The ANTsX ecosystem for quantitative biological and medical imaging

Nicholas J Tustison,Sandhitsu R Das,Gabriel A Devenyi,Hans J Johnson,James R Stone,Nicholas C Cullen,Andrew J Holbrook,James C Gee,Jeffrey T Duda,John Muschelli,Brian B Avants,Daniel L Gillen,Michael A Yassa,Philip A Cook

doi:10.1038/s41598-021-87564-6

Abstract

The Advanced Normalizations Tools ecosystem, known as ANTsX, consists of multiple open-source software libraries which house top-performing algorithms used worldwide by scientific and research communities for processing and analyzing biological and medical imaging data. The base software library, ANTs, is built upon, and contributes to, the NIH-sponsored Insight Toolkit. Founded in 2008 with the highly regarded Symmetric Normalization image registration framework, the ANTs library has since grown to include additional functionality. Recent enhancements include statistical, visualization, and deep learning capabilities through interfacing with both the R statistical project (ANTsR) and Python (ANTsPy). Additionally, the corresponding deep learning extensions ANTsRNet and ANTsPyNet (built on the popular TensorFlow/Keras libraries) contain several popular network architectures and trained models for specific applications. One such comprehensive application is a deep learning analog for generating cortical thickness data from structural T1-weighted brain MRI, both cross-sectionally and longitudinally. These pipelines significantly improve computational efficiency and provide comparable-to-superior accuracy over multiple criteria relative to the existing ANTs workflows and simultaneously illustrate the importance of the comprehensive ANTsX approach as a framework for medical image analysis.

Highlights

The Advanced Normalization Tools (ANTs) is a state-of-the-art, open-source software toolkit for image registration, segmentation, and other functionality for comprehensive biological and medical image analysis
Root mean square error (RMSE) between the actual and predicted ages are the quantity used for comparative evaluation
Given the excellent performance and superior computational efficiency of the proposed ANTsXNet pipeline for cross-sectional data, we evaluated its performance on longitudinal data using the longitudinally-specific evaluation strategy and data we employed with the introduction of the longitudinal version of the ANTs cortical thickness pipeline[41]

Summary

Introduction

The Advanced Normalization Tools (ANTs) is a state-of-the-art, open-source software toolkit for image registration, segmentation, and other functionality for comprehensive biological and medical image analysis. Used ANTs pipelines, such as cortical thickness e stimation[19], have been integrated into Docker containers and packaged as Brain Imaging Data Structure (BIDS)[22] and FlyWheel applications (i.e., “gears’ ’) It has been independently ported for various platforms including Neurodebian[23] (Debian OS), N euroconductor[24] (the R statistical project), and Nipype[25] (Python). Over the course of its development, ANTs has been extended to complementary frameworks resulting in the Python- and R-based ANTsPy and ANTsR toolkits, respectively These ANTs-based packages interface with extremely popular, high-level, open-source programming platforms which have significantly increased the user base of ANTs. The rapidly rising popularity of deep learning motivated further recent enhancement of ANTs and its extensions. We have included other models and weights into our libraries such as a recent BrainAGE estimation m odel[37], based on > 14, 000 individuals; H ippMapp3r38, a hippocampal segmentation tool; the winning entry of the MICCAI 2017 white matter hyperintensity segmentation c ompetition[39]; MRI super resolution using deep backprojection networks[40]; and NoBrainer, a T1-weighted brain extraction approach based on FreeSurfer (see Fig. 1)

Methods

Results

Conclusion