An Open Source Multivariate Framework for n-Tissue Segmentation with Evaluation on Public Data

By Brian B. Avants, Nicholas J. Tustison, Jue Wu, P. Cook, James C. Gee. Neuroinformatics, 2011

583 citations recorded by the source corpus.

We introduce Atropos, an ITK-based multivariate n-class open source segmentation algorithm distributed with ANTs (http://www.picsl.upenn.edu/ANTs). The Bayesian formulation of the segmentation problem is solved using the Expectation Maximization (EM) algorithm with the modeling of the class intensities based on either parametric or non-parametric finite mixtures. Atropos is capable of incorporating spatial prior probability maps (sparse), prior label maps and/or Markov Random Field (MRF) modeling. Atropos has also been efficiently implemented to handle large quantities of possible labelings (in the experimental section, we use up to 69 classes) with a minimal memory footprint. This work describes the technical and implementation aspects of Atropos and evaluates its performance on two different ground-truth datasets. First, we use the BrainWeb dataset from Montreal Neurological Institute to evaluate three-tissue segmentation performance via (1) K-means segmentation without use of template data; (2) MRF segmentation with initialization by prior probability maps derived from a group template; (3) Prior-based segmentation with use of spatial prior probability maps derived from a group template. We also evaluate Atropos performance by using spatial priors to drive a 69-class EM segmentation problem derived from the Hammers atlas from University College London. These evaluation studies, combined with illustrative examples that exercise Atropos options, demonstrate both performance and wide applicability of this new platform-independent open source segmentation tool.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/4ef9872e2ea1828d2dfba099f4b1fa03a188db86

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Benchmarking of participant‐level confound regression strategies for the control of motion artifact in studies of functional connectivity (2017, methodology): “In confound regression model 10, tCompcor was implemented using ANTs, with 6 tCompCor components used as confound regressors for each participant.”
Mindboggling morphometry of human brains (2016, methodology): “gz) segmented file generated by the ANTs Atropos function [77] to binary files of pseudo-white matter and gray (including deep gray) matter.”
A review on automatic fetal and neonatal brain MRI segmentation (2017, unknown): “Wu and Avants (2012) presented a technique based on the Atropos tool (Avants et al., 2011).”
Training confounder-free deep learning models for medical applications (2020, methodology): “Based on the MR preprocessing pipeline described in the main article, tissue classification was performed by Atropos [2] resulting in Gray-Matter (GM), White-Matter (WM), and CerebroSpinal Fluid (CSF) masks for each T1w-MRI.”
Large-scale evaluation of ANTs and FreeSurfer cortical thickness measurements (2014, methodology): “Coupling the intrinsic symmetry of SyN pairwise registration (Avants et al., 2011a) and an optimized shape-based sharpening/averaging of the template appearance, Symmetric Group Normalization (SyGN) is a powerful framework for producing optimal population-specific templates.”
Statistical harmonization corrects site effects in functional connectivity measurements from multi-site fMRI data (2018, methodology): “T1-weighted (T1) images were processed using the ANTS Cortical Thickness pipeline available in the antsCorticalThickness.sh script in advanced normalization tools (ANTs; Avants et al., 2011a; Tustison et al., 2014).”
Harmonization of cortical thickness measurements across scanners and sites (2017, methodology): “For each participant, a tissue segmentation is performed using Atropos (Avants et al., 2011) to create six tissue masks: cerebrospinal ﬂ uid (CSF), grey matter (GM), white matter (WM), deep gray matter, brain stem, and cerebellum.”
Longitudinal multiple sclerosis lesion segmentation: Resource and challenge (2017, unknown): “%) data truncation (Avants et al., 2011).”