Abstract
We introduce a fast image processing system that allows to analyse digital data-bases of retinal images in a short time, and to process the image in situ while the patient is examined. While it achieves a comparable quality as state-of-the-art methods, it differs from most of them by the fact that it is extremely fast. Retinal blood vessels are enhanced via convolution with the second derivative of the local Radon kernel. It is rotated by different angles, and it adapts itself via a maximisation procedure to the vessel directions. We combine smoothing along vessel directions with contrast enhancement across them. We detect vessels as connected structures with very few interruptions. A subsequent skeletonisation allows a higher-level description of the vessel tree. To end up with a very fast system, we combine efficient algorithms for numerical integration, differentiation and interpolation, and we propose an automatic parameter selection strategy. Our convolution kernels are precomputed and stored into cached constant memory. All essential subroutines are intrinsically parallel, and the resulting system is implemented on GPUs using CUDA. Our qualitative evaluations with the DRIVE database and our own database show that the system achieves competitive performance. It is possible to process images of size 4, 288 × 2, 848 pixels in 1.2 s on an NVIDIA Geforce GTX680. Compared to our sequential implementation, this amounts to a speed-up by two orders of magnitude.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Chanwimaluang T., Fan G. (2003) An efficient algorithm for extraction of anatomical structures in retinal images. Proc. IEEE Int. Conf. Image Process. 1: 1093–1096
Chapman N., Witt N., Bharat A., et al (2001) Computer algorithms for the automated measurement of retinal arteriolar diameters. British J Ophtalmol 85:74–79
Cormen, T.H., Leiserson, C.E., Rivest, R.L.: Introduction to Algorithms. MIT Press, Cambridge, MA (1990)
Frangi, A.F., Niessen, W.J., Vincken, K.L., Viergever, M.A.: Multiscale vessel enhancement filtering. In: Medical Image Computing and Computer-Assisted Intervention- MICCAI’98, Lecture Notes in Computer Science, vol. 1496, Springer, pp. 130–137 (1998)
Gang L., Chutape O., Krishnan M. (2002) Detection and measurement of vessels in fundus images using amplitude modified second-order Gaussian filter. IEEE Trans. Biomed. Eng. 49(2):168–172
Gao X., Bharat A., Hughes A., et al.: Towards retinal vessel parameterization. In: Medical Imaging 1997: Image Processing, SPIE Proc. vol. 3034, pp. 734–744 (1997)
Gonzalez, R., Woods, R.: Digital Image Processing. Prentice Hall, New Jersey (2002)
Hoover A., Kouznetsova V., Goldbaum M. (2000) Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE Trans. Med. Imaging 19(3):203–210
Hwu, W.M.W.; GPU Computing Gems Emerald Edition. Morgan Kaufmann, Los Altos, CA (2011)
Kirk, D.B.; Hwu, W.M.W.: Programming Massively Parallel Processors: A Hands-on Approach. Morgan Kaufmann, Los Altos, CA (2010)
Krause, M.: Corner detection in digital images using local tomography. Bachelor’s thesis, Department of Mathematics and Computer Science, Saarland University (2006)
Lowell J., Hunter A., Steel D., Basu A., Kennedy R.L. (2004) Measurement of retinal vessel widths from fundus images based on 2-D modeling. IEEE Trans. Med. Imaging 23(10):1196–1204
Mendonça AM., Campilho A. (2006) Segmentation of retinal blood vessels by combining the detection of centerlines and morphological reonstruction. IEEE Trans. Med. Imaging 25(9):1200–1213
Niemeijer, M., van Ginneken, B.: Drive database. www.isi.uu.nl/Research/Databases/DRIVE/results.php(2002)
Niemeijer M., Staal J., van Ginneken B., Loog M., Abrámoff M.: Comparative study of retinal vessel segmentation methods on a new publicly available database. In: Fitzpatrick M., Sonka M. (eds.) Proceedings ofSPIE Medical Imaging,vol. 5370, pp. 648–656 (2004)
NVIDIA.: Nvidia. http://www.nvidia.com (2012)
Ricci E., Perfetti R. (2007) Retinal blood vessel segmentation using line operators and support vector classification. IEEE Trans. Med. Imaging 26(10):1357–1365
Sanders, J., Kandrot, E.: (2011) CUDA by Example, An Introduction to General-Purpose GPU programming. Addison Wesley, Reading, MA
Savarimuthu T.R., Kjaer-Nielsen A., Sorensen A.S. (2011) Real-time medical video processing, enabled by hardware accelerated correlations. J Real-Time Image Process. 6:187–197
Soares JVB., Leandro JJG., Cesar RM Jr., Jelinek HF., Cree MJ. (2006) Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification. IEEE Trans. Med. Imaging 25(9):1214–1222
Sofka M., Stewart C. (2006) Retinal vessel centerline extraction using multiscale matched filters, confidence and edge measures. IEEE Trans. Med. Imaging 25(12):1531–1546
Soille, P.: Morphological Image Analysis. Springer (1999)
Staal J., Abrámoff M.D., Viergever M.A., van Ginneken B. (2004) Ridge-based vessel segmentation in color images of the retina. IEEE Trans. Med. Imaging 23(4):501–509
van Ginkel, M.: Image analysis using orientation space based on steerable filters. PhD thesis, Delft University of Technology. http://www.ph.tn.tudelft.nl/michael/publications.html (2002)
Vermeer K., Vos F., Lemij H., Vossepoel A. (2004) A model based method for retinal blood vessel detection. Comput. Biol. Med. 34:209–219
Wang L., Bhalerao A., Wilson R. (2007) Analysis of retinal vasculature using a multiresolution Hermite model. IEEE Trans. Med. Imaging 26(2):137–152
Acknowledgements
We thank the authors of the DRIVE database for making their database available and thus allowing us to evaluate our results. Furthermore, we like to thank Rüdiger Leilich for providing the tool ”Algo-Verifier” for better visualisation and documentation of the results in our specifically designed database.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Krause, M., Alles, R.M., Burgeth, B. et al. Fast retinal vessel analysis. J Real-Time Image Proc 11, 413–422 (2016). https://doi.org/10.1007/s11554-013-0342-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11554-013-0342-5