Global image registration using a symmetric block-matching approach

By Marc Modat, D. Cash, P. Daga, G. Winston, J. Duncan, Sébastien Ourselin. Journal of Medical Imaging, 2014

388 citations recorded by the source corpus.

Abstract. Most medical image registration algorithms suffer from a directionality bias that has been shown to largely impact subsequent analyses. Several approaches have been proposed in the literature to address this bias in the context of nonlinear registration, but little work has been done for global registration. We propose a symmetric approach based on a block-matching technique and least-trimmed square regression. The proposed method is suitable for multimodal registration and is robust to outliers in the input images. The symmetric framework is compared with the original asymmetric block-matching technique and is shown to outperform it in terms of accuracy and robustness. The methodology presented in this article has been made available to the community as part of the NiftyReg open-source package.

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

View Paper: https://www.semanticscholar.org/paper/52cd2ed34a903a85db8c4932b8674633b63d780c

How researchers see this paper

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

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Reduced acquisition time PET pharmacokinetic modelling using simultaneous ASL–MRI: proof of concept (2018, methodology): “Analysis was performed in native space such that the T1-weighted MR image was rigidly registered to both ASL (saturation recovery image target) and PET (mmap transformation) space, and the transformation was propagated to the parcellation.(29)”
VoxelMorph: A Learning Framework for Deformable Medical Image Registration (2018, background): “Recent GPU-based algorithms build on these concepts to reduce algorithm runtime to several minutes, but require a GPU to be available for each registration [4], [34].”
Local Temperature Scaling for Probability Calibration (2020, methodology): “For preprocessing, all images are first affinely registered to the ICBM MNI152 nonlinear atlas [15] using NiftyReg [40, 41, 50] and intensity normalized via histogram equalization.”
Longitudinal multiple sclerosis lesion segmentation: Resource and challenge (2017, neutral): “This is performed through an iterative set of affine registrations refined afterwards by non-rigid deformations (Modat et al., 2014).”
Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces (2019, methodology): “In addition, we implemented the integration of the velocity field using Tensorflow ODE solvers and using standard quadrature, but found that these required significantly more runtime compared to the scaling and squaring strategy, consistent with literature findings [4, 5, 50].”
TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning (2020, methodology): “1-weighted MR images from the IXI dataset using geodesical information ﬂows (GIF) [Cardoso et al., 2015], 2) registered the images to an Montreal Neurological Institute (MNI) template using NiftyReg [Modat et al., 2014], and 3) resampled the images to have a size of I J K = 83 44 55 after a Gaussian”
Naturalistic Audiovisual Illusions Reveal the Cortical Sites Involved in the Multisensory Processing of Speech (2025, unknown): “Briefly, a postimplantation high-resolution CT scan was aligned to a preimplantation millimetric, isometric T1-weighted MRI scan using FSL, (Jenkinson et al. 2012) FreeSurfer (Fischl 2012) or NiftyReg (Modat et al. 2014).”