Multi-atlas Segmentation of Subcortical Brain Structures Via the AutoSeg Software Pipeline

Overview

Journal Front Neuroinform

Specialty Neurology

Date 2014 Feb 26

PMID 24567717

Citations 71

Authors

Jiahui Wang

Clement Vachet

Ashley Rumple

Sylvain Gouttard

Clementine Ouziel

Emilie Perrot

Guangwei Du

Xuemei Huang

Guido Gerig

Martin Styner

Affiliations

Soon will be listed here.

Abstract

Automated segmenting and labeling of individual brain anatomical regions, in MRI are challenging, due to the issue of individual structural variability. Although atlas-based segmentation has shown its potential for both tissue and structure segmentation, due to the inherent natural variability as well as disease-related changes in MR appearance, a single atlas image is often inappropriate to represent the full population of datasets processed in a given neuroimaging study. As an alternative for the case of single atlas segmentation, the use of multiple atlases alongside label fusion techniques has been introduced using a set of individual "atlases" that encompasses the expected variability in the studied population. In our study, we proposed a multi-atlas segmentation scheme with a novel graph-based atlas selection technique. We first paired and co-registered all atlases and the subject MR scans. A directed graph with edge weights based on intensity and shape similarity between all MR scans is then computed. The set of neighboring templates is selected via clustering of the graph. Finally, weighted majority voting is employed to create the final segmentation over the selected atlases. This multi-atlas segmentation scheme is used to extend a single-atlas-based segmentation toolkit entitled AutoSeg, which is an open-source, extensible C++ based software pipeline employing BatchMake for its pipeline scripting, developed at the Neuro Image Research and Analysis Laboratories of the University of North Carolina at Chapel Hill. AutoSeg performs N4 intensity inhomogeneity correction, rigid registration to a common template space, automated brain tissue classification based skull-stripping, and the multi-atlas segmentation. The multi-atlas-based AutoSeg has been evaluated on subcortical structure segmentation with a testing dataset of 20 adult brain MRI scans and 15 atlas MRI scans. The AutoSeg achieved mean Dice coefficients of 81.73% for the subcortical structures.

Citing Articles

Myelination across cortical hierarchies and depths in humans and macaques.

Nishio M, Liu X, Mackey A, Arcaro M bioRxiv. 2025; .

PMID: 39975294 PMC: 11839058. DOI: 10.1101/2025.02.06.636851.

Atypical functional connectivity between the amygdala and visual, salience regions in infants with genetic liability for autism.

Liu J, Girault J, Nishino T, Shen M, Kim S, Burrows C Cereb Cortex. 2024; 34(13):30-39.

PMID: 38696599 PMC: 11065105. DOI: 10.1093/cercor/bhae092.

A global multicohort study to map subcortical brain development and cognition in infancy and early childhood.

Alex A, Aguate F, Botteron K, Buss C, Chong Y, Dager S Nat Neurosci. 2023; 27(1):176-186.

PMID: 37996530 PMC: 10774128. DOI: 10.1038/s41593-023-01501-6.

Maternal Perinatal Stress Trajectories and Negative Affect and Amygdala Development in Offspring.

Marr M, Graham A, Feczko E, Nolvi S, Thomas E, Sturgeon D Am J Psychiatry. 2023; 180(10):766-777.

PMID: 37670606 PMC: 11646109. DOI: 10.1176/appi.ajp.21111176.

Extracellular free water elevations are associated with brain volume and maternal cytokine response in a longitudinal nonhuman primate maternal immune activation model.

Lesh T, Iosif A, Tanase C, Vlasova R, Ryan A, Bennett J Mol Psychiatry. 2023; 28(10):4185-4194.

PMID: 37582858 PMC: 10867284. DOI: 10.1038/s41380-023-02213-w.

References

Van Leemput K, Maes F, Vandermeulen D, Suetens P . Automated model-based tissue classification of MR images of the brain. IEEE Trans Med Imaging. 2000; 18(10):897-908. DOI: 10.1109/42.811270. View

Jia H, Wu G, Wang Q, Wang Y, Kim M, Shen D . Directed graph based image registration. Comput Med Imaging Graph. 2011; 36(2):139-51. PMC: 3272327. DOI: 10.1016/j.compmedimag.2011.09.001. View

Sled J, Zijdenbos A, Evans A . A nonparametric method for automatic correction of intensity nonuniformity in MRI data. IEEE Trans Med Imaging. 1998; 17(1):87-97. DOI: 10.1109/42.668698. View

Hazlett H, Poe M, Gerig G, Styner M, Chappell C, Smith R . Early brain overgrowth in autism associated with an increase in cortical surface area before age 2 years. Arch Gen Psychiatry. 2011; 68(5):467-76. PMC: 3315057. DOI: 10.1001/archgenpsychiatry.2011.39. View

Aljabar P, Heckemann R, Hammers A, Hajnal J, Rueckert D . Multi-atlas based segmentation of brain images: atlas selection and its effect on accuracy. Neuroimage. 2009; 46(3):726-38. DOI: 10.1016/j.neuroimage.2009.02.018. View

Hazlett H, Gu H, McKinstry R, Shaw D, Botteron K, Dager S . Brain volume findings in 6-month-old infants at high familial risk for autism. Am J Psychiatry. 2012; 169(6):601-8. PMC: 3744332. DOI: 10.1176/appi.ajp.2012.11091425. View

McClure R, Styner M, Maltbie E, Lieberman J, Gouttard S, Gerig G . Localized differences in caudate and hippocampal shape are associated with schizophrenia but not antipsychotic type. Psychiatry Res. 2012; 211(1):1-10. PMC: 3557605. DOI: 10.1016/j.pscychresns.2012.07.001. View

Tustison N, Johnson H, Rohlfing T, Klein A, Ghosh S, Ibanez L . Instrumentation bias in the use and evaluation of scientific software: recommendations for reproducible practices in the computational sciences. Front Neurosci. 2013; 7:162. PMC: 3766821. DOI: 10.3389/fnins.2013.00162. View

Khan A, Cherbuin N, Wen W, Anstey K, Sachdev P, Beg M . Optimal weights for local multi-atlas fusion using supervised learning and dynamic information (SuperDyn): validation on hippocampus segmentation. Neuroimage. 2011; 56(1):126-39. DOI: 10.1016/j.neuroimage.2011.01.078. View

10.

Prastawa M, Bullitt E, Moon N, Van Leemput K, Gerig G . Automatic brain tumor segmentation by subject specific modification of atlas priors. Acad Radiol. 2003; 10(12):1341-8. PMC: 2430604. DOI: 10.1016/s1076-6332(03)00506-3. View

11.

Sterling N, Du G, Lewis M, DiMaio C, Kong L, Eslinger P . Striatal shape in Parkinson's disease. Neurobiol Aging. 2013; 34(11):2510-6. PMC: 3742686. DOI: 10.1016/j.neurobiolaging.2013.05.017. View

12.

Asman A, Landman B . Non-local statistical label fusion for multi-atlas segmentation. Med Image Anal. 2012; 17(2):194-208. PMC: 3648421. DOI: 10.1016/j.media.2012.10.002. View

13.

Christensen G, Rabbitt R, Miller M . Deformable templates using large deformation kinematics. IEEE Trans Image Process. 1996; 5(10):1435-47. DOI: 10.1109/83.536892. View

14.

Van Leemput K, Maes F, Vandermeulen D, Suetens P . Automated model-based bias field correction of MR images of the brain. IEEE Trans Med Imaging. 2000; 18(10):885-96. DOI: 10.1109/42.811268. View

15.

Warfield S, Zou K, Wells W . Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation. IEEE Trans Med Imaging. 2004; 23(7):903-21. PMC: 1283110. DOI: 10.1109/TMI.2004.828354. View

16.

Wang H, Suh J, Das S, Pluta J, Craige C, Yushkevich P . Multi-Atlas Segmentation with Joint Label Fusion. IEEE Trans Pattern Anal Mach Intell. 2012; 35(3):611-23. PMC: 3864549. DOI: 10.1109/TPAMI.2012.143. View

17.

Asman A, Landman B . Robust statistical label fusion through COnsensus Level, Labeler Accuracy, and Truth Estimation (COLLATE). IEEE Trans Med Imaging. 2011; 30(10):1779-94. PMC: 3150602. DOI: 10.1109/TMI.2011.2147795. View

18.

Frey B, Dueck D . Clustering by passing messages between data points. Science. 2007; 315(5814):972-6. DOI: 10.1126/science.1136800. View

19.

Vovk U, Pernus F, Likar B . A review of methods for correction of intensity inhomogeneity in MRI. IEEE Trans Med Imaging. 2007; 26(3):405-21. DOI: 10.1109/TMI.2006.891486. View

20.

Gerig G, Oguz I, Gouttard S, Lee J, An H, Lin W . Synergy of image analysis for animal and human neuroimaging supports translational research on drug abuse. Front Psychiatry. 2011; 2:53. PMC: 3189614. DOI: 10.3389/fpsyt.2011.00053. View