Adaptive Tracking Algorithm Based on Direction Field using ML Estimation in Angiogram

초록

In conventional tracking algorithm, the direction of vessel centerline is varied excessively was corrected variation of vessel diameter due to the centerline inclining and lessened the complex computation. We present a new tracking algorithm for the main artery contour in digital angiogram. The proposed work extracts feature and profiles narrow blood detection by calculating the maximum-likelihood(ML) estimation on adjacent pixels. The proposed algorithm detects the position of centerline as direction vector with entire vessel's direction field adaptively. The ML estimation is most effective at profiling for vessel contour that has anomalies and noise. This proposed algorithm are intended to support radiologists in diagnosis, radiation therapy planning , and surgical planning.