Search

Deformable image registration aims to deliver a plausible spatial transformation between two or more images by solving a highly dimensional, ill-posed optimization problem. Covering the complexity of physiological motion has so far been limited to either generic physical models or local motion regularization models. This paper presents an alternative, graphical regularization model, which captures well the non-local scale of motion, and thus enables to incorporate complex regularization models directly into deformable image registration. In order to build the proposed graph-based regularization, a Minimum Spanning Tree (MST), which represents the underlying tissue physiology in a perceptually meaningful way, is computed first. This is followed by a fast non-local cost aggregation algorithm that performs regularization of the estimated displacement field using the precomputed MST. To demonstrate the advantage of the presented regularization, we embed it into the widely used Demons registration framework. The presented method is shown to improve the accuracy for exhale-inhale CT data pairs.

The purpose is to develop and validate an automated method for detecting image unsharpness caused by patient motion blur in digital mammograms. The goal is that such a tool would facilitate immediate re-taking of blurred images, which has the potential to reduce the number of recalled examinations, and to ensure that sharp, high-quality mammograms are presented for reading. To meet this goal, an automated method was developed based on interpretation of the normalized image Wiener Spectrum. A preliminary algorithm was developed using 25 cases acquired using a single vendor system, read by two expert readers identifying the presence of blur, location, and severity. A predictive blur severity score was established using multivariate modeling, which had an adjusted coefficient of determination, R2 =0.63±0.02, for linear regression against the average reader-scored blur severity. A heatmap of the relative blur magnitude showed good correspondence with reader sketches of blur location, with a Spearman rank correlation of 0.70 between the algorithmestimated area fraction with blur and the maximum of the blur area fraction categories of the two readers. Given these promising results, the algorithm-estimated blur severity score and heatmap are proposed to be used to aid observer interpretation. The use of this automated blur analysis approach, ideally with feedback during an exam, could lead to a reduction in repeat appointments for technical reasons, saving time, cost, potential anxiety, and improving image quality for accurate diagnosis.

This paper describes a new approach to low level image processing; in particular, edge and corner detection and structure preserving noise reduction. Non-linear filtering is used to define which parts of the image are closely related to each individual pixel; each pixel has associated with it a local image region which is of similar brightness to that pixel. The new feature detectors are based on the minimization of this local image region, and the noise reduction method uses this region as the smoothing neighbourhood. The resulting methods are accurate, noise resistant and fast. Details of the new feature detectors and of the new noise reduction method are described, along with test results.

Progress on a system to monitor the development of glaucoma by measuring the topography of the optic disk is reported. The need for an accurate method for doing this using passive vision is explained. Sparse depth measurements from stereo matching of blood vessels provide insufficient constraint for reconstructing the surface of the optic disk. Shape from shading has to contend with a spatially-varying albedo. We show how a particular arrangement of fundus cameras allows us to apply a technique akin to homomorphic filtering to recover estimates of δz δx that can be smoothed by appropriate regularization. Stereo is integrated with these photometric stereo depth estimates. Examples of artificial object and optic disk surface reconstructions are presented.

We are developing a system for patient management in colorectal cancer, in which the need for segmentation and non-rigid registration of pre- and post-therapy images arises. Several methods for non-rigid registration have been proposed, all of which embody a ’generic’ algorithm to solve registration, largely irrespective both of the kinds of images and of the application. We have evaluated several of these algorithms for this application and find their performance unsuitable for aligning pre- and post- therapy colorectal images. This leads us to identify some of the implicit assumptions and fundamental limitations of these algorithms. None of the currently available algorithms take into account the issue of scale salience and more importantly, none of the algorithms ”know” enough about colorectal MRI to focus their attention for registration on those parts of the image that are clinically important. Based on this analysis, we propose a way in which we can perform registration by mobilizing the knowledge of the particular application, for example the prior shape knowledge that we have within the colorectal images as well as knowledge of the large scale non-rigid changes due to therapy.

In this paper we describe a novel technique for detecting salient regions in an image. The detector is a generalization to affine invariance of the method introduced by Kadir and Brady [10]. The detector deems a region salient if it exhibits unpredictability in both its attributes and its spatial scale.

Outdoor navigation poses a challenge since uneven road surface, sunshine, clutter background will cause problems for odometry, laser, and vision sensors. To improve position accuracy, single strip retroreflective beacons have been used in the localization process. But to match observed beacons during the motion of the robot is a problem since all beacons are identical. Also strong reflective objects in outdoors may cause false reading.In this paper, we describe how we use the extended Kalman filter algorithm to integrate data scanned from the laser scanner rotating at 2Hz and readings from other sensors. The results obtained from outdoor navigation are presented.

We present a robust and inherently parallel strategy for tracking “corner” features on independently moving (and possibly non-rigid) objects. The system operates over long, monocular image sequences and comprises two main parts. A matcher performs two-frame correspondence based on spatial proximity and similarity in local image structure, while a tracker maintains an image trajectory (and predictor) for every feature. The use of low-level features ensures an opportunistic and widely applicable algorithm. Moreover, the system copes with noisy data, predictor failure, and occlusion and disocclusion of scene structure. Motion and scene analysis modules can then be built onto this framework. The algorithm is aimed at applications with small inter-frame motion, such as videoconferencing.

In this paper we introduce a novel representation of the significant changes in curvature along the bounding contour of planar shape. We call the representation the Curvature Primal Sketch because of the close analogy to the primal sketch representation advocated by Marr for describing significant intensity changes. We define a set of primitive parameterized curvature discontinuities, and derive expressions for their convolutions with the first and second derivatives of a Gaussian. We describe an implemented algorithm that computes the Curvature Primal Sketch by matching the multiscale convolutions of a shape, and illustrate its performance on a set of tool shapes. Several applications of the representation are sketched.

We describe a new model which is able to model accurately the characteristics of subject motion, a dominant artefact in Functional Magnetic Resonance Images. Using the model, which is based on specific knowledge regarding the nature of the image acquisition, it is possible to correct for this motion which would otherwise render activation detection on the images invalid. We also present an initial implementation based on the model and are able to demonstrate that the corrections available under this new scheme are significantly more accurate than existing approaches to the problem of subject motion, enabling a far more accurate analysis of the patterns of brain activation which these images seek to capture. © Springer-Verlag 2004.

Deformable registration of images obtained from different modalities remains a challenging task in medical image analysis. This paper addresses this problem and proposes a new similarity metric for multi-modal registration, the non-local shape descriptor. It aims to extract the shape of anatomical features in a non-local region. By utilizing the dense evaluation of shape descriptors, this new measure bridges the gap between intensity-based and geometric feature-based similarity criteria. Our new metric allows for accurate and reliable registration of clinical multi-modal datasets and is robust against the most considerable differences between modalities, such as non-functional intensity relations, different amounts of noise and non-uniform bias fields. The measure has been implemented in a non-rigid diffusion-regularized registration framework. It has been applied to synthetic test images and challenging clinical MRI and CT chest scans. Experimental results demonstrate its advantages over the most commonly used similarity metric - mutual information, and show improved alignment of anatomical landmarks. © 2011 Springer-Verlag.