Retinal Vasculature Segmentation Using Wavelets and Supervised Classification

• João V. B. Soares USP
• Roberto M. Cesar Jr. USP

Abstract

Segmentation of the retinal vasculature is a first step towards automated screening for diabetic retinopathy, a leading cause of adult blindness, but which can be prevented if identified early enough. This paper summarizes the retinal vasculature segmentation approach developed combining the twodimensional continuous wavelet transform and supervised pixel classification. The open source software developed for testing and demonstration is also described. Experimental evaluation using receiver operating characteristic (ROC) analysis on two public image databases yields areas under the ROC curves slightly superior to those presented by other state-of-the-art methods, while minimizing the need for user interaction and showing efficient computing times.

References

Chaudhuri, S., Chatterjee, S., Katz, N., Nelson, M., and Goldbaum, M. (1989). Detection of blood vessels in retinal images using two-dimensional matched filters. IEEE Transactions on Medical Imaging, 8(3):263–269.

Cornforth, D. J., Jelinek, H. F., Leandro, J. J. G., Soares, J. V. B., Cesar-Jr., R. M., Cree, M. J., Mitchell, P., and Bossomaier, T. R. J. (2005). Development of retinal blood vessel segmentation methodology using wavelet transforms for assessment of diabetic retinopathy. Complexity International, 11.

Jelinek, H. F., Cree, M. J., Leandro, J. J. G., Soares, J. V. B., Cesar-Jr., R. M., and Luckie, A. (2007). Automated segmentation of retinal blood vessels and identification of proliferative diabetic retinopathy. J. Opt. Soc. Am. A, 24(5):1448–1456.

Jiang, X. and Mojon, D. (2003). Adaptive local thresholding by verification-based multi-threshold probing with application to vessel detection in retinal images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(1):131–137.

Soares, J. V. B. (2006). Segmentação de vasos sangüíneos em imagens de retina usando wavelets e classificadores estatísticos. Master’s thesis, Institute of Mathematics and Statistics - University of São Paulo. Available from [link].

Soares, J. V. B. and Cesar-Jr., R. M. (2007). Segmentation of retinal vasculature using wavelets and supervised classification: Theory and implementation. In Jelinek, H. F. and Cree, M. J., editors, Automated Image Detection of Retinal Pathology. CRC Press. To appear.

Soares, J. V. B., Leandro, J. J. G., Cesar-Jr., R. M., Jelinek, H. F., and Cree, M. J. (2005). Using the 2-D Morlet wavelet with supervised classification for retinal vessel segmentation. In IV Workshop of Theses and Dissertations, CD-ROM - 18th Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI), Natal, Brazil.

Soares, J. V. B., Leandro, J. J. G., Cesar-Jr., R. M., Jelinek, H. F., and Cree, M. J. (2006). Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification. IEEE Transactions on Medical Imaging, 25(9):1214–1222.

Staal, J. J., Abràmoff, M. D., Niemeijer, M., Viergever, M. A., and van Ginneken, B. (2004). Ridge based vessel segmentation in color images of the retina. IEEE Transactions on Medical Imaging, 23(4):501–509.