Schaap Michiel, Smal Ihor, Metz Coert, van Walsum Theo, Niessen Wiro
Biomedical Imaging Group Rotterdam, Departments of Radiology and Medical Informatics Erasmus MC - University Medical Center Rotterdam.
Inf Process Med Imaging. 2007;20:74-85. doi: 10.1007/978-3-540-73273-0_7.
Tracking of tubular elongated structures is an important goal in a wide range of biomedical imaging applications. A Bayesian tube tracking algorithm is presented that allows to easily incorporate a priori knowledge. Because probabilistic tube tracking algorithms are computationally complex, steps towards a computational efficient implementation are suggested in this paper. The algorithm is evaluated on 2D and 3D synthetic data with different noise levels and clinical CTA data. The approach shows good performance on data with high levels of Gaussian noise.
追踪管状细长结构是众多生物医学成像应用中的一个重要目标。本文提出了一种贝叶斯管追踪算法，该算法能够轻松融入先验知识。由于概率管追踪算法计算复杂，本文提出了迈向高效计算实现的步骤。该算法在具有不同噪声水平的二维和三维合成数据以及临床CTA数据上进行了评估。该方法在具有高高斯噪声水平的数据上表现出良好性能。
