Blob Enhancement and Visualization for Improved Intracranial Aneurysm Detection

Abstract

Several researches have established that the sensitivity of visual assessment of smaller intracranial aneurysms is not satisfactory. Computer-aided diagnosis based on volume rendering of the response of blob enhancement filters may shorten visual inspection and increase detection sensitivity by directing a diagnostician to suspicious locations in cerebral vasculature. We proposed a novel blob enhancement filter based on a modified volume ratio of Hessian eigenvalues that has a more uniform response inside the blob-like structures compared to state-of-the-art filters. Because the response of proposed filter is independent of the size and intensity of structures, it is especially sensitive for detecting small blob-like structures such as aneuryms. We proposed a novel volume rendering method, which is sensitive to signal energy along the viewing ray and which visually enhances the visualization of true positives and suppresses usually sharp false positive responses. The proposed and state-of-the-art methods were quantitatively evaluated on a synthetic dataset and 42 clinical datasets of patients with aneurysms. Because of the capability to accurately enhance the aneurysm's boundary and due to a low number of visualized false positive responses, the combined use of the proposed filter and visualization method ensures a reliable detection of (small) intracranial aneurysms.

Plasma membrane topography governs the three-dimensional dynamic localization of IgM B cell receptor clusters

“…The latrunculin-treated cells showed a surface topography that contained short stretches of curvilinear elevations as well as disorganized blob-like chunks of membrane with varying sizes. To detect both types of structures, two detection filters to each raw image were separately applied, one for curvilinear structures [64] and one blob-shaped structures [65]. To detect structures of different sizes, each filter was applied at multiple scales, using sigma values of 1 and 2 for the curvilinearity filter and sigma values of 1, 2 and 3 for the blob filter.…”

Automatic detection of intracranial aneurysms in 3D-DSA based on a Bayesian optimized filter

“…Based on the Hessian matrix eigenvalue attributes of 3D images, different filters can be constructed to enhance a specific shape structure. In this paper, inspired by the method proposed by Jerman [ 31 ], we used an enhancement filter that combines these eigenvalues to detect intracranial aneurysms as follows: where denotes at scale s ; the minimum of all is computed to find the eigenvalue with the highest magnitude. The value of determines the response intensity of the filter.…”

Validation and Optimization of an Image-Based Screening Method Applied to the Study of Neuronal Processes on Nanogrooves

“…Orientation of detected neurites for each image (Figure 2C ) was calculated using a custom algorithm, which was kindly supplied by Biomedical Engineering and developed by Stefan Mariën at the Eindhoven University of Technology; this algorithm is based on the Frangi vesselness filter ( Frangi et al, 1998 ). Algorithms based on the Frangi vesselness filter have previously been used to measure collagen fiber orientation ( Foolen et al, 2012 ; van Spreeuwel et al, 2014 ), and scripts are available based on medical image improvement filters such as with 2D and 3D angiographic images ( Jerman et al, 2016a , b ). In brief, the Frangi vesselness filter uses the Hessian, which is a matrix of second-order partial derivatives, of a Gaussian kernel convoluted with a presented image to calculate eigenvalues and thereby locally determines vesselness likelihood.…”