A nonparametric method for automatic correction of intensity nonuniformity in MRI data

By John G. Sled, Alex P. Zijdenbos, Alan C. Evans. 1998

How researchers see this paper

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

Citations in the corpus

Interpreting support vector machine models for multivariate group wise analysis in neuroimaging (2015, neutral): “The preprocessing protocols included a) skull removal using the BET algorithm (Smith, 2002) b) n3 bias correction using N3(Sled et al., 1998) c) segmentation using adaptive k-means (Pham and Prince, 1999) d) registration to a common template and generation of RAVENS maps using the (Davatzikos et…”
Maternal cortisol over the course of pregnancy and subsequent child amygdala and hippocampus volumes and affective problems (2012, methodology): “The native anatomic images were processed before manual volume segmentation tofirst correct for intensity nonuniformity (85).”
Deep ensemble learning of sparse regression models for brain disease diagnosis (2017, methodology): “Specifically, e used MIPAV software 2 for AC-PC correction, resampled images o 256 × 256 × 256, and applied N3 algorithm ( Sled et al., 1998 ) o correct intensity inhomogeneity.”
Automatic "pipeline" analysis of 3-D MRI data for clinical trials: application to multiple sclerosis (2002, background): “[38], which was shown to be accurate and robust [41], [42].”
Convolutional Neural Networks for Classification of Alzheimer's Disease: Overview and Reproducible Evaluation (2019, methodology): “registration ( Vovk et al., 2007). Several methods exist to correct these intensity inhomogeneities, two popular ones being the nonparametric nonuniformity intensity normalization (N3) algorithm ( Sled et al., 1998), available for example in the Freesurfer software package1, and the N4 algorithm ( T”
Unique developmental trajectories of cortical thickness and surface area (2014, unknown): “…matter, deep gray matter structures and cerebellar structures (Fischl et al., 2004a,b; Hutton et al., 2009; Salat, 2004), intensity normalization (Sled et al., 1998); tessellation of gray white matter boundary automated topology correction (Fischl et al., 2001; Segonne et al., 2007), and surface…”
Multi-spectral brain tissue segmentation using automatically trained k-Nearest-Neighbor classification (2007, methodology): “Automated processing tools from the Brain Imaging Center, Montreal Neurological Institute (MNI) and McGill University (www.bic.mni.mcgill.ca) were used to co-register the MRI data (based on mutual information) and to correct for non-uniformities (N3; Sled et al., 1998).”
Multimodal Neuroimaging Feature Learning With Multimodal Stacked Deep Polynomial Networks for Diagnosis of Alzheimer's Disease (2018, methodology): “Specifically, the preprocessing is first performed on MRI images including anterior commissure (AC)-posterior commissure (PC) correction, intensity inhomogeneity by N3 algorithm [46], and skull-stripping and removal of cerebellum with the algorithm proposed by Wang et al.”
Multi-atlas segmentation of the whole hippocampus and subfields using multiple automatically generated templates (2014, methodology): “Before registration, all images underwent preprocessingwith the N3 algorithm(Sled et al., 1998) tominimise intensity nonuniformity.”
N4ITK: Improved N3 Bias Correction (2010, unknown): “The derivation of the expected value of the true image given the current estimate of the corrected image, , is also given in [4].”
Patch-based segmentation using expert priors: Application to hippocampus and ventricle segmentation (2011, methodology): “To ensure that each tissue type has the same intensity within a single image, the well-known N3 intensity nonuniformity correction of Sled et al. (1998) was used.”
One year brain atrophy evident in healthy aging (2009, methodology): “Briefly, these data were reviewed for quality, automatically corrected for spatial distortion due to gradient nonlinearity (Jovicich et al., 2006) and B1 field inhomogeneity (Sled et al., 1998), registered, and averaged to improve signal-to-noise ratio.”
Automated 3-D extraction and evaluation of the inner and outer cortical surfaces using a Laplacian map and partial volume effect classification (2005, methodology): “The non-parametric N3 method, which iteratively maximizes the frequency content of tissue intensity distributions (Sled et al., 1998) was used here.”
Effects of memory training on cortical thickness in the elderly (2010, unknown): “, 2006) and B1 field inhomogeneity (Sled et al., 1998).”
ISLES 2015 - A public evaluation benchmark for ischemic stroke lesion segmentation from multispectral MRI (2016, methodology): “images as input and includes two preprocessing steps: (1) Cor1033 rection of bias field using the N3 bias field correction algo1034 rithm (Sled et al., 1998) and (2) normalization of the inten1035 sity values of each MRI modality to the interval [0, 1], done 1036 by applying linear histogram stretch”
Cortical thickness analysis in autism with heat kernel smoothing (2005, methodology): “Image intensity nonuniformity was corrected using nonparametric nonuniform intensity normalization method (N3), which eliminates the dependence of the field estimate on anatomy (Sled et al., 1988).”
Mathematical/computational challenges in creating deformable and probabilistic atlases of the human brain (2000, methodology): “Aligned MR volumes were corrected for nonuniformity of MR signal intensity [Zijdenbos and Dawant, 1994; Sled et al., 1998], and high-resolution surface models of the cerebral cortex were extracted, as described previously [Thompson et al., 1997; MacDonald et al., 1998].”
Mapping anatomical correlations across cerebral cortex (MACACC) using cortical thickness from MRI (2006, methodology): “The native MR image is corrected for non-uniformity artefacts (Sled et al., 1998) and registered into stereotaxic space using a nine parameter linear transformation (Collins et al.”