Learn More
The detection of image features is an essential component of medical image processing, and has wide-ranging applications including adaptive filtering, segmentation, and registration. In this paper, we present an information-theoretic approach to feature detection in ultrasound images. Ultrasound images are corrupted by speckle noise, which is a disruptive(More)
This study aims to generate synthetic and realistic retinal fundus colour images, similar in characteristics to a given dataset, as well as the values of all morphological parameters. A representative task could be, for example, the synthesis of a retinal image with the corresponding vessel tree and optic nerve head binary map, measurement of vessel width(More)
Segmentation of ultrasound images is a challenging problem due to speckle, which corrupts the image and can result in weak or missing image boundaries, poor signal to noise ratio and diminished contrast resolution. Speckle is a random interference pattern that is characterized by an asymmetric distribution as well as significant spatial correlation. These(More)
Segmentation of arterial wall boundaries from intravascu-lar images is an important problem for many applications in study of plaque characteristics, mechanical properties of the arterial wall, its 3D reconstruction, and its measurements such as lumen size, lumen radius, and wall radius. We present a shape-driven approach to segmentation of the arterial(More)
PURPOSE Computed tomographic (CT) colonography is a relatively new technique for detecting bowel cancer or potentially precancerous polyps. CT scanning is combined with three-dimensional (3D) image reconstruction to produce a virtual endoluminal representation similar to optical colonoscopy. Because retained fluid and stool can mimic pathology, CT data are(More)
This paper presents a new, fully automatic method of accurately extracting lesions from CT data. It first determines, at each voxel, a five-dimensional feature vector that contains intensity, shape index, and 3D spatial location. Then, non-parametric mean shift clustering is applied to produce intensity and shape mode maps. Finally, a graph cut algorithm(More)
The most frequent cause of heart attack and sudden cardiac death is the disruption of plaque build ups in the arteries. Current technologies such as intravascular ultrasound (IVUS) and optical coherence tomography (OCT) image the vessels from inside-out in order to detect plaque deposits as well as other structures. In this work we develop a novel image(More)
In building robust classifiers for computer-aided detection (CAD) of lesions, selection of relevant features is of fundamental importance. Typically one is interested in determining which, of a large number of potentially redundant or noisy features, are most discriminative for classification. Searching all possible subsets of features is impractical(More)