Ketut Fundana

Discontinuity preserving registration of abdominal MR images with apparent sliding organ motion

Discontinuous displacement fields are quite common in the medical field, in particular at organ boundaries with breathing induced organ motion. The sliding motion of the liver along the abdominal wall clearly causes a discontinuous displacement field. Todays common medical image registration methods, however, cannot properly deal with this kind of motion as their regularisation term enforces a smooth displacement field. Since these motion discontinuities appear at organ boundaries, motion segmentation could play an important guiding role during registration. In this paper we propose a novel method that integrates registration and globally optimal motion segmentation in a variational framework. The energy functional is formulated such that the segmentation, via continuous cuts, supports the computation of discontinuous displacement fields. The proposed energy functional is then minimised in a coarse-to-fine strategy by using a fast dual method for motion segmentation and a fixed point iteration scheme for motion estimation. Experimental results are shown for synthetic and real MR images of breathing induced liver motion.

Histology to μCT data matching using landmarks and a density biased RANSAC

The fusion of information from different medical imaging techniques plays an important role in data analysis. Despite the many proposed registration algorithms the problem of registering 2D histological images to 3D CT or MR imaging data is still largely unsolved.

Automatic Segmentation of the Spinal Cord Using Continuous Max Flow with Cross-sectional Similarity Prior and Tubularity Features

Segmenting tubular structures from medical image data is a common problem; be it vessels, airways, or nervous tissue like the spinal cord. Many application-specific segmentation techniques have been proposed in the literature, but only few of them are fully automatic and even fewer approaches maintain a convex formulation. In this paper, we show how to integrate a cross-sectional similarity prior into the convex continuous max-flow framework that helps to guide segmentations in image regions suffering from noise or artefacts. Furthermore, we propose a scheme to explicitly include tubularity features in the segmentation process for increased robustness and measurement repeatability. We demonstrate the performance of our approach by automatically segmenting the cervical spinal cord in magnetic resonance images, by reconstructing its surface, and acquiring volume measurements.

Discontinuity Preserving Image Registration through Motion Segmentation: A Primal-Dual Approach.

Image registration is a powerful tool in medical image analysis and facilitates the clinical routine in several aspects. There are many well established elastic registration methods, but none of them can so far preserve discontinuities in the displacement field. These discontinuities appear in particular at organ boundaries during the breathing induced organ motion. In this paper, we exploit the fact that motion segmentation could play a guiding role during discontinuity preserving registration. The motion segmentation is embedded in a continuous cut framework guaranteeing convexity for motion segmentation. Furthermore we show that a primal-dual method can be used to estimate a solution to this challenging variational problem. Experimental results are presented for MR images with apparent breathing induced sliding motion of the liver along the abdominal wall.

Using a flexibility constrained 3D statistical shape model for robust MRF-based segmentation

In this paper we propose a novel segmentation method that integrates prior shape knowledge obtained from a 3D statistical model into the Markov Random Field (MRF) segmentation framework to deal with severe artifacts, noise and shape deformations. The statistical model is learned using a Probabilistic Principal Component Analysis (PPCA), which allows us to reconstruct the optimal shape and to compute the remaining variance of the statistical model from partial information. The statistical model, with its remaining variance, can then be used to constrain the shape space, which is a more efficient shape update as compared to a regularization-based shape model reconstruction. The reconstructed shape is optimized over an edge weighted unsigned distance map calculated from the current segmentation, and is then used as a shape prior for the next iteration of the segmentation. We show the robustness to high-density imaging artifacts of the proposed method by providing a quantitative and qualitative evaluation to the challenging problem of 3D masseter muscles segmentation from CT datasets.

Automatic, Robust, and Globally Optimal Segmentation of Tubular Structures

We present an automatic three-dimensional segmentation approach based on continuous max flow that targets tubular structures in medical images. Our method uses second-order derivative information provided by Frangi et al.’s vesselness feature and exploits it twofold: First, the vesselness response itself is used for localizing the tubular structure of interest. Second, the eigenvectors of the Hessian eigendecomposition guide our anisotropic total variation–regularized segmentation. In a simulation experiment, we demonstrate the superiority of anisotropic as compared to isotropic total variation–regularized segmentation in the presence of noise. In an experiment with magnetic resonance images of the human cervical spinal cord, we compare our automated segmentations to those of two human observers. Finally, a comparison with a dedicated state-of-the-art spinal cord segmentation framework shows that we achieve comparable to superior segmentation quality.

A Semi-automatic Method for the Quantification of Spinal Cord Atrophy

Due to its high flexibility, the spinal cord is a particularly challenging part of the central nervous system for the quantification of nervous tissue changes. In this paper, a novel semi-automatic method is presented that reconstructs the cord surface from MR images and reformats it to slices that lie perpendicular to its centerline. In this way, meaningful comparisons of cord cross-sectional areas are possible. Furthermore, the method enables to quantify the complete upper cervical cord volume. Our approach combines graph cut for presegmentation, edge detection in intensity profiles for segmentation refinement, and the application of starbursts for reformatting the cord surface. Only a minimum amount of user input and interaction time is required. To quantify the limits and to demonstrate the robustness of our approach, its accuracy is validated in a phantom study and its precision is shown in a volunteer scan–rescan study. The method’s reproducibility is compared to similar published quantification approaches. The application to clinical patient data is presented by comparing the cord cross-sections of a group of multiple sclerosis patients with those of a matched control group, and by correlating the upper cervical cord volumes of a large MS patient cohort with the patients’ disability status. Finally, we demonstrate that the geometric distortion correction of the MR scanner is crucial when quantitatively evaluating spinal cord atrophy.

A primal-dual approach for discontinuity preserving registration

Image registration is a powerful tool in medical image analysis and facilitates the clinical routine in several aspects. There are many well established non-rigid registration methods, but those which are able to preserve discontinuities in the displacement field are rather rare. This paper deals with a nonrigid registration method, that can handle discontinuities in the motion field that appear in particular at organ boundaries during the breathing induced organ motion. Due to the fact that motion segmentation could play a guiding role during discontinuity preserving registration, we therefore embed the registration method in a segmentation framework. Furthermore, we are able to use a primal-dual method to estimate a solution to this complex variational problem. Experimental results are presented for MR Images with apparent breathing induced sliding motion of the liver along the abdominal wall.

A landmark-based primal-dual approach for discontinuity preserving registration

Discontinuous motion is quite common in the medical field as for example in the case of breathing induced organ motion. Registration methods that are able to preserve discontinuities are therefore of special interest. To achieve this goal we developed in our previous work a framework that combines motion segmentation and registration. To avoid unreliable motion fields the incorporation of landmark correspondences can be a remedy. We therefore describe in this paper how we integrate the landmarks in our variational approach and how to solve the minimisation problem with a primal-dual algorithm. Qualitative and quantitative results are shown for real MR images of breathing induced liver motion.

A shape prior-based MRF model for 3D masseter muscle segmentation

Medical image segmentation is generally an ill-posed problem that can only be solved by incorporating prior knowledge. The ambiguities arise due to the presence of noise, weak edges, imaging artifacts, inhomogeneous interior and adjacent anatomical structures having similar intensity profile as the target structure. In this paper we propose a novel approach to segment the masseter muscle using the graph-cut incorporating additional 3D shape priors in CT datasets, which is robust to noise; artifacts; and shape deformations. The main contribution of this paper is in translating the 3D shape knowledge into both unary and pairwise potentials of the Markov Random Field (MRF). The segmentation task is casted as a Maximum-A-Posteriori (MAP) estimation of the MRF. Graph-cut is then used to obtain the global minimum which results in the segmentation of the masseter muscle. The method is tested on 21 CT datasets of the masseter muscle, which are noisy with almost all possessing mild to severe imaging artifacts such as high-density artifacts caused by e.g. the very common dental fillings and dental implants. We show that the proposed technique produces clinically acceptable results to the challenging problem of muscle segmentation, and further provide a quantitative and qualitative comparison with other methods. We statistically show that adding additional shape prior into both unary and pairwise potentials can increase the robustness of the proposed method in noisy datasets.