Highly Accurate Inverse Consistent Registration: A Robust Approach

By Martin Reuter, H. Rosas, Bruce Fischl. NeuroImage, 2010

1,402 citations recorded by the source corpus.

The registration of images is a task that is at the core of many applications in computer vision. In computational neuroimaging where the automated segmentation of brain structures is frequently used to quantify change, a highly accurate registration is necessary for motion correction of images taken in the same session, or across time in longitudinal studies where changes in the images can be expected. This paper, inspired by Nestares and Heeger (2000), presents a method based on robust statistics to register images in the presence of differences, such as jaw movement, differential MR distortions and true anatomical change. The approach we present guarantees inverse consistency (symmetry), can deal with different intensity scales and automatically estimates a sensitivity parameter to detect outlier regions in the images. The resulting registrations are highly accurate due to their ability to ignore outlier regions and show superior robustness with respect to noise, to intensity scaling and outliers when compared to state-of-the-art registration tools such as FLIRT (in FSL) or the coregistration tool in SPM.

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

View Paper: https://www.semanticscholar.org/paper/de885aa4b9306b5ce4f11f0b9a1780e7d7bd11ba

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

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Unique developmental trajectories of cortical thickness and surface area (2014, positive): “This method increases repeatability and statistical power (Reuter et al., 2010).”
Head motion during MRI acquisition reduces gray matter volume and thickness estimates (2015, positive): “7; Gray matter (GM) volumes were estimated using voxel based morphometry VBM8 toolbox [12] of the SPM8 package [2]; Cortical thickness and gray matter volume were estimated using both the independent [11,10] and longitudinal image-processing stream [23,22] of FreeSurfer 5.”
Models of the Aging Brain Structure and Individual Decline (2012, background): “Thus it needs highly sophisticated preprocessing pipelines in order to detect the changes of interest and achieve unbiased results (Reuter et al., 2010; Reuter and Fischl, 2011).”
Within-subject template estimation for unbiased longitudinal image analysis (2012, methodology): “Reuter et al. (2010b) show the superiority of this method over standard registration tools available in the FSL (Jenkinson et al., 2002; Smith et al., 2004) or SPM packages (Collignon et al., 1995; Ashburner and Friston, 1999) with respect to inverse consistency , noise, outlier data, test–retest…”
FreeSurfer (2012, methodology): “…(thanks to Florent Ségonne). unbiased and extremely accurate in the presence of nonlinearities such as B0 distortions, and tongue/jaw/eye movement (Reuter et al., 2010), and has taken over primary responsibility for the ongoing development of our longitudinal analysis stream, and also worked with…”
Avoiding asymmetry-induced bias in longitudinal image processing (2011, background): “edu/fswiki/ LongitudinalProcessing, Reuter et al. (2010)).”
What is normal in normal aging? Effects of Aging, Amyloid and Alzheimer’s Disease on the Cerebral Cortex and the Hippocampus (2014, background): “With high-quality MR-scans and state-of-the-art analysis tools (Reuter et al., 2010; Holland and Dale, 2011; Holland et al., 2012b; Reuter et al., 2012), brain changes can be detected reliably and monitored over intervals as”
Structural brain development between childhood and adulthood: Convergence across four longitudinal samples (2016, methodology): “This processing stream includes motion correction (Reuter et al., 2010), removal of non-brain tissue using a hybrid watershed/surface deformation procedure (Ségonne et al., 2004), automated Talairach transformation, non-parametric non-uniform intensity normalization (Sled et al., 1998),…”
Volumetric Navigators (vNavs) for Prospective Motion Correction and Selective Reacquisition in Neuroanatomical MRI (2011, methodology): “For the MEMPRAGE subject, the nine volumes were analyzed using parts of the FreeSurfer longitudinal analysis stream: our analysis consisted of skull-stripping each volume, followed by an unbiased coregistration of the brain volumes (21,22), then the construction of a within-subject “average volume” ”
A survey of GPU-based medical image computing techniques. (2012, background): “In practical applications for medical registration, there may not be a one-to-one correspondence between these two images, which are degenerated by partial or missing data sets (152).”
A Correspondence between Individual Differences in the Brain's Intrinsic Functional Architecture and the Content and Form of Self-Generated Thoughts (2014, neutral): “1 [43–52] followed by iterative manual inspection and correction of the cortical segmentations.”
Statistical Analysis of Longitudinal Neuroimage Data with Linear Mixed Effects Models (2012, methodology): “The longitudinal stream in FreeSurfer (Reuter et al., 2012) utilizes an unbiased subject-specific template (Reuter and Fischl, 2011), which is created by co-registering scans from each time-point using a robust and inverse consistent registration algorithm (Reuter et al., 2010).”
OASIS-3: Longitudinal Neuroimaging, Clinical, and Cognitive Dataset for Normal Aging and Alzheimer Disease (2019, neutral): “The technical details of these procedures are described in prior publications 23–34 .”
Global image registration using a symmetric block-matching approach (2014, methodology): “Reuter et al. 12 developed a global registration technique based on robust statistic optimization performed in a midpoint space.”