Advertisement

Neuro-Fuzzy Approach for Reconstruction of 3-D Spine Model Using 2-D Spine Images and Human Anatomy

  • Saurabh AgrawalEmail author
  • Dilip Singh Sisodia
  • Naresh Kumar Nagwani
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 922)

Abstract

The present research paper deals with the reconstruction process of thoracic spine images through 2D thoracic spine x-ray images with the help of Artificial Neural Network and Fuzzy Set Rules. The present work has been carried out in two phases: the Modelling phase and Understanding phase. In the modeling phase, a knowledge-based model has been framed with natural human anatomy spine images collected from different sources. The formation of model has been done after proper selection and extraction of geometric features from natural human anatomy images. The features are based on shape size orientation. In the present paper the main focus has been kept on the extraction of twenty features based on the different orientation of thoracic spine image. A unique innovative approach for feature selection, extraction and mapping are adopted in the present paper for understanding the model, for proper reconstruction of 3D thoracic spine images through thoracic spine X-ray/MRI/CT images. The mapping and classification process has been done using Support Vector Machine. The experimental work has been carried out using Artificial Neural Network and Fuzzy Set Rules.

Keywords

Artificial Neural Network (ANN) Fuzzy Set Rules (FSR) Thoracic spine Neuro-Fuzzy Approach (NFA) 

References

  1. 1.
    Gonzalez, R.C., Woods, R.E.: Digital Image Processing, 3rd edn. Pearson Education, London (2013)Google Scholar
  2. 2.
    Jain, A.K.: Fundamentals of Digital Image Processing. Pearson Education, London (2013)zbMATHGoogle Scholar
  3. 3.
    Long, L.R., Thoma, G.R.: Computer assisted retrieval of biomedical image features from spine x-rays: progress and prospects. Open access. http://archive.nlm.nih.gov/staff/long.php
  4. 4.
    Wang, S., Summers, R.M.: Machine learning and radiology. Medical Image Analysis 16, 933–951 (2012)CrossRefGoogle Scholar
  5. 5.
    Major, D., Hladucvka, J., Schulze, F., Bühler, K.: Automated landmarking and labeling of fully and partially scanned spinal columns in CT images. Med. Image Anal. 17, 1151–1163 (2013)CrossRefGoogle Scholar
  6. 6.
    Wade, R., Yang, H., McKenna, C., Faria, R., Gummerson, N., WoolacottL, N.: A systematic review of the clinical effectiveness of EOS 2D/3D X-ray imaging system. Euro Spine J. 22, 296–304 (2013)CrossRefGoogle Scholar
  7. 7.
    Yvanl, P., Jean, D., Hubert, L., de Guise, J.: 3D radiographic reconstruction of thoracic facet joints. In: The Proceeding of IEEE-EMBC and CMBEC, vol. 2, pp. 397–408 (2005)Google Scholar
  8. 8.
    Lin, H.: The simplified spine modeling by 3-D Bezier curve based on the orthogonal spinal radiographic images. In: The Proceeding of the 25th Annual International Conference of the IEEE EMBS, pp. 945–946 (2006)Google Scholar
  9. 9.
    Delorme, S., Petit, Y., de Guise, J.A., Labelle, H., Aubin, C.-É., Dansereau, J.: Assessment of the 3-D reconstruction and high-resolution geometrical modeling of the human skeletal trunk from 2-D radiographic images. IEEE Trans. Biomed. Eng. 50(8), 989–998 (2003)CrossRefGoogle Scholar
  10. 10.
    Novosad, J., Cheriet, F., Petit, Y., Labelle, H.: Three-dimensional (3-D) reconstruction of spine from a single x-ray image and prior vertebra models. IEEE Trans. Biomed. Eng. 51(9), 1628–1639 (2004)CrossRefGoogle Scholar
  11. 11.
    Lin, H.: Identification of spinal deformity classification with total curvature analysis and artificial neural network. In: The proceedings of the 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference, pp. 6168–6171 (2005)Google Scholar
  12. 12.
    Benjelloun, M., Mahmoudi, S.: Mobility estimation and analysis in medical x-ray images using corners and faces contours detection. In: The Proceeding of International Machine Vision and Image Processing Conference, pp. 106–115 (2007)Google Scholar
  13. 13.
    Zhang, Y., Wang, M., Song, Z.: Multi-step 3D/2D image registration for image-guided spinal surgery. In: The Proceeding of International Conference on BioMedical Engineering and Informatics, pp. 188–192 (2008)Google Scholar
  14. 14.
    Boisvert, J., Cheriet, F., Pennec, X., Labelle, H., Ayache, N.: Articulated spine models for 3-D reconstruction from partial radiographic data. IEEE Trans. Biomed. Eng. 55(11), 2565–2574 (2008)CrossRefGoogle Scholar
  15. 15.
    Kadoury, S., Cheriet, F., Labelle, H.: Segmentation of scoliotic spine silhouettes from enhanced biplanar x-rays using prior knowledge bayesian framework. In: The Proceeding of ISBI, pp. 478–481 (2009)Google Scholar
  16. 16.
    Yang, H., Yu, B., Wang, A.: Measurement of cross-sectional area of spinal canal through coordinate axis rotation and projection transformation. In: The Proceeding of Second International Symposium on Knowledge Acquisition and Modeling, pp. 95–97 (2009)Google Scholar
  17. 17.
    Kadoury, S., Cheriet, F., Labelle, H.: Personalized x-ray 3-D reconstruction of the scoliotic spine from hybrid statistical and image-based models. IEEE Trans. Med. Imaging 28(9), 1422–1435 (2009)CrossRefGoogle Scholar
  18. 18.
    Qian, X., Tagare, H.D., Fulbright, R.K., Long, R., Antani, S.: Optimal embedding for shape indexing in medical image databases. Med. Image Anal. 14, 243–254 (2010)CrossRefGoogle Scholar
  19. 19.
    Punarselvam, E. Suresh, P.: Edge detection of CT scan spine disc image using canny edge detection algorithm based on magnitude and edge length. In: The Proceeding of IEEE, vol.1, pp. 136–140 (2011)Google Scholar
  20. 20.
    Kadoury, S., Labelle, H., Paragios, N.: Automatic inference of articulated spine models in CT images using high-order Markov random fields. Med. Image Anal. 14, 426–437 (2011)CrossRefGoogle Scholar
  21. 21.
    Anitha, H., Prabhu, G.K.: Automatic quantification of spinal curvature in scoliotic radiograph using image processing. J. Med. Syst. 36, 1943–1951 (2012)CrossRefGoogle Scholar
  22. 22.
    Larhmam, M.A., Mahmoudi, S., Benjelloun, M.: Semi-automatic detection of cervical vertebrae in x-ray images using generalized hough transform. In: The Proceeding of Image Processing Theory, Tools and Applications (2012)Google Scholar
  23. 23.
    Wu, C.-C., Li, H.-C., Chiang, Y.-H., Lin, J.: Classification of cross-section area of spinal canal on kernel-based support vector machine. In: The Proceeding of IEEE International Conference on Systems, Man, and Cybernetics, pp. 2622–2625 (2012)Google Scholar
  24. 24.
    Zhang, J., et al.: 3-D reconstruction of the spine from biplanar radiographs based on contour matching using the hough transform. IEEE Trans. Biomed. 60(7), 1954–1964 (2013)CrossRefGoogle Scholar
  25. 25.
    Cortez, S., Claro, J.C.P., Alves, J.L.: 3D reconstruction of a spinal motion segment from 2D medical images: objective quantification of the geometric accuracy of the FE mesh generation procedure. In: The Proceeding of 3rd Portuguese Meeting in Bioengineering (2013)Google Scholar
  26. 26.
    Boev, A., Bregovic, R., Damyanov, D., Gotchev, A.: Anti-aliasing filtering of 2D images for multi-view auto-stereoscopic displays. In: The Proceeding of IEEE, vol. 5, pp. 87–97 (2009)Google Scholar
  27. 27.
    Do, C.M., Javid, B.: 3D integral imaging reconstruction of occluded objects using independent component analysis-based K-means clustering. J. Display Technol. 7(6), 251–262 (2010)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Saurabh Agrawal
    • 1
    Email author
  • Dilip Singh Sisodia
    • 1
  • Naresh Kumar Nagwani
    • 1
  1. 1.National Institute of Technology RaipurRaipurIndia

Personalised recommendations