Ultra Sound Imaging System of Kidney Stones Using Deep Neural Network

  • S. R. BalajiEmail author
  • R. Manikandan
  • S. Karthikeyan
  • R. Sakthivel
Conference paper
Part of the Lecture Notes on Data Engineering and Communications Technologies book series (LNDECT, volume 35)


Magnetic resonance is one of the imaging modality through which medical images can be diagnosed. Each modality like imaging (MRI), Ultrasonography (US), Intravenous Urography (IVU), computed Tomography (CT), Angiography (AG) has their own advantages and disadvantages in various aspects like formation, sensitivity, resolution, level of invasive and cost. Both MRI and CT scan give same information in regarding to kidney imaging. However in MRI, the material gadolinium is associated with Nephroenic Systemic Fibrosis (NSF), which decreases the kidney functioning. The measurement of size and shape of the kidney and evaluation of pelvis and ureters is done by IVU. The major drawback is that, there may be renal failure due to radiation and 1 V contrast administration. In CT the tomographic image is formed by computer processed image, where more information is same as ultrasound. The major advantages are excellent spatial/contrast resolution and low cost. However there is a major drawback of exposure of radiation and contrast dye causes damage to kidney. In Radiography, the kidney stones are distinguished by the ratio of absorption over dark field signal. The limitation of radiography is that it can determine only the intensities of average signal through the projection of x-ray direction. In this project enhancement (Smoothening and Sharpening) technique is used in order to contrast the image. We use the active contour segmentation in order to extract the particular portion of image and then deep neural network is used in order to classify the various types of stones.


Ultra Sound image Deep Neural Network Feature extraction Region of Interest 


  1. 1.
    Hafizah, W.M.: Feature extraction of kidney ultrasound images based on intensity histogram and gray level matrix. In: Sixth Asia Modelling symposium (2012)Google Scholar
  2. 2.
    Martin-Fernandez, M., Alberola-Lopez, C.: An approach for contour detection of human kidneys from ultrasound images using markov random fields and active contours. Med. Image Anal. 9, 1–23 (2005)CrossRefGoogle Scholar
  3. 3.
    Sehrawat, R., Gupta, P., Yadav, R.: Basic of artificial neural network. J. Comput. Sci. Eng. 1 (2015)Google Scholar
  4. 4.
    Shalma Beebi, A., Saranya, D., Sathya, T.: A study on neural networks. Int. J. Innov. Res. Comput. Commun. Eng. 3 (2015)Google Scholar
  5. 5.
    Narkhede, H.P.: Review on image segmentation techniques. Int. J. Sci. Mod. Eng. (IJISME) 1(8) (2013). ISSN: 2319-6386Google Scholar
  6. 6.
    Tsai, A., Yezzi, A., Wells, W., Tempany, C., Tucker, D., Fan, A., Grimson, W.E., Willsky, A.: A shape-based approach to the segmentation of medical images. IEEE Trans. Med. Imaging 22(2) (2003)CrossRefGoogle Scholar
  7. 7.
    Zhang, Y.J.: An overview of image and video segmentation in the last 40 years. In: Proceedings of the 6th International Symposium on Signal Processing and its Applications, pp. 144–151 (2001)Google Scholar
  8. 8.
    Pham, D.L., Xu, C., Princo, J.L.: A survey on current methods in medical image segmentation. Ann. Rev. Biomed. Eng. 2 (1998)CrossRefGoogle Scholar
  9. 9.
    Eleyan, A., Demirel, H.: Co-occurrence matrix and its statistical features as a new approach for face recognition. Turk. J. Electr. Eng. Comput. Sci. 19, 97–107 (2011)Google Scholar
  10. 10.
    Hitesh, M.R., Asari, S.: A research paper on reducion of speckle noise in ultrasound imaging using wavelet and contourlet transform (2011)Google Scholar
  11. 11.
    Rahman, T., Uddin, M.S.: Speckle noise reduction and segmentation of kidney regions from ultrasound image. In: International Conference on Informatics, Electronics and Vision (ICIEV) (2013)Google Scholar
  12. 12.
    Hu, S., Yang, F., Griffa, M., Kaufmann, R., Anton, G., Maier, A., Riess, C.: Towards quantification of kidney stones using x-ray dark-field tomography. In: IEEE 14th International Symposium on Biomedical Imaging (2017). ISSN: 1945-8452Google Scholar
  13. 13.
    Moustafa, A.A.: Performance analysis of artificial neural networks for spatial data analysis. Contemp. Eng. Sci. 4(4), 149–163 (2011)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • S. R. Balaji
    • 1
    Email author
  • R. Manikandan
    • 1
  • S. Karthikeyan
    • 2
  • R. Sakthivel
    • 1
  1. 1.Department of EIEPanimalar Engineering CollegeChennaiIndia
  2. 2.Department of ECESathyabama Institute of Science and TechnologyChennaiIndia

Personalised recommendations