order of magnitude compared to running each individual software package. We demonstrate very good reproducibility of the original outputs while increasing robustness to variations in the input data. We believe NeuroNet could be an important tool in large-scale population imaging studies and serve as a new standard in neuroscience by reducing the risk of introducing bias when choosing a specific software package.