Jürgen Weese

Automatic Model-Based Segmentation of the Heart in CT Images

Automatic image processing methods are a pre-requisite to efficiently analyze the large amount of image data produced by computed tomography (CT) scanners during cardiac exams. This paper introduces a model-based approach for the fully automatic segmentation of the whole heart (four chambers, myocardium, and great vessels) from 3-D CT images. Model adaptation is done by progressively increasing the degrees-of-freedom of the allowed deformations. This improves convergence as well as segmentation accuracy. The heart is first localized in the image using a 3-D implementation of the generalized Hough transform. Pose misalignment is corrected by matching the model to the image making use of a global similarity transformation. The complex initialization of the multicompartment mesh is then addressed by assigning an affine transformation to each anatomical region of the model. Finally, a deformable adaptation is performed to accurately match the boundaries of the patients anatomy. A mean surface-to-surface error of 0.82 mm was measured in a leave-one-out quantitative validation carried out on 28 images. Moreover, the piecewise affine transformation introduced for mesh initialization and adaptation shows better interphase and interpatient shape variability characterization than commonly used principal component analysis.

Multi-scale line segmentation with automatic estimation of width, contrast and tangential direction in 2D and 3D medical images

A new multi-scale segmentation technique for line-like structures in 2D and 3D medical images is presented. It is based on normalized first and second derivatives and on the eigenvector analysis of the hessian matrix. Application areas are the segmentation and tracking of bloodvessels, electrodes, catheters and other line-like objects. It allows for the estimation of the local diameter, the longitudinal direction and the contrast of the vessel and for the distinction between edge-like and line-like structures. The method is applicable as automatic 2D and 3D line-filter, as well as for interactive algorithms that are based on local direction estimation. A 3D line-tracker has been constructed that uses the estimated longitudinal direction as step-direction. After extraction of the centerline, the hull of the structure is determined by a 2D active-contour algorithm, applied in planes, orthogonal to the longitudinal line-direction. The procedure results in a stack of contours allowing quantitative crosssection area determination and visualization by means of a triangulation based rendering.

Automated segmentation of the left ventricle in cardiac MRI

We present a fully automated deformable model technique for myocardium segmentation in 3D MRI. Loss of signal due to blood flow, partial volume effects and significant variation of surface grey value appearance make this a difficult problem. We integrate various sources of prior knowledge learned from annotated image data into a deformable model. Inter-individual shape variation is represented by a statistical point distribution model, and the spatial relationship of the epi- and endocardium is modeled by adapting two coupled triangular surface meshes. To robustly accommodate variation of grey value appearance around the myocardiac surface, a prior parametric spatially varying feature model is established by classification of grey value surface profiles. Quantitative validation of 121 3D MRI datasets in end-diastolic (end-systolic) phase demonstrates accuracy and robustness, with 2.45 mm (2.84 mm) mean deviation from manual segmentation.

Automated 3-D PDM construction from segmented images using deformable models

In recent years, several methods have been proposed for constructing statistical shape models to aid image analysis tasks by providing a priori knowledge. Examples include principal component analysis of manually or semiautomatically placed corresponding landmarks on the learning shapes [point distribution models (PDMs)], which is time consuming and subjective. However, automatically establishing surface correspondences continues to be a difficult problem. This paper presents a novel method for the automated construction of three-dimensional PDM from segmented images. Corresponding surface landmarks are established by adapting a triangulated learning shape to segmented volumetric images of the remaining shapes. The adaptation is based on a novel deformable model technique. We illustrate our approach using computed tomography data of the vertebra and the femur. We demonstrate that our method accurately represents and predicts shapes.

Point-Based Elastic Registration of Medical Image Data Using Approximating Thin-Plate Splines

We consider elastic registration of medical image data based on thin-plate splines using a set of corresponding anatomical point landmarks. Previous work on this topic has concentrated on using interpolation schemes. Such schemes force the corresponding landmarks to exactly match each other and assume that the landmark positions are known exactly. However, in real applications the localization of landmarks is always prone to some error. Therefore, to take into account these localization errors, we have investigated the application of an approximation scheme which is based on regularization theory. This approach generally leads to a more accurate and robust registration result. In particular, outliers do not disturb the registration result as much as is the case with an interpolation scheme. Also, it is possible to individually weight the landmarks according to their localization uncertainty. In addition to this study, we report on investigations into semi-automatic extraction of anatomical point landmarks.

Shape Constrained Deformable Models for 3D Medical Image Segmentation

To improve the robustness of segmentation methods, more and more methods use prior knowledge. We present an approach which embeds an active shape model into an elastically deformable surface model, and combines the advantages of both approaches. The shape model constrains the flexibility of the surface mesh representing the deformable model and maintains an optimal distribution of mesh vertices. A specific external energy which attracts the deformable model to locally detected surfaces, reduces the danger that the mesh is trapped by false object boundaries. Examples are shown, and furthermore a validation study for the segmentation of vertebrae in CT images is presented. With the exception of a few problematic areas, the algorithm leads reliably to a very good overall segmentation.

An approach to 2D/3D registration of a vertebra in 2D X-ray fluoroscopies with 3D CT images

In order to use pre-operative images during an operation for navigation, they must be registered to the patients coordinate system in the operating theater or to an intra-operative image. One problem in this area is the registration of a vertebra in intra-operatively acquired x-ray fluoroscopies with 3D CT images obtained before the intervention. The result can be used to support the placement of pedicle screws in spine surgery or stents in Transfemoral Endovascular Aneurysm Management (TEAM). For this 2D/3D registration task a novel voxel-based method is presented. Using a small part of the CT image covering the vertebra only, pseudo projections are computed and the resulting vertebra template is compared to the x-ray projection. A new similarity measure was introduced for that purpose, because commonly used measures did not work. The method allows for a much faster implementation than other voxel-based 2D/3D registration approaches, because they use the entire CT image to calculate pseudo projections. Unlike contour-based 2D/3D registration approaches, the method does not require segmentation of the vertebras contours in the x-ray projection. Application and performance of the proposed registration method are demonstrated by application to images of a TEAM procedure.

Optimizing boundary detection via Simulated Search with applications to multi-modal heart segmentation

Segmentation of medical images can be achieved with the help of model-based algorithms. Reliable boundary detection is a crucial component to obtain robust and accurate segmentation results and to enable full automation. This is especially important if the anatomy being segmented is too variable to initialize a mean shape model such that all surface regions are close to the desired contours. Several boundary detection algorithms are widely used in the literature. Most use some trained image appearance model to characterize and detect the desired boundaries. Although parameters of the boundary detection can vary over the model surface and are trained on images, their performance (i.e., accuracy and reliability of boundary detection) can only be assessed as an integral part of the entire segmentation algorithm. In particular, assessment of boundary detection cannot be done locally and independently on model parameterization and internal energies controlling geometric model properties. In this paper, we propose a new method for the local assessment of boundary detection called Simulated Search. This method takes any boundary detection function and evaluates its performance for a single model landmark in terms of an estimated geometric boundary detection error. In consequence, boundary detection can be optimized per landmark during model training. We demonstrate the success of the method for cardiac image segmentation. In particular we show that the Simulated Search improves the capture range and the accuracy of the boundary detection compared to a traditional training scheme. We also illustrate how the Simulated Search can be used to identify suitable classes of features when addressing a new segmentation task. Finally, we show that the Simulated Search enables multi-modal heart segmentation using a single algorithmic framework. On computed tomography and magnetic resonance images, average segmentation errors (surface-to-surface distances) for the four chambers and the trunks of the large vessels are in the order of 0.8 mm. For 3D rotational X-ray angiography images of the left atrium and pulmonary veins, the average error is 1.3 mm. In all modalities, the locally optimized boundary detection enables fully automatic segmentation.

A Multi-scale Line Filter with Automatic Scale Selection Based on the Hessian Matrix for Medical Image Segmentation

A multi-scale segmentation technique for line-like structures in 2D and 3D medical images is presented. It is based on normalized second derivatives and on the eigenvector analysis of the Hessian matrix. The method allows for the estimation of the local diameter, the longitudinal direction and the contrast of line-structures and for the distinction between edge-like and line-like structures. The characteristics of the method in respect to several analytic line-profiles as well as the influence of neighboring structures and line-bending is discussed. The method is applied to 3D medical images.

Segmentation of the heart and great vessels in CT images using a model-based adaptation framework

Recently, model-based methods for the automatic segmentation of the heart chambers have been proposed. An important application of these methods is the characterization of the heart function. Heart models are, however, increasingly used for interventional guidance making it necessary to also extract the attached great vessels. It is, for instance, important to extract the left atrium and the proximal part of the pulmonary veins to support guidance of ablation procedures for atrial fibrillation treatment. For cardiac resynchronization therapy, a heart model including the coronary sinus is needed. We present a heart model comprising the four heart chambers and the attached great vessels. By assigning individual linear transformations to the heart chambers and to short tubular segments building the great vessels, variable sizes of the heart chambers and bending of the vessels can be described in a consistent way. A configurable algorithmic framework that we call adaptation engine matches the heart model automatically to cardiac CT angiography images in a multi-stage process. First, the heart is detected using a Generalized Hough Transformation. Subsequently, the heart chambers are adapted. This stage uses parametric as well as deformable mesh adaptation techniques. In the final stage, segments of the large vascular structures are successively activated and adapted. To optimize the computational performance, the adaptation engine can vary the mesh resolution and freeze already adapted mesh parts. The data used for validation were independent from the data used for model-building. Ground truth segmentations were generated for 37 CT data sets reconstructed at several cardiac phases from 17 patients. Segmentation errors were assessed for anatomical sub-structures resulting in a mean surface-to-surface error ranging 0.50-0.82mm for the heart chambers and 0.60-1.32mm for the parts of the great vessels visible in the images.