Snakules: A Model-Based Active Contour Algorithm for the Annotation of Spicules on Mammography

Abstract

Abstract-We have developed a novel, model-based active contour algorithm, termed "snakules", for the annotation of spicules on mammography. At each suspect spiculated mass location that has been identified by either a radiologist or a computer-aided detection (CADe) algorithm, we deploy snakules that are converging open-ended active contours also known as snakes. The set of convergent snakules have the ability to deform, grow and adapt to the true spicules in the image, by an attractive process of curve evolution and motion that optimizes the local matching energy. Starting from a natural set of automatically detected candidate points, snakules are deployed in the region around a suspect spiculated mass location. Statistics of prior physical measurements of spiculated masses on mammography are used in the process of detecting the set of candidate points. Observer studies with experienced radiologists to evaluate the performance of snakules demonstrate the potential of the algorithm as an image analysis technique to improve the specificity of CADe algorithms and as a CADe prompting tool.

Active segmentation of 3D axonal images

“…However, a problem encountered when segmenting open-ended curvilinear structures such as axons, is that the length of the structure is not known a priori. To solve this problem, we adopt a scheme that we have used previously to segment open-ended curvilinear structures on mammograms [9]. Essentially, we let the active contour curve alternately grow and deform.…”

“…We do not use a stopping criterion but rely on a fixed number of iterations, though a stopping criterion based on factors such as curvature could easily be incorporated. For instance, in our previous work [9], we have used a curvature based stopping criterion for openended active contours, where the growth of the contour was terminated at a point where the curvature exceed a 30…”

“…Active contour models, also known as snakes [6], [7], [8], are commonly employed to represent and track objects of interest in natural and medical images. While the traditional application of active contour models has been the representation of closed regions in images, they have been applied in a few applications involving segmentation of openended curvilinear structures [9], [10], particularly in 3D.…”

Semantic, Automatic Image Annotation Based on Multi-Layered Active Contours and Decision Trees

“…The active contour approach [10] does not present this drawback as it delineates the boundaries of the entire object. However, active contours have been used up to now only for semi-automatic graphic annotation processes [8], [17], [9], thus not providing fully automatic graphic nor semantic annotations, as these specific implementations found in the literature present weaknesses in presence of noise and do not offer any semantic computational framework.…”

Active contours with neighborhood-extending and noise-smoothing gradient vector flow external force

“…Since the external force defines the evolution of an active contour, many external force models have been proposed [5][6][7][8][9][10][11][12][13][14]. Among these, the gradient vector flow (GVF) [10] has been most successful, as it provides a large capture range and the ability to capture concavities by diffusing the gradient vectors of an edge map generated from the image.…”