Search

Studies have shown that aortic calcification is associated with increased risk of cardiovascular disease. Furthermore, aortic calcium assessment can be performed on standard cardiac calcium scoring Computed Tomography scans, which may help to avoid additional imaging studies. In this paper, we present an entropy-based, narrow band restricted, iterative method for segmentation of the ascending aorta in non-contrast CT images, as a step towards aortic calcification detection and pericardial fat quantitation. First, an estimate of the aorta center and radius is obtained by applying dynamic programming in Hough space. In the second step, these estimates serve to reduce the aorta boundary search area to within a narrow band, and the contour is updated iteratively using dynamic programming methods. Our algorithm is able to overcome the limitations of previous approaches in characterizing (i) the boundary edge features and (ii) non-circular shape at aortic root. The results from the proposed method compare favorably with the manually traced aorta boundaries and outperform other approaches in terms of boundary distance and volume overlap.

Recent studies show that pericardial fat is associated with vascular calcification and cardiovascular risk. The fat is imaged with Computed Tomography (CT) as part of coronary calcium scoring but it is not included in routine clinical analysis due to the lack of automatic tools for fat quantification. Previous attempts to create such an automated tool have the limitations of either assuming a preset threshold or a Gaussian distribution for fat. In order to overcome these limitations, we present a novel approach using a classification-based method to discriminate fat from other tissues. The classifier is constructed from three binary SVM classifiers trained separately for multiple tissues (fat, muscle/blood and calcium), and a specific code is assigned to each tissue type based on the number of classifiers. The decisions of these binary classifiers are combined and compared with previously determined codes using a minimum Hamming decoding distance to identify fat. We also present an improved method for detection of a compact region-of-interest around the heart to reduce the number of false positives due to neighboring organs. The proposed method UH-PFAT attained a maximum overlap of 87%, and an average overlap of 76% with expert annotations when tested on unseen data from 36 subjects. Our method can be improved by identifying additional discriminative features for fat and muscle/blood separation, or by using more advanced classification approaches such as cascaded classifiers to reduce the number of false detections.

Endovascular treatment planning of intracranial aneurysms requires accurate quantification of their geometric parameters, including the neck length, dome height and maximum diameter. Today, the geometry of intracranial aneurysms is typically quantified manually based on three-dimensional (3D) Digital Subtraction Angiography (DSA) images. Since the repeatability of manual measurements is not guaranteed and their accuracy is dependent on the experience of the treating physician, we propose a semi-automated approach for computer-aided measurement of these parameters. In particular, a tubular deformable model, initialized based on user-provided points, is first fit to the surface of the parent artery. An initial estimate of the aneurysmal segment is obtained based on differences between the two surfaces. A 3D deformable contour model is then used to localize the aneurysmal neck and to separate its dome surface from the parent artery. Finally, approaches for estimation of the clinically relevant geometric parameters are applied based on the aneurysmal neck and dome surface. Results on 19 3D DSA datasets of saccular aneurysms indicate that, for the maximum diameter, the standard deviation of the difference between the proposed approach and two independent manual sets of measurements obtained by expert readers is similar to the inter-rater standard deviation. For the neck length and dome height, the results improve considerably if we exclude datasets with high deviation from the manual measurements.

Face recognition performance has always been affected by the different facial expressions a subject may display. In this paper, we present an extension to the UR3D face recognition algorithm, which enables us to decrease the discrepancy in its performance for datasets from subjects with and without a neutral facial expression, from 15% to 3%.

Three dimensional (3D) surfaces can be sampled parametrically in the form of range image data. Smoothing/denoising of such raw data is usually accomplished by adapting techniques developed for intensity image processing, since both range and intensity images comprise parametrically sampled geometry and appearance measurements, respectively. We present a transform-based algorithm for surface denoising, motivated by our previous work on intensity image denoising, which utilizes a non-separable Parseval frame and an ensemble thresholding scheme. The frame is constructed from separable (tensor) products of a piecewise linear spline tight frame and incorporates the weighted average operator and the Sobel operators in directions that are integer multiples of 45°. We compare the performance of this algorithm with other transform-based methods from the recent literature. Our results indicate that such transform methods are suited to the task of smoothing range images.

In this paper we present a non-separable multiresolution structure based on frames which is defined by radial scaling functions of the form of the Shannon scaling function. We also construct the resulting frame multiwavelets, which can be isotropic as well. Our construction can be carried out in any number of dimensions and for a great variety of dilation matrices.