Automatic retinal image registration scheme using global optimization techniques

Effect of segmentation errors on 3D-to-2D registration of implant models in X-ray images

In many biomedical applications, it is desirable to estimate the three-dimensional (3D) position and orientation (pose) of a metallic rigid object (such as a knee or hip implant) from its projection in a two-dimensional (2D) X-ray image. If the geometry of the object is known, as well as the details of the image formation process, then the pose of the object with respect to the sensor can be determined. A common method for 3D-to-2D registration is to first segment the silhouette contour from the X-ray image; that is, identify all points in the image that belong to the 2D silhouette and not to the background. This segmentation step is then followed by a search for the 3D pose that will best match the observed contour with a predicted contour. Although the silhouette of a metallic object is often clearly visible in an X-ray image, adjacent tissue and occlusions can make the exact location of the silhouette contour difficult to determine in places. Occlusion can occur when another object (such as another implant component) partially blocks the view of the object of interest. In this paper, we argue that common methods for segmentation can produce errors in the location of the 2D contour, and hence errors in the resulting 3D estimate of the pose. We show, on a typical fluoroscopy image of a knee implant component, that interactive and automatic methods for segmentation result in segmented contours that vary significantly. We show how the variability in the 2D contours (quantified by two different metrics) corresponds to variability in the 3D poses. Finally, we illustrate how traditional segmentation methods can fail completely in the (not uncommon) cases of images with occlusion.

Multimodal registration of retinal images using self organizing maps

In this paper, an automatic method for registering multimodal retinal images is presented. The method consists of three steps: the vessel centerline detection and extraction of bifurcation points only in the reference image, the automatic correspondence of bifurcation points in the two images using a novel implementation of the self organizing maps and the extraction of the parameters of the affine transform using the previously obtained correspondences. The proposed registration algorithm was tested on 24 multimodal retinal pairs and the obtained results show an advantageous performance in terms of accuracy with respect to the manual registration.

A robust method for registration of three-dimensional knee implant models to two-dimensional fluoroscopy images

A method was developed for registering three-dimensional knee implant models to single plane X-ray fluoroscopy images. We use a direct image-to-image similarity measure, taking advantage of the speed of modern computer graphics workstations to quickly render simulated (predicted) images. As a result, the method does not require an accurate segmentation of the implant silhouette in the image (which can be prone to errors). A robust optimization algorithm (simulated annealing) is used that can escape local minima and find the global minimum (true solution). Although we focus on the analysis of total knee arthroplasty (TKA) in this paper, the method can be (and has been) applied to other implanted joints, including, but not limited to, hips, ankles, and temporomandibular joints. Convergence tests on an in vivo image show that the registration method can reliably find poses that are very close to the optimal (i.e., within 0.4 degrees and 0.1 mm), even from starting poses with large initial errors. However, the precision of translation measurement in the Z (out-of-plane) direction is not as good. We also show that the method is robust with respect to image noise and occlusions. However, a small amount of user supervision and intervention is necessary to detect cases when the optimization algorithm falls into a local minimum. Intervention is required less than 5% of the time when the initial starting pose is reasonably close to the correct answer, but up to 50% of the time when the initial starting pose is far away. Finally, extensive evaluations were performed on cadaver images to determine accuracy of relative pose measurement. Comparing against data derived from an optical sensor as a "gold standard," the overall root-mean-square error of the registration method was approximately 1.5 degrees and 0.65 mm (although Z translation error was higher). However, uncertainty in the optical sensor data may account for a large part of the observed error.

The dual-bootstrap iterative closest point algorithm with application to retinal image registration

Motivated by the problem of retinal image registration, this paper introduces and analyzes a new registration algorithm called Dual-Bootstrap Iterative Closest Point (Dual-Bootstrap ICP). The approach is to start from one or more initial, low-order estimates that are only accurate in small image regions, called bootstrap regions. In each bootstrap region, the algorithm iteratively: 1) refines the transformation estimate using constraints only from within the bootstrap region; 2) expands the bootstrap region; and 3) tests to see if a higher order transformation model can be used, stopping when the region expands to cover the overlap between images. Steps 1): and 3), the bootstrap steps, are governed by the covariance matrix of the estimated transformation. Estimation refinement [Step 2)] uses a novel robust version of the ICP algorithm. In registering retinal image pairs, Dual-Bootstrap ICP is initialized by automatically matching individual vascular landmarks, and it aligns images based on detected blood vessel centerlines. The resulting quadratic transformations are accurate to less than a pixel. On tests involving approximately 6000 image pairs, it successfully registered 99.5% of the pairs containing at least one common landmark, and 100% of the pairs containing at least one common landmark and at least 35% image overlap.

A comparative study of surface- and volume-based techniques for the automatic registration between CT and SPECT brain images

Image registration of multimodality images is an essential task in numerous applications in three-dimensional medical image processing. Medical diagnosis can benefit from the complementary information in different modality images. Surface-based registration techniques, while still widely used, were succeeded by volume-based registration algorithms that appear to be theoretically advantageous in terms of reliability and accuracy. Several applications of such algorithms for the registration of CT-MRI, CT-PET, MRI-PET, and SPECT-MRI images have emerged in the literature, using local optimization techniques for the matching of images. Our purpose in this work is the development of automatic techniques for the registration of real CT and SPECT images, based on either surface- or volume-based algorithms. Optimization is achieved using genetic algorithms that are known for their robustness. The two techniques are compared against a well-established method, the Iterative Closest Point-ICP. The correlation coefficient was employed as an independent measure of spatial match, to produce unbiased results. The repeated measures ANOVA indicates the significant impact of the choice of registration method on the magnitude of the correlation (F = 4.968, p = 0.0396). The volume-based method achieves an average correlation coefficient value of 0.454 with a standard deviation of 0.0395, as opposed to an average of 0.380 with a standard deviation of 0.0603 achieved by the surface-based method and an average of 0.396 with a standard deviation equal to 0.0353 achieved by ICP. The volume-based technique performs significantly better compared to both ICP (p<0.05, Neuman Keuls test) and the surface-based technique (p<0.05, Neuman-Keuls test). Surface-based registration and ICP do not differ significantly in performance.

Evolutionary computation in medicine: an overview

The term evolutionary computation encompasses a host of methodologies inspired by natural evolution that are used to solve hard problems. This paper provides an overview of evolutionary computation as applied to problems in the medical domains. We begin by outlining the basic workings of six types of evolutionary algorithms: genetic algorithms, genetic programming, evolution strategies, evolutionary programming, classifier systems, and hybrid systems. We then describe how evolutionary algorithms are applied to solve medical problems, including diagnosis, prognosis, imaging, signal processing, planning, and scheduling. Finally, we provide an extensive bibliography, classified both according to the medical task addressed and according to the evolutionary technique used.