Model Based Segmentation for Retinal Fundus Images
This paper presents a method for detecting and measuring the vascular structures of retinal images. Features are modelled as a superposition of Gaussian functions in a local region. The parameters i.e. centroid, orientation, width of the feature are derived by a minimum mean square error (MMSE) type of spatial regression. We employ a penalised likelihood test, the Akakie Information Criteria (AIC), to select the best model and scale for vessel segments. A maximum-cost spanning tree (MST) algorithm is then used to perform the neighbourhood linking and infer the global vascular structure. We present results of evaluations on a set of twenty digital fundus retinal images.
KeywordsRetinal Image Minimum Mean Square Error Ground Truth Image Spatial Frequency Domain Minimum Mean Square Error Estimation
- 1.H. Shen, C.V. Stewart, B. Roysam, G. Lin, and H.L. Tanenbaum, “Frame-rate spatial referencing based on invariant indexing and alignment with application to online retinal image registration,” IEEE Trans. on PAMI, vol.25, pp.379–384, Mar. 2003.Google Scholar
- 6.A. R. Davies and R. Wilson, “Curve and corner extraction using the multiresolution fourier transform,” in Image Processing and its Applications. 4h IEE Conf., 1992.Google Scholar
- 7.L. Wang and A. Bhalerao, “Detecting branching structures using local gaussian models,” in International Symposium on Biomedical Imaging (ISBI). IEEE, July 2002.Google Scholar
- 8.K.P. Burnham and D.R. Anderson, Model Selection and Inference, Springer-Verlag, 1998.Google Scholar
- 9.A. Bhalerao, E. Thönnes, W. Kendall, and R. Wilson, “Inferring vascular structure from 2d and 3d imagery,” in Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2001.Google Scholar