A Reproducible Evaluation of ANTs Similarity Metric Performance in Brain Image Registration

By Brian B. Avants, Nicholas J. Tustison, Gang Song, P. Cook, Arno Klein, James C. Gee. NeuroImage, 2010

4,637 citations recorded by the source corpus.

The United States National Institutes of Health (NIH) commit significant support to open-source data and software resources in order to foment reproducibility in the biomedical imaging sciences. Here, we report and evaluate a recent product of this commitment: Advanced Neuroimaging Tools (ANTs), which is approaching its 2.0 release. The ANTs open source software library consists of a suite of state-of-the-art image registration, segmentation and template building tools for quantitative morphometric analysis. In this work, we use ANTs to quantify, for the first time, the impact of similarity metrics on the affine and deformable components of a template-based normalization study. We detail the ANTs implementation of three similarity metrics: squared intensity difference, a new and faster cross-correlation, and voxel-wise mutual information. We then use two-fold cross-validation to compare their performance on openly available, manually labeled, T1-weighted MRI brain image data of 40 subjects (UCLA's LPBA40 dataset). We report evaluation results on cortical and whole brain labels for both the affine and deformable components of the registration. Results indicate that the best ANTs methods are competitive with existing brain extraction results (Jaccard=0.958) and cortical labeling approaches. Mutual information affine mapping combined with cross-correlation diffeomorphic mapping gave the best cortical labeling results (Jaccard=0.669±0.022). Furthermore, our two-fold cross-validation allows us to quantify the similarity of templates derived from different subgroups. Our open code, data and evaluation scripts set performance benchmark parameters for this state-of-the-art toolkit. This is the first study to use a consistent transformation framework to provide a reproducible evaluation of the isolated effect of the similarity metric on optimal template construction and brain labeling.

Subfields: Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/2dd32ff6608812d9b5d3877340df1cf9fceda08f

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Whole-brain imaging with single-cell resolution using chemical cocktails and computational analysis. (2014, neutral): “Because computational image analysis is so essential, informatics tools have been developed and implemented to facilitate this process in conventional human brain imaging (Avants et al., 2011).”
An Open Source Multivariate Framework for n-Tissue Segmentation with Evaluation on Public Data (2011, methodology): “Our prior work, (Avants et al. 2011), showed that the majority vote initialization provided to Atropos by ANTs template mapping is competitive with Heckemann et al.”
VoxelMorph: A Learning Framework for Deformable Medical Image Registration (2018, methodology): “We use the SyN implementation in the publicly available Advanced Normalization Tools (ANTs) software package [3], with a crosscorrelation similarity measure.”
CycleMorph: Cycle Consistent Unsupervised Deformable Image Registration (2020, methodology): “…Methods: In order to verify the improved performance of the proposed method, we employed several comparative methods that show the state-of-the-art performance in the image registration: Elastix [8], SyN [7] by Advanced Normalization Tools (ANTs) [36], VoxelMorph [16], and MS-DIRNet [18].”
3D Whole Brain Segmentation using Spatially Localized Atlas Network Tiles (2019, methodology): “With intensity harmonization [26], whole brain registrations [27], and multi-atlas label fusion (MALF), stateof-the-art MAS methods are able to segment brain from a”
A massive 7T fMRI dataset to bridge cognitive neuroscience and artificial intelligence (2021, methodology): “Data analysis and visualization were performed using custom code in MATLAB and Python as well as tools from various packages, such as FreeSurfer, SPM, FSL, ANTs 74 and ITK-SNAP 75 .”
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.”
A Correspondence between Individual Differences in the Brain's Intrinsic Functional Architecture and the Content and Form of Self-Generated Thoughts (2014, methodology): “A nonlinear transformation from T1 to MNI template (created from 152 subjects, 1 mm, provided with FSL) was calculated for individual T1 images using ANTs [57].”
The impact of T1 vs EPI spatial normalization templates for fMRI data analyses (2017, result): “ANTs has been demonstrably more accurate in published studies comparing T1 normalization strategies than standard voxelwise normalization [Avants and Gee, 2004; Avants et al., 2011].”
Deep learning in medical image registration: a survey (2019, methodology): “Their method outperforms ANTs based registration [6] and the deep learning based method described in [7].”
SCT: Spinal Cord Toolbox, an open‐source software for processing spinal cord MRI data (2017, methodology): “SliceReg (3rd order polynomial) was compared against ANTs (Avants et al., 2011) and FSL FLIRT (Jenkinson et al.”