Robust Brain Extraction Across Datasets and Comparison With Publicly Available Methods

By Juan Eugenio Iglesias, Cheng-Yi Liu, Paul M. Thompson, Zhuowen Tu. 2011

595 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Neurology

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

1. José Vicente Manjón
2. Pierrick Coupé
3. Klaus Hermann Maier-Hein
4. Fabian Isensee
5. Shadi Albarqouni
6. Martin Bendszus
7. Wolfgang Wick
8. P. Kickingereder

In Neurology

1. Klaus Hermann Maier-Hein
2. Heinz-Peter Schlemmer
3. Neil A. Tenenholtz
4. Fabian Isensee

Citations in the corpus

• SynthStrip: skull-stripping for any brain image (2022, unknown): “Classical, or traditional, algorithms that remove non-brain image signal vary substantially in their implementation (Cox, 1996; Eskildsen et al., 2012; Iglesias et al., 2011; Roy et al., 2017; S´egonne et al., 2004; Shattuck et al., 2001; Smith, 2002).”
• Deep MRI brain extraction: A 3D convolutional neural network for skull stripping (2016, methodology): “Volumetric measures already utilized in several studies (FennemaNotestine et al., 2006; Galdames et al., 2012; Iglesias et al., 2011; Rex et al., 2004; Wang et al., 2014) were used to compare a predicted brain segmentation Pwith the associated referencemask R.”
• Random forest-based similarity measures for multi-modal classification of Alzheimer's disease (2013, unknown): “Random forests have not been extensively applied in neuroimaging research, although they are becoming more widely used for applications including classification (Hope et al., 2008; Chincarini et al., 2011) and segmentation (Geremia et al., 2011; Iglesias et al., 2011).”
• Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A Comparative Study (2020, methodology): “In succession, the scans have been skull-stripped with ROBEX [21] and denoised with CurvatureFlow [22].”
• BEaST: Brain extraction based on nonlocal segmentation technique (2012, methodology): “We chose to compare with BET, as BET is publicly available, widely used, and has been shown to perform well in several recent brain extraction comparisons (Carass et al., 2011; Iglesias et al., 2011; Leung et al., 2011).”
• Automated brain extraction of multisequence MRI using artificial neural networks (2019, methodology): “…available and frequently used brain extraction algorithms, namely, BET (Smith, 2002), 3dSkullStrip (Cox, 1996), BSE (Shattuck & Leahy, 2002), ROBEX (Iglesias et al., 2011), BEaST (Eskildsen et al., 2012), and MONSTR (Roy, et al., 2017) (see Methods S1, Supporting Information for detailed…”
• Medical Image Synthesis for Data Augmentation and Anonymization using Generative Adversarial Networks (2018, methodology): “As a pre-processing step, we perform skull-stripping [11] on the ADNI data set as skulls are not present in the BRATS data set.”
• Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review (2017, methodology): “Among the different methods proposed in the literature for skull-stripping [103, 100, 104], methods such as BET [105, 106], BSE [107], ROBEX [108] and BEaST [109] are commonly used.”