A General Segmentation Scheme for Contouring Kidney Region in Ultrasound Kidney Images using Improved Higher Order Spline Interpolation

Authors: K. Bommanna Raja, M.Madheswaran, K.Thyagarajah

Abstract:

A higher order spline interpolated contour obtained with up-sampling of homogenously distributed coordinates for segmentation of kidney region in different classes of ultrasound kidney images has been developed and presented in this paper. The performance of the proposed method is measured and compared with modified snake model contour, Markov random field contour and expert outlined contour. The validation of the method is made in correspondence with expert outlined contour using maximum coordinate distance, Hausdorff distance and mean radial distance metrics. The results obtained reveal that proposed scheme provides optimum contour that agrees well with expert outlined contour. Moreover this technique helps to preserve the pixels-of-interest which in specific defines the functional characteristic of kidney. This explores various possibilities in implementing computer-aided diagnosis system exclusively for US kidney images.

Keywords: Ultrasound Kidney Image – Kidney Segmentation –Active Contour – Markov Random Field – Higher Order SplineInterpolation

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1081870

References:

[1] Hagen - Ansert S, (1995), ÔÇÿUrinary System, In: Diagnostic Ultrasound-, 4th edition, St. Louis, MO: Mosby/Elsevier.
[2] H.M.Pollack and B.L.McClennan, (2000), ÔÇÿClinical Urography-, 2nd Edition, Philadelphia: W. B. Saunders/Elsevier.
[3] Sheng-Fang Huang, Ruey-Feng Chang, Dar-Ren Chen and Woo Kyung Moon, (2004): ÔÇÿCharacterization of Speculation on Ultrasound Lesions-, IEEE Trans. on Medical Imaging, 23, pp. 111-121.
[4] C.P.Loizou, C.Christodoulou, C.S.Pattischis, R.S.H.Istepanian, M.Pantziaris and A.Nicolaides, (2002):ÔÇÿSpeckle Reduction in Ultrasound Images of Atherosclerotic Carotid Plaque-, Proc. 14th IEEE Intl. Conf. on Digital Signal Processing, Santorini, Greece, pp. 525 - 528.
[5] C.P.Loizou, C.S.Pattischis, R.S.H.Istepanian, M.Pantziaris, T.Tyllis and A.Nicolaides, (2004): ÔÇÿQuality Evaluation of Ultrasound Imaging in the Carotid Artery-, Proc. 12th IEEE Mediterranean Electrotechnical Conference, Dubrovnik-Croatia, pp. 395 - 398.
[6] A.Ahumada and C.Null, (1993): ÔÇÿImage Quality: A Multidimensional Problem-, Digital Images and Human Vision, Branford press: Cambridge Mass.
[7] Bakker, J.,Olree, M., Kaatee, R., de Lange, E.E. and Beek, R.J.A., (1997): ÔÇÿInvitro Measurement of Kidney Size: Comparison of Ultrasonography and MRI-, Ultrasound Med. Biol. 24, pp. 683 - 688.
[8] Matre, K., Stokke, E.M., Martens, D. and Gilja, O.H., (1999): ÔÇÿInvitro Volume Estimation of Kidneys using 3-D Ultrasonography and a Position Sensor-, Eur. J. Ultrasound, 10, pp. 65 - 73.
[9] Jain, A.K., Zhong and Y., Lakshmanan, S., (1996): ÔÇÿObject Matching using Deformable Templates-, IEEE Trans. Patt. Anal. Mach. Intell., 18, pp. 267 - 278.
[10] Jun Xie, Yifeng Jiang and Hung-tat Tsui, (2005): ÔÇÿSegmentation of Kidney from Ultrasound Images Based on texture and Shape Priors-, IEEE Trans. on Medical Imaging, 24 , pp. 45 - 57.
[11] Marcos Martin-Fernandez and Carlos Alberola-Lopez, (2005): ÔÇÿAn Approach for Contour Detection of Human Kidney from Ultrasound Images using Markov Random Fields and Active Contours-, Medical Image Analysis, 9, pp. 1 - 23.
[12] Abouzar Eslami, Shohreh Kasaei and Mehran Jahed, (2004): ÔÇÿRadial Multiscale Cyst Segmentation in Ultrasound Images of Kidney-, Proc. 4th IEEE International Symposium on Signal Processing and Information Technology, Rome, Italy, pp. 42 - 45.
[13] A.Eslami, M.Jahed and M.Naroienejad, (2005): ÔÇÿFully Automated Cyst Segmentation in Ultrasound Images of Kidney-, Proc. 3rd IASTED Intl. Conf. on Biomedical Engineering, Austria, PaperID -19418.
[14] Vikram Chalana and Yongmin Kim, (1997): ÔÇÿA Methodology for Evaluation of Boundary Detection Algorithms on Medical Images-, IEEE Trans. on Medical Imaging, 16, pp. 642 - 652.
[15] Kass, M., Witkin, A., and Terzopoulos, D., (1988): ÔÇÿSnakes: Active Contour Models-, Intl. J. Comp. Vis., 1, pp. 321 - 331.
[16] Cohen, L.D., (1991): ÔÇÿOn Active Contour Models and Balloons-, CVGIP - Image Understanding, 53, pp. 211 - 218.
[17] Marcos Martin and Carlos Alberola, (2002): ÔÇÿA Bayesian Approach to Invivo Kidney Ultrasound Contour Detection Using Markov Random Fields-, Proc. 5th Intl. Conf. on Medical Image Computing and Computer-Assisted Intervention, Tokyo, Japan, pp. 397 - 404.
[18] Friedland, N.S., and Rosenfeld, A., (1989): ÔÇÿVentricular Cavity Boundary Detection from Sequential Ultrasound Images using simulated Annealing-, IEEE Trans. Medical Imaging, 8, pp. 344 - 353.
[19] T.M.Lehmann, C.Gonner and K.Spitzer, (1999): ÔÇÿSurvey: Interpolation Methods in Medical Image Processing-, IEEE Trans. on Medical Imaging, 18, pp. 1049 - 1075.
[20] M.Unser, (1999): ÔÇÿSplines: A perfect fit for Signal and Image Processing-, IEEE Signal Processing Magazine, 16, pp. 22 - 38.
[21] C. de Boor, (1978): ÔÇÿA Practical Guide to Splines-, New York: Springer- Verlag.
[22] M.Unser, A.Aldroubi and M.Eden, (1993): ÔÇÿB-Spline Signal Processing: Part I - Theory-, IEEE Trans. on Signal Processing, 41, pp. 821 - 833.
[23] M.Unser, A.Aldroubi and M.Eden, (1993): ÔÇÿB-Spline Signal Processing: Part II - Efficient Design and Applications-, IEEE Trans. on Signal Processing, 41, pp. 834 - 848.
[24] Bojan Vrcelj and P.P.Vaidyanathan, (2001): ÔÇÿEfficient Implementation of All-Digital Interpolation-, IEEE Trans. on Image Processing, 10, pp. 1639 - 1646.
[25] M.Helbing, L.Kahi, C.Rothlubbers and R.Orgimeister, (1997): ÔÇÿA Reliable Algorithm for Automatic Contour Estimation in Medical Ultrasonic Images of Human Heart-, Proc. 4th Intl. Workshop on Systems, Signals and Image Processing, Poznan, Poland, pp. 141 - 144.
[26] D.P.Huttenlocher, G.A.Klanderman and W.J. Rucklidge, (1993): ÔÇÿComparing Images using Hausdorff Distance-, IEEE Trans. Patt. Anal. Mach. Intell., 15, pp. 850 - 863.