Automatic anatomical brain MRI segmentation combining label propagation and decision fusion

By Rolf A. Heckemann, Joseph V. Hajnal, Paul Aljabar, Daniel Rueckert, Alexander Hammers. NeuroImage, 2006

987 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/f5a29eb7f645fcbd6bf6016b6ec75f98d1fc95b1

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

Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registration (2009, background): “…(Gee et al., 1993; Jaccard, 1912), the intersection over the union: UO = ∑ r |Sr ∩ Tr|∑ r |Sr ∪ Tr| (4) UO can be converted to MO by the following (Heckemann et al., 2006): MO = 2× UO 1 + UO (5) To complement the above agreement measures, we also computed false negative (FN) and false…”
Multi-Atlas Segmentation with Joint Label Fusion (2012, methodology): “This method requires higher computational costs but, as extensive empirical studies have verified in the recent literature, e.g., [16], [3], [22], it is more accurate than single atlas-based segmentation.”
Performing Label-Fusion-Based Segmentation Using Multiple Automatically Generated Templates (2012, methodology): “While other voxel voting procedures exist [Heckemann et al., 2006], the evaluation of the best voxel-decision method is outside of the scope of this manuscript.”
A Generative Model for Image Segmentation Based on Label Fusion (2010, positive): “A detailed parcellation of the brain anatomy into structurally or functionally defined regions of interest (ROI) typically requires supervision, commonly in the form of labeled training data, since the local appearance of most such structures is not easily distinguishable [23], [30], [40], [51], [72”
VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images (2017, positive): “For example, multi-atlas label fusion (MALF) made use of multiple reference atlases and achieved good performance in brain segmentation tasks (Aljabar et al., 2009; Lötjönen et al., 2010; Wang et al., 2013; Heckemann et al., 2006).”
Inflammation after trauma: Microglial activation and traumatic brain injury (2011, methodology): “The procedure has previously been shown to yield accurate and robust segmentations in normal subjects and patients with dementia.(22,23) This approach minimizes the potential sampling error associated with misregistration and brain atrophy.”
The SRI24 Multi-Channel Atlas of Normal Adult Human Brain Structure (2009, result): “This is supported by increasing body of studies [e.g., Chou et al., 2008; Gousias et al., 2008; Heckemann et al., 2006; Klein and Hirsch, 2005; Klein et al., 2008; Rohlfing and Maurer, 2005; Rohlfing et al., 2004a,b; Svarer et al., 2005].”
A Fully Convolutional Neural Network for Cardiac Segmentation in Short-Axis MRI (2016, methodology): “…competition highlights the current interest in methods based on the multi-atlas segmentation framework (Rohlfing et al., 2004; Klein et al., 2005; Heckemann et al., 2006), which is becoming one of the most widely used and successful image segmentation techniques in medical imaging applications…”
volBrain: An Online MRI Brain Volumetry System (2015, background): “…label fusion segmentation techniques has gained in popularity because they can combine multiple atlas information, thereby minimizing mislabeling from inaccurate aﬃne or non-linear registration (Rohlﬁng et al., 2004; Heckemann et al., 2006; Collins and Pruessner, 2010; Lötjönen et al., 2010).”
Learning clinically useful information from images: Past, present and future (2016, methodology): “We have also shown that atlas selection plays an important role in this context: Choosing similar atlases is likely to lead to better segmentation performance [Heckemann et al. (2006)].”
Fully Automatic Hippocampus Segmentation and Classification in Alzheimer’s Disease and Mild Cognitive Impairment Applied on Data from ADNI (2009, positive): “Segmentation using probabilistic information (Fischl et al., 2002, Heckemann et al., 2006) offers more thorough global spatial knowledge compared to single object atlases.”
A dynamic 4D probabilistic atlas of the developing brain (2011, background): “More recently multi-atlas techniques are gaining popularity (Gousias et al., 2008; Heckemann et al., 2006; Rohlfing and Maurer, 2005; Rohlfing et al., 2004; Shi et al., 2010b; Warfield et al., 2004) because of their robustness and increased computational power available for processing of the…”
Combination Strategies in Multi-Atlas Image Segmentation: Application to Brain MR Data (2009, methodology): “This approach weights each candidate segmentation equally and assigns to each voxel the label that most segmentations agree on [10], [ 11 ].”
A review of atlas-based segmentation for magnetic resonance brain images (2011, methodology): “As for healthy elderly subjects, the strategies presented in the previous sections are also used on these cases [67,130–134].”
Non-commercial Research and Educational Use including without Limitation Use in Instruction at Your Institution, Sending It to Specific Colleagues That You Know, and Providing a Copy to Your Institution's Administrator. All Other Uses, Reproduction and Distribution, including without Limitation Comm (2005, neutral): “In order to describe the orientational order of the solute, the Saupe order matrix S kl is employed, with S kl defined as averages over reorientational motion of the second-order Legendre polynomials: S kl ¼ 1 2 < 3 cos h Z;k cos h Z;l À d kl > ð2Þ where h Z,k is the angle between the…”