• Corpus ID: 239050237

Cross-Sim-NGF: FFT-Based Global Rigid Multimodal Alignment of Image Volumes using Normalized Gradient Fields

  title={Cross-Sim-NGF: FFT-Based Global Rigid Multimodal Alignment of Image Volumes using Normalized Gradient Fields},
  author={Johan Ofverstedt and Joakim Lindblad and Natavsa Sladoje},
Multimodal image alignment involves finding spatial correspondences between volumes varying in appearance and structure. Automated alignment methods are often based on local optimization that can be highly sensitive to their initialization. We propose a global optimization method for rigid multimodal 3D image alignment, based on a novel efficient algorithm for computing similarity of normalized gradient fields (NGF) in the frequency domain. We validate the method experimentally on a dataset… 

Figures and Tables from this paper


Fast computation of mutual information in the frequency domain with applications to global multimodal image alignment
An efficient algorithm for computing MI for all discrete displacements (formalized as the cross-mutual information function (CMIF)), which is based on cross-correlation computed in the frequency domain is proposed, and it is shown that the algorithm is equivalent to a direct method while asymptotically superior in terms of run-time.
Image registration by maximization of combined mutual information and gradient information
Results indicate that the combined measures yield a better registration function does mutual information or normalized mutual information per se, and the registration functions are less sensitive to low sampling resolution, do not contain incorrect global maxima that are sometimes found in the mutual information function, and interpolation-induced local minima can be reduced.
Normalized gradient fields cross-correlation for automated detection of prostate in magnetic resonance images
Three-dimensional method for fast automated prostate detection based on normalized gradient fields cross-correlation, insensitive to intensity variations and coil-induced artifacts is presented and evaluated, demonstrating high utility of the detection method for a fully automated prostate segmentation.
elastix: A Toolbox for Intensity-Based Medical Image Registration
The software consists of a collection of algorithms that are commonly used to solve medical image registration problems, and allows the user to quickly configure, test, and compare different registration methods for a specific application.
Adaptive Stochastic Gradient Descent Optimisation for Image Registration
The proposed adaptive stochastic gradient descent method is compared to a standard, non-adaptive Robbins-Monro (RM) algorithm and indicates that ASGD is robust to variations in the registration framework and is less sensitive to the settings of the user-defined parameters than RM.
Robust FFT-Based Scale-Invariant Image Registration with Image Gradients
A robust FFT-based approach to scale-invariant image registration and introduces the normalized gradient correlation, which shows that, using image gradients to perform correlation, the errors induced by outliers are mapped to a uniform distribution for which it features robust performance.
Intensity Gradient Based Registration and Fusion of Multi-modal Images
This work investigates an alternative distance measure which is based on normalized gradients and compares its performance to Mutual Information, and calls it Normalized Gradient Fields (NGF).
MIND: Modality independent neighbourhood descriptor for multi-modal deformable registration
A modality independent neighbourhood descriptor (MIND), based on the concept of image self-similarity, which has been introduced for non-local means filtering for image denoising, is proposed and applied for the registration of clinical 3D thoracic CT scans between inhale and exhale as well as the alignment of 3D CT and MRI scans.
A deep learning based framework for the registration of three dimensional multi-modal medical images of the head
A registration framework is introduced that creates synthetic data to augment existing datasets, generates ground truth data to be used in the training and testing of algorithms, and registers multi-modal images in an accurate and fast manner and automatically classifies the image modality so that the process of registration can be fully automated.
Alignment by Maximization of Mutual Information
A new information-theoretic approach is presented for finding the pose of an object in an image that works well in domains where edge or gradient-magnitude based methods have difficulty, yet it is more robust than traditional correlation.