Towards accurate, automatic segmentation of the hippocampus and amygdala from MRI by augmenting ANIMAL with a template library and label fusion

Collins, D. Louis; Pruessner, Jens C.

doi:10.1016/j.neuroimage.2010.04.193

Cited by 212 publications

(264 citation statements)

References 58 publications

Supporting

Mentioning

245

Contrasting

Unclassified

Order By: Relevance

“…The latest published methods based on the nonlinear warping of the best templates and involving a label fusion step (Collins and Pruessner, 2010;Gousias et al, 2008;Lotjonen et al, 2010) obtained kappa index values equal to or greater than 0.88. As discussed by Aljabar et al (2009), the accuracy obtained with these techniques reach the limit of the variability of expert human raters.…”

Section: Discussionmentioning

confidence: 99%

“…Obtained by using the ADNI database of healthy subjects and patients with AD, these kappa index values indicate the high performance of these approaches. In our case, only the method proposed by Collins and Pruessner (2010) can be directly compared with our proposed one as they used the same database and the same validation framework. Collins and Pruessner (2010) obtained a median kappa index of 0.886 by nonlinearly registering the N = 11 closest subjects with ANIMAL (Collins et al, 1995) and by fusing the resulting label with a classical majority voting scheme.…”

Section: Discussionmentioning

confidence: 99%

“…Second, template-warping methods usually use a majority voting scheme to fuse the labels (Aljabar et al, 2009;Collins and Pruessner, 2010;Heckemann et al, 2006;Rohlfing et al, 2004) that considers the relevance (or weight) of all the samples labeled as similar. In the proposed method, the intensity-based distances between the patch under study and the patches in the training subjects are used to perform a weighted label fusion based on the nonlocal means estimator (Buades et al, 2005).…”

Section: Methods Overviewmentioning

confidence: 99%

See 2 more Smart Citations

Patch-based segmentation using expert priors: Application to hippocampus and ventricle segmentation

et al. 2011

Self Cite

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Methods Overviewmentioning

confidence: 99%

See 1 more Smart Citation

Patch-based segmentation using expert priors: Application to hippocampus and ventricle segmentation

et al. 2011

Self Cite

View full text Add to dashboard Cite

“…Building on recent work on label fusion (Aljabar et al, 2007;Collins and Pruessner, 2010;Heckemann et al, 2006), the multi-atlas propagation and segmentation (MAPS) method (Leung et al, 2010) was adapted to brain extraction to address the problem of variability in anatomy and acquisition, producing more robust results and leading to the best currently published results (Leung et al, 2011). In label fusion approaches, multiple atlases are selected from a library of Eskildsen et al, 2011 4 previously labelled images.…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, existing brain extraction methods often need to be adapted specifically for a certain type of study or, in the best case, need to be tuned to work on a certain population. A method that works reliably and robustly on a variety of different brain morphologies and acquisition sequences without requiring adjustment of parameters would greatly reduce the need for manual intervention and exclusion of subjects in neuroimaging studies.Building on recent work on label fusion (Aljabar et al, 2007;Collins and Pruessner, 2010;Heckemann et al, 2006), the multi-atlas propagation and segmentation (MAPS) method (Leung et al, 2010) was adapted to brain extraction to address the problem of variability in anatomy and acquisition, producing more robust results and leading to the best currently published results (Leung et al, 2011). In label fusion approaches, multiple atlases are selected from a library of Eskildsen et al, 2011 4 previously labelled images.…”

mentioning

confidence: 99%

BEaST: Brain extraction based on nonlocal segmentation technique

et al. 2012

Self Cite

View full text Add to dashboard Cite

-Brain extraction is an important step in the analysis of brain images. The variability in brain morphology and the difference in intensity characteristics due to imaging sequences make the development of a general purpose brain extraction algorithm challenging. To address this issue, we propose a new robust method (BEaST) dedicated to produce consistent and accurate brain extraction. This method is based on nonlocal segmentation embedded in a multi-resolution framework. A library of 80 priors is semi-automatically constructed from the NIH-sponsored MRI study of normal brain development, the International Consortium for Brain Mapping, and the Alzheimer's Disease Neuroimaging Initiative databases.In testing, a mean Dice similarity coefficient of 0.9834±0.0053 was obtained when performing leave-one-out cross validation selecting only 20 priors from the library. Validation using the online Segmentation Validation Engine resulted in a top ranking position with a mean Dice coefficient of 0.9781±0.0047. Robustness of BEaST is demonstrated on all baseline ADNI data, resulting in a very low failure rate. The segmentation accuracy of the method is better than two widely used publicly available methods and recent state-of-the-art hybrid approaches. BEaST provides results comparable to a recent label fusion approach, while being 40 times faster and requiring a much smaller library of priors.Keywords: Brain extraction, skull stripping, patch-based segmentation, multi-resolution, MRI, BET ** Data used in the preparation of this article were obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database (www.loni.ucla.edu/ADNI). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. IntroductionBrain extraction (or skull stripping) is an important step in many neuroimaging analyses, such as registration, tissue classification, and segmentation. While methods such as the estimation of intensity normalization fields and registration do not require perfect brain masks, other methods such as measuring cortical thickness rely on very accurate brain extraction to work properly. For instance, failure to remove the dura may lead to an overestimation of cortical thickness (van der Kouwe et al., 2008), while removing part of the brain would lead to an underestimation. In cases of incorrect brain extraction, subjects may be excluded from further processing, a potentially expensive consequence for many studies. The solution of manually correcting the brain masks is a labour intensive and time-consuming task that is highly sensitive to inter-and intra-rater variability (Warfield et al., 2004).An accurate brain extraction method should exclude all tissues external to the brain, such as skull, dura, and eyes, without removing any part of the brain. The number of methods proposed to address the brain segmentation problem reflects the importance of accurate and robust brain extraction. During th...

show abstract

The developing human brain: age‐related changes in cortical, subcortical, and cerebellar anatomy

et al. 2016

View full text Add to dashboard Cite

IntroductionThis study is the first to characterize normal development and sex differences across neuroanatomical structures in cortical, subcortical, and cerebellar brain regions in a single large cohort.MethodsOne hundred and ninety‐two magnetic resonance images were examined from 96 typically developing females and 96 age‐matched typically developing males from 4 to 18 years of age. Image segmentation of the cortex was conducted with CIVET, while that of the cerebellum, hippocampi, thalamus, and basal ganglia were conducted using the MAGeT algorithm.ResultsCortical thickness analysis revealed that most cortical regions decrease linearly, while surface area increases linearly with age. Volume relative to total cerebrum followed a quadratic trend with age, with only the left supramarginal gyrus showing sexual dimorphism. Hippocampal relative volume increased linearly, while the thalamus, caudate, and putamen decreased linearly, and the cerebellum did not change with age. The relative volumes of several subcortical subregions followed inverted U‐shaped trends that peaked at ~12 years of age. Many subcortical structures were found to be larger in females than in males, independently of age, while others showed a sex‐by‐age interaction.ConclusionThis study provides a comprehensive assessment of cortical, subcortical, and cerebellar growth patterns during normal development, and draws attention to the role of sex on neuroanatomical maturation throughout childhood and adolescence.

show abstract

Towards accurate, automatic segmentation of the hippocampus and amygdala from MRI by augmenting ANIMAL with a template library and label fusion

Cited by 212 publications

References 58 publications

Patch-based segmentation using expert priors: Application to hippocampus and ventricle segmentation

Patch-based segmentation using expert priors: Application to hippocampus and ventricle segmentation

BEaST: Brain extraction based on nonlocal segmentation technique

The developing human brain: age‐related changes in cortical, subcortical, and cerebellar anatomy

Contact Info

Product

Resources

About