Deepbet: Fast brain extraction of T1-weighted MRI using Convolutional Neural Networks

TL;DR

Deepbet is a fast, high-precision brain extraction tool for T1-weighted MRI that leverages deep learning, achieving state-of-the-art accuracy and significantly faster processing times.

Contribution

This paper introduces deepbet, a novel deep learning-based brain extraction method using LinkNet architecture, achieving superior accuracy and speed over existing methods.

Findings

Median Dice score of 99.0% on unseen datasets

Outperforms current state-of-the-art models in accuracy

Accelerates processing by a factor of ~10

Abstract

Brain extraction in magnetic resonance imaging (MRI) data is an important segmentation step in many neuroimaging preprocessing pipelines. Image segmentation is one of the research fields in which deep learning had the biggest impact in recent years enabling high precision segmentation with minimal compute. Consequently, traditional brain extraction methods are now being replaced by deep learning-based methods. Here, we used a unique dataset comprising 568 T1-weighted (T1w) MR images from 191 different studies in combination with cutting edge deep learning methods to build a fast, high-precision brain extraction tool called deepbet. deepbet uses LinkNet, a modern UNet architecture, in a two stage prediction process. This increases its segmentation performance, setting a novel state-of-the-art performance during cross-validation with a median Dice score (DSC) of 99.0% on unseen datasets, outperforming current state of the art models (DSC = 97.8% and DSC = 97.9%). While current methods are more sensitive to outliers, resulting in Dice scores as low as 76.5%, deepbet manages to achieve a Dice score of > 96.9% for all samples. Finally, our model accelerates brain extraction by a factor of ~10 compared to current methods, enabling the processing of one image in ~2 seconds on low level hardware.