Title :
Vessel scale-selection using MRF optimization
Author :
Mirzaalian, Hengameh ; Hamarneh, Ghassan
Author_Institution :
Med. Image Anal. Lab., Simon Fraser Univ., BC, Canada
Abstract :
Many feature detection algorithms rely on the choice of scale. In this paper, we complement standard scale-selection algorithms with spatial regularization. To this end, we formulate scale-selection as a graph labeling problem and employ Markov random field multi-label optimization. We focus on detecting the scales of vascular structures in medical images. We compare the detected vessel scales using our method to those obtained using the selection approach of the well-known vesselness filter (Frangi et al 1998). We propose and discuss two different approaches for evaluating the goodness of scale-selection. Our results on 40 images from the Digital Retinal Images for Vessel Extraction (DRIVE) database show an average reduction in these error measurements by more than 15%.
Keywords :
Markov processes; blood vessels; feature extraction; graph theory; medical image processing; optimisation; MRF optimization; Markov random field multilabel optimization; feature detection; graph labeling problem; medical images; spatial regularization; standard scale-selection algorithm; vascular structures; vessel scale-selection; vesselness filter; Biomedical imaging; Computer vision; Detection algorithms; Detectors; Filters; Image analysis; Image databases; Markov random fields; Pixel; Retina;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
978-1-4244-6984-0
DOI :
10.1109/CVPR.2010.5540051