Adaptive tracking algorithm based on direction field using ML estimation in angiogram

We present a new tracking algorithm for the main artery contours in a digital angiogram. The proposed work extracts features and profiles the narrow blood vessel, mainly the blood vessel in the digital subtraction angiography image. A consecutive value is performed on the boundary detection by calculating maximum-likelihood (ML) estimation on adjacent pixels. The proposed algorithm adaptively detects the position of the centerline as a direction vector with the entire vessel's direction field. ML estimation is most effective at profiling for a vessel's contour having anomalies and noise. This proposed algorithm is intended to support radiologists in diagnosis, radiation therapy planning, and surgical planning.