Automatic Segmentation of Blood Vessels in Colour Retinal Images using Spatial Gabor Filter and Multiscale Analysis

Retinal blood vessels are significant anatomical structures in ophthalmic images. Automatic segmentation of blood vessels is one of the important steps in computer aided diagnosis system for the detection of diseases such as Diabetic Retinopathy that affect human retina. We propose a method for the segmentation of retinal blood vessels using Spatial Gabor filters as they can be tuned to the specific frequency and orientation. A new parameter is defined to facilitate filtering at different scales to detect the vessels of varying thicknesses. The method is tested on forty colour retinal images of DRIVE (Digital Retinal Images for Vessel Extraction) database with manual segmentations as ground truth. An overall accuracy of 84.22% is achieved for segmentation of retinal blood vessels.

[1]  R.M. Rangayyan,et al.  Detection of Blood Vessels in the Retina Using Gabor Filters , 2007, 2007 Canadian Conference on Electrical and Computer Engineering.

[2]  Frédéric Zana,et al.  Segmentation of vessel-like patterns using mathematical morphology and curvature evaluation , 2001, IEEE Trans. Image Process..

[3]  Ming Zhang,et al.  On the Small Vessel Detection in High Resolution Retinal Images , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[4]  A. Pinz,et al.  Mapping the human retina , 1996, IEEE Transactions on Medical Imaging.

[5]  M. Goldbaum,et al.  Detection of blood vessels in retinal images using two-dimensional matched filters. , 1989, IEEE transactions on medical imaging.

[6]  Pascale Massin,et al.  A contribution of image processing to the diagnosis of diabetic retinopathy-detection of exudates in color fundus images of the human retina , 2002, IEEE Transactions on Medical Imaging.

[7]  Yoshinobu Sato,et al.  Orientation Space Filtering for Multiple Orientation Line Segmentation , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Yulong Shen,et al.  Registration and fusion of retinal images-an evaluation study , 2003, IEEE Transactions on Medical Imaging.

[9]  A.D. Hoover,et al.  Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response , 2000, IEEE Transactions on Medical Imaging.

[10]  Di Wu,et al.  On the adaptive detection of blood vessels in retinal images , 2006, IEEE Transactions on Biomedical Engineering.

[11]  C. Sinthanayothin,et al.  Automated localisation of the optic disc, fovea, and retinal blood vessels from digital colour fundus images , 1999, The British journal of ophthalmology.

[12]  Tai Sing Lee,et al.  Image Representation Using 2D Gabor Wavelets , 1996, IEEE Trans. Pattern Anal. Mach. Intell..