Performing Label-Fusion-Based Segmentation Using Multiple Automatically Generated Templates

By M. Mallar Chakravarty, P. Steadman, Matthijs C. Eede, Rebecca D. Calcott, Victoria Gu, P. Shaw, Armin Raznahan, D. Louis Collins, Jason P. Lerch. Human Brain Mapping, 2012

345 citations recorded by the source corpus.

Classically, model‐based segmentation procedures match magnetic resonance imaging (MRI) volumes to an expertly labeled atlas using nonlinear registration. The accuracy of these techniques are limited due to atlas biases, misregistration, and resampling error. Multi‐atlas‐based approaches are used as a remedy and involve matching each subject to a number of manually labeled templates. This approach yields numerous independent segmentations that are fused using a voxel‐by‐voxel label‐voting procedure. In this article, we demonstrate how the multi‐atlas approach can be extended to work with input atlases that are unique and extremely time consuming to construct by generating a library of multiple automatically generated templates of different brains (MAGeT Brain). We demonstrate the efficacy of our method for the mouse and human using two different nonlinear registration algorithms (ANIMAL and ANTs). The input atlases consist a high‐resolution mouse brain atlas and an atlas of the human basal ganglia and thalamus derived from serial histological data. MAGeT Brain segmentation improves the identification of the mouse anterior commissure (mean Dice Kappa values (κ = 0.801), but may be encountering a ceiling effect for hippocampal segmentations. Applying MAGeT Brain to human subcortical structures improves segmentation accuracy for all structures compared to regular model‐based techniques (κ = 0.845, 0.752, and 0.861 for the striatum, globus pallidus, and thalamus, respectively). Experiments performed with three manually derived input templates suggest that MAGeT Brain can approach or exceed the accuracy of multi‐atlas label‐fusion segmentation (κ = 0.894, 0.815, and 0.895 for the striatum, globus pallidus, and thalamus, respectively). Hum Brain Mapp 34:2635–2654, 2013. © 2012 Wiley Periodicals, Inc.

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

View Paper: https://www.semanticscholar.org/paper/13d2b5a31c9d2e6ef0e0c5f074bab08b28b823de

How researchers see this paper

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

In Biophysics

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Multi-atlas segmentation of the whole hippocampus and subfields using multiple automatically generated templates (2014, methodology): “Our group recently demonstrated that through the use of an intermediary automated segmentation stage, robust and reliable segmentation of the striatum, pallidum, and thalamus using a single atlas derived from serial histological data is possible (Chakravarty et al., 2013).”
BIDS apps: Improving ease of use, accessibility, and reproducibility of neuroimaging data analysis methods (2016, methodology): “…for NeuroImaging, for analysis of fMRI data. fMRI [38–41] MAGeTbrain Multiple Automatically Generated Templates brain segmentation algorithm T1w [42–45] tracula Automatic reconstruction of a set of major white-matter pathways from diffusion-weighted MR images T1w, DWI [46]…”
Lead-DBS v2: Towards a comprehensive pipeline for deep brain stimulation imaging (2018, neutral): “The intuitive understanding of the approach is that it increases robustness by introducing anatomical variance and the original authors showed this increased precision empirically in multiple studies (Chakravarty et al., 2012; Pipitone et al., 2014).”
Multi-Atlas Segmentation of Biomedical Images: A Survey (2014, methodology): “Finally, we have semi-supervised approaches that utilize the collection of novel images along with the atlases (Chakravarty et al., 2013; Gass et al., 2013; Jia et al., 2012; Liao et al., 2013; Shen et al., 2010; Wang and Yushke-vich, 2013a; Wolz et al., 2010a) For example, the LEAP algorithm (Wolz…”