Boundary detection of kidney ultrasound image based on vector graphic approach

This paper presents a new approach for boundary detection of kidney from three-dimensional ultrasound images. The technique proposed here is based on vector graphic image formation. Before converting the ultrasound image into vector graphic image, the region of interest (ROI) of the kidney for each slice was generated automatically. Some images also needed to be rotated to zero degree depending on the position of the kidney in the images. After the vector graphic formation, the boundary points of the kidney were identified. The error points were removed and the interpolation was then performed for contouring the kidney from its background. Experiments had been carried out step by step for validation purposes. Test result based on 30 kidney ultrasound image slices showed that the developed algorithms were able to detect 86.67% true ROIs. When compared to manual contouring, the sensitivity of this boundary detection technique was in between 94.95% to 97.75% and the specificity was in between 99.26% to 99.92%. Based on the results, it can be concluded that this new semi-automatic technique is reliable to be used for contouring the kidney from three-dimensional ultrasound images.

[1]  Vijay Jeyakumar,et al.  QUANTITATIVE ANALYSIS OF SEGMENTATION METHODS ON ULTRASOUND KIDNEY IMAGE , 2013 .

[2]  Raja Muthupillai,et al.  Normal values for renal length and volume as measured by magnetic resonance imaging. , 2006, Clinical journal of the American Society of Nephrology : CJASN.

[3]  Baining Guo,et al.  Real-time texture synthesis by patch-based sampling , 2001, TOGS.

[4]  Eko Supriyanto,et al.  Assessment of Kidney Volume Measurement Techniques for Ultrasound Images , 2014 .

[5]  Shimon Ullman,et al.  Object Classification Using a Fragment-Based Representation , 2000, Biologically Motivated Computer Vision.

[6]  Ravindra S. Hegadi,et al.  Kidney Segmentation from Ultrasound Images using Gradient Vector Force , 2010 .

[7]  Shimon Ullman,et al.  Class-Specific, Top-Down Segmentation , 2002, ECCV.

[8]  T. Shimamura,et al.  Smooth region ’ s mean deviation-based denoising method , .

[9]  William T. Freeman,et al.  Example-Based Super-Resolution , 2002, IEEE Computer Graphics and Applications.

[10]  Leo Joskowicz,et al.  Non-parametric Iterative Model Constraint Graph min-cut for Automatic Kidney Segmentation , 2010, MICCAI.

[11]  Daniel Cohen-Or,et al.  Fragment-based image completion , 2003, ACM Trans. Graph..

[12]  O. Faugeras,et al.  Statistical shape influence in geodesic active contours , 2002, 5th IEEE EMBS International Summer School on Biomedical Imaging, 2002..

[13]  Gupta Supratim,et al.  Comparative Evaluation of Ultrasound Kidney Image Enhancement Techniques , 2011 .

[14]  P. Thangaraj,et al.  Improved Gabor Filter for Extracting Texture Edge Features in Ultrasound Kidney Images , 2010 .

[15]  M. Dewal,et al.  Ultrasound Imaging and Image Segmentation in the area of Ultrasound: A Review , 2010 .

[16]  Suyash P. Awate,et al.  Image denoising with unsupervised, information-theoretic, adaptive filtering , 2004 .

[17]  B. Leibovich,et al.  A simple method to estimate renal volume from computed tomography. , 2013, Canadian Urological Association journal = Journal de l'Association des urologues du Canada.

[18]  Alexei A. Efros,et al.  Image quilting for texture synthesis and transfer , 2001, SIGGRAPH.

[19]  Yang Tang,et al.  Automatic renal segmentation applied in pediatric MR Urography , 2010, Int. J. Intell. Inf. Process..

[20]  Bum Soon Choi,et al.  A comparative study of methods of estimating kidney length in kidney transplantation donors. , 2007, Nephrology, dialysis, transplantation : official publication of the European Dialysis and Transplant Association - European Renal Association.

[21]  Vibhakar Shrimali,et al.  Current Trends in Segmentation of Medical Ultrasound B-mode Images: A Review , 2009 .

[22]  L. Cohen,et al.  Kidney Detection and Segmentation in Contrast-Enhanced Ultrasound 3D Images , 2014 .