Rudi Verbeeck

Continuous voxel classification by stochastic relaxation: theory and application to MR imaging and MR angiography

Abstract In this paper we present a stochastic relaxation method for voxel classification in magnetic resonance (MR) images. This method is based on Bayesian decision theory. In this framework, the optimal classification corresponds to the minimum of an objective function, which is here defined as the expected number of misclassified voxels. The objective function encodes constraints according to two a priori models: the scene model and the camera model. The scene model reflects a priori knowledge of anatomy and morphology; the camera model relates observed MR-image intensities to anatomical objects. Both models are described using the concept of Markov random fields (MRF). This allows continuity and local contextual constraints to be easily modelled via the associated Gibbs Potential Functions. The minimum of the objective function is approximated asymptotically by stochastically sampling the associated Gibbs posterior joint probability distribution. The method is applied to brain tissue classification in MRI and blood vessel classification in MR angiograms. Each application contains a novel aspect: in the former, we introduce topological constraints on neighbouring tissues; in the latter, we incorporate shape constraints on cylindrical structures.

Computer assisted stereotactic neurosurgery

Abstract We present a software package for the manipulation of multimodality digital images for computer assisted stereotactic neurosurgery. Stereotactic neurosurgery uses imaging data to guide a surgical instrument to reach an intracerebral target through a small bore-hole in the skull. Besides the specific requirements for image acquisition, we discuss the different functions of the package: image transfer, geometric calibration of CT, MR and DSA, user interfacing and display modalities (multi-planar reslicing, angiographie projections). We finally demonstrate the improved functionality by reporting on some typical clinical cases for functional neursurgery and stereotactic biopsies.

Continuous Voxel Classification by Stochastic Relaxation: Theory and Application to MR Imaging and MR Angiography

In this paper we present a stochastic relaxation method based on Bayesian decision theory for voxel classification in medical images. The labels are continuous (as opposed to discrete) values representing the degree of belief that a voxel belongs to a certain object class.

Protocol for the clinical functionality assessment of a workstation for stereotactic neurosurgery

The objective of this study is to establish a protocol for the technical and clinical evaluation of a workstation for the planning of stereotactic neurosurgical interventions that has been developed in the framework of a joint European research project. Although several such workstations have been proposed before, they lacked the final and most important step, that of clinical validation. They failed to rigorously prove that their product was useful. The authors present a new method that is applicable to the evaluation of a wide range of medical technologies. Their protocol basically assesses the clinical relevance of the user requirements that are at the root of the development of the new technology. The evaluation consists of two stages. During functional specification, iterative prototyping is used to establish the clinical requirements and to assure the quality of the final product. A case study design is used in a second stage that assesses the clinical usability. A before-after study gives a first indication of cost effectiveness and improvement of health care quality.

Model-Based Image Segmentation: Methods and Applications

We discuss different methods and applications of model-based segmentation of medical images. In this paper model-based segmentation is defined as the assignment of labels to pixels or voxels by matching the a priori known object model to the image data. Labels may have probabilities expressing their uncertainty. Particularly we compare optimization methods with the knowledge-based system approach.

Magnetic resonance voxel labeling based on Bayesian Decision Theory

In this paper, Bayesian decision theory is applied to the labelling of voxels in Magnetic Resonance (MR) images of the brain. The Bayes optimal decision rule defines a cost function that consists of a loss function weighted by the a posteriori probability of the labelling. Two options for the loss function are presented in this paper. A zero-one loss function gives rise to the maximum a posteriori (MAP) estimate, which requires a simulated annealing optimization process. The probability term of the cost function is the product of the a priori probability of the labelling (or an a priori model of the underlying scene) and the conditional probability of the data, given the labelling (or the model for the imaging modality). By modelling the label image as a Markov random field, the model for the underlying scene can be described by a Gibbs distribution. In the application discussed, here, they reflect the compatibility of anatomical structures. The imaging method represents the expected voxel intensities and possible noise or image distortions.

How does the stereotactic workstation help the neurosurgeon

At the KUL University of Leuven a workstation for the planning of neurosurgical stereotactic procedures has been developed. Its benefits are illustrated in three exemplary cases. The CT and/or MR images, acquired under stereotactic conditions, are transmitted via a PACS network (picture archiving and communication systems) directly to the stereotactic workstation in the operating theater. Target and entry point can be accurately defined on zoomed images. The trajectory can be checked and modified on all registered data sets and on resliced images along any plane. Maximum intensity projection of magnetic resonance angiography data sets along any arbitrary direction show the relative position of the blood vessels and the trajectory. During the preceding 32 months 29 patients were operated on using the stereotactic workstation. Postoperatively no new neurological deficit was observed in any of these patients. The workstation improves patient safety and increases the accuracy of neurosurgical stereotactic operations, because it helps the neurosurgeon to avoid blood vessels and/or important functional areas.

FUZZY VOXEL LABELING OF MAGNETIC RESONANCE IMAGES BY GLOBAL OPTIMIZATION

In this paper, we present a probabilistic method that is devised to improve the visual representation and the quantitative analysis of magnetic resonance (MR) images. The result of this procedure can be seen as a “fuzzy” labeling of the image voxels (where the voxel intensity represents the degree of belief that the voxel belongs to a certain object class).

Prototype medical workstation for computer-assisted stereotactic neurosurgery

We present a prototype system for computer assisted stereotactic neurosurgery. It is especially suited to integrate vascular data with the stereotactic trajectory and with other information obtained from different imaging modalities. Patient image data from CT, MRI and DSA are acquired using a patient-fixed stereotactic frame with additional external markers for image registration. After preprocessing, all data are available for stereotactic planning and confirmation of electrode positioning. Interactive 3D devices simulate the electrode trajectory, which is projected on a stereoscopic set of angiograms. Alternatively, cross-sections of this trajectory with each of the CT or MR slices can be calculated at the same time. Additional features such as reslicing of the original CT or MR slices along the probe trajectory, are being implemented. All software is written on a 3D graphics workstation. In addition, we use a stereoscopic imaging system employing electro-optical shuttering glasses, and a 3D cursor in stylus form for the simulation of the electrode trajectory.