Article

An efficient motion estimator with application to medical image registration.

Department of Computer & Information Sciences & Engineering, University of Florida, Gainesville 32611, USA.
Medical Image Analysis (Impact Factor: 4.09). 04/1998; 2(1):79-98. DOI: 10.1016/S1361-8415(01)80029-3
Source: PubMed

ABSTRACT Image registration is a very important problem in computer vision and medical image processing. Numerous algorithms for registering single and multi-modal image data have been reported in these areas. Robustness as well as computational efficiency are prime factors of importance in image data registration. In this paper, a robust/reliable and efficient algorithm for estimating the transformation between two image data sets of a patient taken from the same modality over time is presented. Estimating the registration between two image data sets is formulated as a motion-estimation problem. We use a hierarchical optical flow motion model which allows for both global as well as local motion between the data sets. In this hierarchical motion model, we represent the flow field with a B-spline basis which implicitly incorporates smoothness constraints on the field. In computing the motion, we minimize the expectation of the squared differences energy function numerically via a modified Newton iteration scheme. The main idea in the modified Newton method is that we precompute the Hessian of the energy function at the optimum without explicitly knowing the optimum. This idea is used for both global and local motion estimation in the hierarchical motion model. We present examples of motion estimation on synthetic and real data (from a patient acquired during pre- and post-operative stages) and compare the performance of our algorithm with that of competing ones.

0 Bookmarks
 · 
61 Views
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Magnetic resonance image analysis is a promising technique for diagnosing breast cancer, particularly in women for whom X-ray mammography is ineffective. If breast motion is not corrected for, diagnostic accuracy is significantly reduced. In this paper, we analyse the kinds of motion that arise during image formation and we describe a model based non-rigid registration algorithm to estimate and correct for breast motion. Registration of breast MR images is complicated by the use of a contrast agent which results in a non-uniform increase in intensity across the image. The work described here forms part of an implemented breast MR analysis system which allows automatic detection and segmentation of regions of focal enhancement and non-rigid image registration.
    Artificial Intelligence 01/1999; · 2.19 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The purpose of image registration is to spatially align two or more single-modality images taken at different times, or several images acquired by multiple imaging modalities. Intensity-based registration usually requires optimization of the similarity metric between the images. However, global optimization techniques are too time-consuming, and local optimization techniques frequently fail to search the global transformation space because of the large initial misalignment of the two images. Moreover, for large non-overlapping area registration, the similarity metric cannot reach its optimum value when the two images are properly registered. In order to solve these problems, we propose a novel Symmetric Scale Invariant Feature Transform (symmetric-SIFT) descriptor and develop a fast multi-modal image registration technique. The proposed technique automatically generates a lot of highly distinctive symmetric-SIFT descriptors for two images, and the registration is performed by matching the corresponding descriptors over two images. These descriptors are invariant to image scale and rotation, and are partially invariant to affine transformation. Moreover, these descriptors are symmetric to contrast, which makes it suitable for multi-modal image registration. The proposed technique abandons the optimization and similarity metric strategy. It works with near real-time performance, and can deal with the large non-overlapping and large initial misalignment situations. Test cases involving scale change, large non-overlapping, and large initial misalignment on computed tomography (CT) and magnetic resonance (MR) datasets show that it needs much less runtime and achieves better accuracy when compared to other algorithms.
    Progress in Natural Science 05/2009; 19(5):643–651. · 0.99 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: CT colonography (CTC) is a non-invasive technique for detecting colorectal polyps and colon cancer. Through the addition of the prone scanning with the original supine scanning, the possibility of detecting the polyps is increased. The registration process for this application requires the comparison between the prone and supine colons for diagnosis. A level-set representation of the object boundary using a distance map is presented in this paper as an input to demons registration algorithm for supine and prone CT colonography image data. After first aligning the colon volumes based on the patient's anus position, distances inside and outside the objects' boundary are computed. The level-set from the distance map allows the demons algorithm to decide the moving direction for the initial demons' force between the two colons. We present a result with a 3 dimensional volume of a patient's colon. The results suggest that our method has excellent registration performance with high confidence even with considerable deformation of the colon lumen in 3 dimensional case.
    Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 02/2006; 1:1997-2000.

Full-text (2 Sources)

View
2 Downloads
Available from
Oct 7, 2014