Extraction of Tenuous Vasculature in Medical Images

This paper presents a method for the extraction of tenuous vasculature in medical images. The method includes the following steps: maximum intensity projection (MIP), two-dimensional vasculature extraction, three-dimensional seed point generation, and three-dimensional vasculature extraction. The regular region growing algorithm is revised and the extraction result is improved. Little intervention is needed during the processing, except that four parameters should be designated.

[1]  Bernhard Preim,et al.  Visualization of anatomic tree structures with convolution surfaces , 2004, VISSYM'04.

[2]  Badrinath Roysam,et al.  Robust model-based vasculature detection in noisy biomedical images , 2004, IEEE Transactions on Information Technology in Biomedicine.

[3]  Sharon A. Stansfield,et al.  ANGY: A Rule-Based Expert System for Automatic Segmentation of Coronary Vessels From Digital Subtracted Angiograms , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Ying Sun,et al.  Back-propagation network and its configuration for blood vessel detection in angiograms , 1995, IEEE Trans. Neural Networks.

[5]  Jayaram K. Udupa,et al.  Artery-vein separation via MRA-An image processing approach , 2001, IEEE Transactions on Medical Imaging.

[6]  P. Choyke,et al.  Gray-scale skeletonization of small vessels in magnetic resonance angiography , 2000, IEEE Transactions on Medical Imaging.