Convolutional neural network MRI segmentation for fast and robust optimization of transcranial electrical current stimulation of the human brain

Convolutional neural network MRI segmentation for fast and robust optimization of transcranial electrical current stimulation of the human brain

Publication date: Feb 12, 2020

The segmentation of structural MRI data is an essential step for deriving geometrical information about brain tissues. One important application is in transcranial electrical stimulation (e.g., tDCS), a non-invasive neuromodulatory technique where head modeling is required to determine the electric field (E-field) generated in the cortex to predict and optimize its effects. Here we propose a deep learning-based model (StarNEt) to automatize white matter (WM) and gray matter (GM) segmentation and compare its performance with FreeSurfer, an established tool. Since good definition of sulci and gyri in the cortical surface is an important requirement for E-field calculation, StarNEt is specifically designed to output masks at a higher resolution than that of the original input T1w-MRI. StarNEt uses a residual network as the encoder (ResNet) and a fully convolutional neural network with U-net skip connections as the decoder to segment an MRI slice by slice. Slice vertical location is provided as an extra input. The model was trained on scans from 425 patients in the open-access ADNI+IXI datasets, and using FreeSurfer segmentation as ground truth. Model performance was evaluated using the Dice Coefficient (DC) in a separate subset (N=105) of ADNI+IXI and in two extra testing sets not involved in training. In addition, FreeSurfer and StarNEt were compared to manual segmentations of the MRBrainS18 dataset, also unseen by the model. To study performance in real use cases, first, we created electrical head models derived from the FreeSurfer and StarNEt segmentations and used them for montage optimization with a common target region using a standard algorithm (Stimweaver) and second, we used StarNEt to successfully segment the brains of minimally conscious state (MCS) patients having suffered from brain trauma, a scenario where FreeSurfer typically fails. Our results indicate that StarNEt matches FreeSurfer performance on the trained tasks while reducing computation time from several hours to a few seconds, and with the potential to evolve into an effective technique even when patients present large brain abnormalities.

PDF

Concepts Keywords
Algorithm Good optimal solution
Anisotropy Segmentation algorithms
Atlas Optimization algorithm
Barcelona Surface processing hourson
Boston Skull defects
Brain Convolutional neural network
Brain Trauma Usinga standard algorithm
Cerebrospinal Fluid Genetic algorithm
CNN Discriminative neural network
Convolution Neuroimaging
Convolutional Neural Network Contents
Cortex Publishing
Cortical Academia
Deep Learning FreeSurfer
Deformation Analyze
E Field Image segmentation
Electrical Conductivity Preprint
Electrical Current CT scan
Electrode Magnetic resonance imaging
Ethnic Group Starnet
FEM BioRxiv
Finite Element Adam
Force Av
Geometry Html
Gray Matter Image processing
Gyri MRI
Harvard Neural network
Hebrew Segmentation algorithms
Henschel
Image Segmentation
Liege
Memory
Metric
MRI
Neural Network
Neural Networks
Neuromodulatory
Ona
Open Access
Optimization
Pipeline
Resonance
Roslindale
Sagittal
Scalp
Semantic
Skull
Spatial Resolution
Sulci
TDCS
Tibidabo
Topology
Ventricles
Vivo
Voxel
White Matter

Semantics

Type Source Name
disease MESH minimally conscious state
disease MESH abnormalities

Download Document

Leave a Comment

Your email address will not be published. Required fields are marked *