Farsad Zamani Boroujeni, Rahmita Wirza O.K. Rahmat, Norwati Mustapha, Lilly Suriani Affendey and Oteh Maskon, Automatic Selection of Initial points for Exploratory Vessel Tracing in Fluoroscopic Images, Defence Science Journal, Vol. 61, No. 5, pp 443-451, 2011. (IF: 0.304)
ABSTRACT
Automatic extraction of vessel centerlines is viewed as an essential process in majority of image-guided diagnostic and therapeutic applications. Among a considerable number of methods, direct exploratory tracing method is known as an efficient solution for reliable extraction of vessel features from two-dimensional fluoroscopic images. The first step of most automatic exploratory tracing algorithms is to collect some candidate initial seed points as well as their initial tracing directions. To detect reliable initial points, a validation procedure is required to filter out the false candidates and avoid unnecessary tracing. Starting from reliable initial points, the algorithm efficiently extracts the centerline points along the initial direction until certain pre-defined criteria are met. However, most of these algorithms suffer from incomplete results due to inappropriate selection of the initial seed points. The conventional seed point selection algorithms either rely merely on signal-to-noise ratio analysis, which results in a large number of false traces, or impose a set of strict geometrical validation rules which leads to more false negatives and as a consequence more time shall be spent on computation. This paper presents a new method for efficient selection of initial points for exploratory tracing algorithms. The proposed method improves the performance upon existing methods by employing a combination of geometrical and intensity-based approaches. Moreover, it provides a tunable trade-off between the strictness of the validation procedure and computational efficiency. The results of comparative performance with other proposed techniques are included.
Automatic extraction of vessel centerlines is viewed as an essential process in majority of image-guided diagnostic and therapeutic applications. Among a considerable number of methods, direct exploratory tracing method is known as an efficient solution for reliable extraction of vessel features from two-dimensional fluoroscopic images. The first step of most automatic exploratory tracing algorithms is to collect some candidate initial seed points as well as their initial tracing directions. To detect reliable initial points, a validation procedure is required to filter out the false candidates and avoid unnecessary tracing. Starting from reliable initial points, the algorithm efficiently extracts the centerline points along the initial direction until certain pre-defined criteria are met. However, most of these algorithms suffer from incomplete results due to inappropriate selection of the initial seed points. The conventional seed point selection algorithms either rely merely on signal-to-noise ratio analysis, which results in a large number of false traces, or impose a set of strict geometrical validation rules which leads to more false negatives and as a consequence more time shall be spent on computation. This paper presents a new method for efficient selection of initial points for exploratory tracing algorithms. The proposed method improves the performance upon existing methods by employing a combination of geometrical and intensity-based approaches. Moreover, it provides a tunable trade-off between the strictness of the validation procedure and computational efficiency. The results of comparative performance with other proposed techniques are included.
Keywords: Centerline extraction, coronaries, exploratory tracing, seed point detection, tracking
