FastSurfer -- A fast and accurate deep learning based neuroimaging pipeline

Abstract

Traditional neuroimage analysis pipelines involve computationally intensive, time-consuming optimization steps, and thus, do not scale well to large cohort studies with thousands or tens of thousands of individuals. In this work we propose a fast and accurate deep learning based neuroimaging pipeline for the automated processing of structural human brain MRI scans, replicating FreeSurfer's anatomical segmentation including surface reconstruction and cortical parcellation. To this end, we introduce an advanced deep learning architecture capable of whole brain segmentation into 95 classes. The network architecture incorporates local and global competition via competitive dense blocks and competitive skip pathways, as well as multi-slice information aggregation that specifically tailor network performance towards accurate segmentation of both cortical and sub-cortical structures. Further, we perform fast cortical surface reconstruction and thickness analysis by introducing a spectral spherical embedding and by directly mapping the cortical labels from the image to the surface. This approach provides a full FreeSurfer alternative for volumetric analysis (in under 1 minute) and surface-based thickness analysis (within only around 1h runtime). For sustainability of this approach we perform extensive validation: we assert high segmentation accuracy on several unseen datasets, measure generalizability and demonstrate increased test-retest reliability, and high sensitivity to group differences in dementia.

Submitted to NeuroImage

References in corpus (16)

• Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
• Brain Tumor Segmentation with Deep Neural Networks
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Automatic segmentation of MR brain images with a convolutional neural network
• 3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study
• Predicting Alzheimer's disease: a neuroimaging study with 3D convolutional neural networks
• DeepNAT: Deep Convolutional Neural Network for Segmenting Neuroanatomy
• Alzheimer's Disease Diagnostics by Adaptation of 3D Convolutional Network
• Deep Generative Adversarial Networks for Compressed Sensing Automates MRI
• FatSegNet : A Fully Automated Deep Learning Pipeline for Adipose Tissue Segmentation on Abdominal Dixon MRI
• Deep Neural Network with l2-norm Unit for Brain Lesions Detection
• Competition vs. Concatenation in Skip Connections of Fully Convolutional Networks
• Brain Tumor Detection and Classification with Feed Forward Back-Prop Neural Network
• Real-time Dynamic MRI Reconstruction using Stacked Denoising Autoencoder
• Complex Fully Convolutional Neural Networks for MR Image Reconstruction
• Semi-supervised Learning using Denoising Autoencoders for Brain Lesion Detection and Segmentation

Cited by in corpus (27)

• Robust machine learning segmentation for large-scale analysis of heterogeneous clinical brain MRI datasets
• Automatic autism spectrum disorder detection using artificial intelligence methods with MRI neuroimaging: A review
• FastSurferVINN: Building Resolution-Independence into Deep Learning Segmentation Methods -- A Solution for HighRes Brain MRI
• Cortical surface registration using unsupervised learning
• Deep Learning for Neuroimaging-based Diagnosis and Rehabilitation of Autism Spectrum Disorder: A Review
• Quantifying human gray matter microstructure using NEXI and 300 mT/m gradients
• FastSurfer-HypVINN: Automated sub-segmentation of the hypothalamus and adjacent structures on high-resolutional brain MRI
• Influence of segmentation accuracy in structural MR head scans on electric field computation for TMS and tES
• Whole Brain Segmentation with Full Volume Neural Network
• Fighting the scanner effect in brain MRI segmentation with a progressive level-of-detail network trained on multi-site data
• Axial multi-layer perceptron architecture for automatic segmentation of choroid plexus in multiple sclerosis
• Exploring contrast generalisation in deep learning-based brain MRI-to-CT synthesis
• Automated Olfactory Bulb Segmentation on High Resolutional T2-Weighted MRI
• MeDaS: An open-source platform as service to help break the walls between medicine and informatics
• DeepRetinotopy: Predicting the Functional Organization of Human Visual Cortex from Structural MRI Data using Geometric Deep Learning
• UNISELF: A Unified Network with Instance Normalization and Self-Ensembled Lesion Fusion for Multiple Sclerosis Lesion Segmentation
• Label merge-and-split: A graph-colouring approach for memory-efficient brain parcellation
• PialNN: A Fast Deep Learning Framework for Cortical Pial Surface Reconstruction
• DBSegment: Fast and robust segmentation of deep brain structures -- Evaluation of transportability across acquisition domains
• Effects of disease duration and antipsychotics on brain age in schizophrenia
• Gray Matter Segmentation in Ultra High Resolution 7 Tesla ex vivo T2w MRI of Human Brain Hemispheres
• Subcortical Masks Generation in CT Images via Ensemble-Based Cross-Domain Label Transfer
• POLAFFINI: Efficient feature-based polyaffine initialization for improved non-linear image registration
• Identifying and Combating Bias in Segmentation Networks by leveraging multiple resolutions
• Beyond one-hot encoding? Journey into compact encoding for large multi-class segmentation
• Label tree semantic losses for rich multi-class medical image segmentation
• Structural MRI Synthesis for Alzheimer's Disease via Conditional Diffusion on Anatomical Masks