Magnetic resonance (MR) images lack information about radiation transport-a fact which is problematic in applications such as radiotherapy planning and attenuation correction in combined PET/MR imaging. To remedy this, a crude but common approach is to approximate all tissue properties as equivalent to those of water. We improve upon this using an algorithm that automatically identifies bone tissue in MR. More specifically, we focus on segmenting the skull prior to stereotactic neurosurgery, where it is common that only MR images are available. In the proposed approach, a machine learning algorithm known as a support vector machine is trained on patients for which both a CT and an MR scan are available. As input, a combination of local and global information is used. The latter is needed to distinguish between bone and air as this is not possible based only on the local image intensity. A whole skull segmentation is achievable in minutes. In a comparison with two other methods, one based on mathematical morphology and the other on deformable registration, the proposed method was found to yield consistently better segmentations.

We propose non-local analysis of functional magnetic resonance imaging (fMRI) data in order to detect more brain activity. Our non-local approach combines the ideas of regular fMRI analysis with those of functional connectivity analysis, and was inspired by the non-local means algorithm that commonly is used for image denoising. We extend canonical correlation analysis (CCA) based fMRI analysis to handle more than one activity area, such that information from different parts of the brain can be combined. Our non-local approach is compared to fMRI analysis by the general linear model (GLM) and local CCA, by using simulated as well as real data.

Functional connectivity analysis is a way to investigate how different parts of the brain are connected and interact. A common measure of connectivity is the temporal correlation between a reference voxel time series and all the other time series in a functional MRI data set. An fMRI data set generally contains more than 20,000 within-brain voxels, making a complete correlation analysis between all possible combinations of voxels heavy to compute, store, visualize and explore. In this paper, a GPU-accelerated interactive tool for investigating functional connectivity in fMRI data is presented. A reference voxel can be moved by the user and the correlations to all other voxels are calculated in real-time using the graphics processing unit (GPU). The resulting correlation map is updated in real-time and visualized as a 3D volume rendering together with a high resolution anatomical volume. This tool greatly facilitates the search for interesting connectivity patterns in the brain.

We present a method for fast phase based registration of volume data for medical applications. As the number of different modalities within medical imaging increases, it becomes more and more important with registration that works for a mixture of modalities. For these applications the phase based registration approach has proven to be superior. Today there seem to be two kinds of groups that work with medical image registration, one that works with refining of the registration algorithms and one that works with implementation of more simple algorithms on graphic cards for speeding up the algorithms. We put the work from these groups together and get the best from both worlds. We achieve a speedup of 10-30 compared to our CPU implementation, which makes fast phase based registration possible for large medical volumes.

Image registration is a crucial task in many applications and applied in a variety of different areas. In addition to the primary task of image alignment, the deformation field is valuable when studying structural/volumetric changes in the brain. In most applications a regularizing term is added to achieve a smoothly varying deformation field. This can sometimes cause conflicts in situations of local complex deformations. In this paper we present a new regularizer, which aims at handling local complex deformations while maintaining an overall smooth deformation field. It is based on an adaptive anisotropic regularizer and its usefulness is demonstrated by two examples, one synthetic and one with real MRI data from a pre- and post-op situation with normal pressure hydrocephalus.

We present the first step towards a brain computer interface (BCI) for communication using real-time functional magnetic resonance imaging (fMRI). The subject in the MR scanner sees a virtual keyboard and steers a cursor to select different letters that can be combined to create words. The cursor is moved to the left by activating the left hand, to the right by activating the right hand, down by activating the left toes and up by activating the right toes. To select a letter, the subject simply rests for a number of seconds. We can thus communicate with the subject in the scanner by for example showing questions that the subject can answer. Similar BCI for communication have been made with electroencephalography (EEG). In these implementations the subject for example focuses on a letter while different rows and columns of the virtual keyboard are flashing. The system then tries to detect if the correct letter is flashing or not. In our setup we instead classify the brain activity. Our system is not limited to a communication interface, but can be used for any interface where five degrees of freedom is necessary.

Phase-based methods are commonly applied in image registration. When working with phase-difference methods only a single scale is employed, although the algorithms are normally iterated over multiple scales, whereas phase-congruency methods utilize the the phase from multiple scales simultaneously. This paper presents an extension to phase-difference methods employing parallel scales to achieve more accurate displacements. Results are also presented clearly favouring the use of parallel scales over single scale in more than 95% of the 120 tested cases.

The inverse gradient problem, finding a scalar field f with a gradient near a given vector fieldgon some bounded and connected domain Ω ϵ R𝓃, can be solved by means of a Poisson equation with inhomogeneous Neumann boundary conditions. We present an elementary derivation of this partial differential equation and an efficient multigrid-based method to numerically compute the inverse gradient on non-rectangular domains. The utility of the method is demonstrated by a range of important medical applications such as phase unwrapping, pressure computation, inverse deformation fields, and fiber bundle tracking.

A method for detecting and reducing reverberation artifacts in ultrasound image sequences is described. A reverberation artifact localization map is produced using local Rf-bandwidth estimation. To reduce the artifacts an ideal 3D (2D + time) Wiener filter function is computed by using the reverberation map to interactively produce an estimate of the noise and signal spectra. The Wiener filter kernel is optimized to obtain good locality properties. The optimized filter is then applied to the ultrasound image sequence. The test sequence used is from an open chest pig heart, corrupted by strong reverberation artifacts. The selective power of a 3D filter is far superior to that of ID and 2D filters and the reverberation artifacts are almost completely removed by the developed method.

This paper presents a new robust approach for segmentation. The segmentation is attained by morphing of an TV-dimensional model, the Morphon, onto the TV-dimensional data. The approach is general and can, in fact, be said to encompass much of the deformable model ideas that have evolved over the years. However, in contrast to commonly used models, a distinguishing feature of the Morphon approach is that it allows an intuitive interface for specifying prior information, hence the expression paint on priors. In this way it is simple to design Morphons for specific situations. The priors determine the behavior of the Morphon and can be seen as local data interpreters and response generators. There are three different kinds of priors: material parameter fields (elasticity, viscosity, anisotropy etc.), context fields (brightness, hue, scale, phase, anisotropy, certainly etc.) and global programs (filter banks, estimation procedures, adaptive mechanisms etc.). The morphing is performed using a dense displacement field. Both the material parameter and context fields are addressed via the present displacement field. An example of the performance of is given using 2D ultrasound images of a heart where the purpose is to segment the heart wall.

Linear filtering is a fundamental operation in signal processing, but for multidimensional signals the practical use is severely limited by the computer power available. Decomposition of filters into a layered structure of sparse subfilters, i.e. a filter network, significantly reduces the number of multiplications required for each data sample. A filter network, here used for phase invariant estimation of local 3-D structure, provides a flexible solution for linear filtering, especially suited for applying a set of filters on signals of higher dimensionality. The filter network presented, is twice as efficient as convolution based on the fast Fourier transform (FFT) and outperforms standard convolution by a factor exceeding 50 in terms of multiplications and additions performed.

Tensors and tensor fields are commonly used in multidimensional signal processing to represent the local structure of the signal. This paper focuses on the case where the sampling on the original signal is anisotropic, e.g when the resolution of the multidimensional image varies depending on the direction which is common e.g. in medical imaging devices. To obtain a geometrically correct description of the local structure there are mainly two possibilities. To resample the image prior to the computation of the local structure tensor field or to compute the tensor field on the original grid and transform the result to obtain a correct geometry of the local structure. This paper deals with the latter alternative and contains an in depth theoretical analysis establishing the appropriate rules for tensor transformations induced by changes in space-time geometry with emphasis on velocity and motion estimation.

The paper argues for the use of quadrature filters for local structure tensor and motion estimation. The question of which properties of a local motion estimator are important is discussed. Answers are provided via the introduction of a number of fundamental invariances that are required in object motion estimation. A combination of statistical and deterministic modeling leads to mathematical formulations corresponding to the required invariances. The discussion leads up to the introduction of a new class of filter sets loglets. A number of experiments support the claim that loglets are preferable to other designs. In particular it is demonstrated that the loglet approach outperforms a Gaussian derivative approach in resolution and robustness to variations in object illumination.

We present a method for accurate image registration and motion compensation in multidimensional signals, such as two-dimensional (2-D) X-ray images and three-dimensional (3-D) computed tomography/magnetic resonance imaging volumes. The method is based on phase from quadrature filters, which makes it robust to noise and temporal intensity variations. The method is equally applicable to signals of two, three or higher number of dimensions. We use parametric models, e.g., affine models, finite elements or local affine models with global regularization. Experimental results show high accuracy for 2-D and 3-D motion compensation.

We present a method for accurate image registration and motion estimation in multidimensional volumes, such as 3D CT and MR images. The method is based on phase from quadrature filters, which makes it insensitive to variations in luminance and other disturbance in the images. The theory is not restricted to any particular kind of motion model or number of dimensions. Experimental results for affine motions in 3D show high accuracy.

Presents a general strategy for automated generation of efficient representations in vision. The approach is highly task oriented and what constitutes the relevant information is defined by a set of examples. The examples are pairs of situations that are dependent through the chosen feature but are otherwise independent. Particularly important concepts in the work are mutual information and canonical correlation. How visual operators and representation can be generated from examples are presented for a number of features, e.g. local orientation, disparity and motion. Interesting similarities to biological vision functions are observed. The results clearly demonstrates the potential of combining advanced filtering techniques and learning strategies based on canonical correlation analysis.

Conventional gradient methods (optical flow), for motion estimation assume intensity conservation between frames. This assumption is often violated in real applications. The remedy is a novel method that computes constraints on the local motion. These constraint are given on the same form as in conventional methods. Thus, it can directly substitute the gradient method in most applications. Experiments indicate a superior accuracy, even on synthetic images where the intensity conservation assumption is valid. The conventional gradient methods seem obsolete.