Minimally invasive and less invasive procedure is becoming more and more common in medical therapy. Image guidance is an indispensable component in minimally invasive procedures by providing critical information about the position of the target sites and the optimal manipulation of the devices, while the field of view is limited to naked eyes due to the small incision. Registration is one of the enabling technologies for computer-aided image guidance, which brings high-resolution pre-operative data into the operating room to provide more realistic information about the patient's anatomy. In this paper, we survey the recent advances in registration techniques applied to minimally and/or less invasive therapy, including a wide variety of therapies in surgery, endoscopy, interventional cardiology, interventional radiology, and hybrid procedures. The registration approaches are categorized into several groups, including projection-to-volume, slice-to-volume, video-to-volume, and volume-to-volume registration. The focus is on recent advances in registration techniques that are specifically developed for minimally and/or less invasive procedures in the following medical specialties: neuroradiology and neurosurgery, cardiac applications, and thoracic-abdominal interventions.

This paper explores the use of quadratic mutual information as a similarity criterion for dense, non-rigid registration of medical images. Quadratic mutual information between two random variables has been recently proposed as Euclidean distance between the joint density and the product of the marginals. It has been shown to have a smooth sample estimator, that can be computed without having to use numerical approximation techniques for computing the integral over densities. In this paper, we derive Euler-Lagrange equations for optimizing quadratic mutual information in a variational framework. We then obtain a dense deformation field for registering 3D tomography images. Our results demonstrate the applicability of this criterion for such a task, and yield ground for further analysis and research.

The watershed partition of an image often results in over-segmentation. This well-known phenomenon is due to variations of intensity that do not correspond to object boundaries and produce spurious local minima in the image gradient magnitude. Filtering minima or merging watershed regions is then necessary to obtain a higher-level description of the data. In this paper, we propose new solutions to this problem by applying two interactive multilabel partitioning techniques to the adjacency graph of the watershed regions. In our first approach, the partition is derived from the probability that a "random walker" starting at an arbitrary node, first reaches a node with a pre-assigned label. In the second approach, we compute a geodesic partition of the graph using competing wavefronts starting at prescribed nodes. Both methods are based on existing segmentation techniques previously implemented on image lattices. Using a watershed adjacency graph greatly reduces their memory footprint and computational cost. We demonstrate the practicality and versatility of this approach with several experiments on 2D and 3D datasets.

We propose a new region segmentation method based on non-rigid template matching. We align a binary template to an image by maximizing the likelihood of intensity distributions within a region of interest and its background. The intensity model and the corresponding a posteriori distributions are estimated and updated throughout the alignment. The geometric deformation of the template is based on a fluid registration model. Unlike contour-based segmentation techniques, this registration framework allows for a global regularization of the template variations. This enables the segmentation of irregular shapes while avoiding leaks. We apply our method to the segmentation of the liver in computed tomography images, a challenging task due to the high inter-patient variability in the shape of this organ. We show that our segmentation results are equivalent or superior in accuracy to results obtained using existing techniques based on 3D shape models.

It is now common practice in machine vision to define the variability in an object's appearance in a factored manner, as a combination of shape and texture transformations. In this context, we present a simple and practical method for estimating non-parametric probability densities over a group of linear shape deformations. Samples drawn from such a distribution do not lie in a Euclidean space, and standard kernel density estimates may perform poorly. While variable kernel estimators may mitigate this problem to some extent, the geometry of the underlying configuration space ultimately demands a kernel, which accommodates its group structure. In this perspective, we propose a suitable invariant estimator on the linear group of non-singular matrices with positive determinant. We illustrate this approach by modeling image transformations in digit recognition problems, and present results showing the superiority of our estimator to comparable Euclidean estimators in this domain.