Combining Sparse and Dense Features to Improve Multi-Modal Registration for Brain DTI Images
Open Access
- 14 November 2020
- Vol. 22 (11), 1299
- https://doi.org/10.3390/e22111299
Abstract
A new solution to overcome the constraints of multimodality medical intra-subject image registration is proposed, using the mutual information (MI) of image histogram-oriented gradients as a new matching criterion. We present a rigid, multi-modal image registration algorithm based on linear transformation and oriented gradients for the alignment of T2-weighted (T2w) images (as a fixed reference) and diffusion tensor imaging (DTI) (b-values of 500 and 1250 s/mm2) as floating images of three patients to compensate for the motion during the acquisition process. Diffusion MRI is very sensitive to motion, especially when the intensity and duration of the gradient pulses (characterized by the b-value) increases. The proposed method relies on the whole brain surface and addresses the variability of anatomical features into an image stack. The sparse features refer to corners detected using the Harris corner detector operator, while dense features use all image pixels through the image histogram of oriented gradients (HOG) as a measure of the degree of statistical dependence between a pair of registered images. HOG as a dense feature is focused on the structure and extracts the oriented gradient image in the x and y directions. MI is used as an objective function for the optimization process. The entropy functions and joint entropy function are determined using the HOGs data. To determine the best image transformation, the fiducial registration error (FRE) measure is used. We compare the results against the MI-based intensities results computed using a statistical intensity relationship between corresponding pixels in source and target images. Our approach, which is devoted to the whole brain, shows improved registration accuracy, robustness, and computational cost compared with the registration algorithms, which use anatomical features or regions of interest areas with specific neuroanatomy. Despite the supplementary HOG computation task, the computation time is comparable for MI-based intensities and MI-based HOG methods.This publication has 27 references indexed in Scilit:
- Confidence Estimation for Medical Image Registration Based On Stereo ConfidencesIEEE Transactions on Medical Imaging, 2015
- Multi-channel registration of fractional anisotropy and T1-weighted images in the presence of atrophy: application to multiple sclerosisFunctional Neurology, 2015
- Image Registration Using Log Polar Transform and Phase Correlation to Recover Higher ScaleJournal of Pattern Recognition Research, 2012
- Geometrical analysis of registration errors in point-based rigid-body registration using invariantsMedical Image Analysis, 2011
- Validation for 2D/3D registration II: The comparison of intensity‐ and gradient‐based merit functions using a new gold standard data setMedical Physics, 2011
- General Approach to First-Order Error Prediction in Rigid Point RegistrationIEEE Transactions on Medical Imaging, 2010
- Vehicle Detection Using Partial Least SquaresIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registrationNeuroImage, 2009
- Non-rigid image registration: theory and practiceThe British Journal of Radiology, 2004
- Enhancing accuracy of magnetic resonance image fusion by defining a volume of interestNeuroradiology, 2003