Different Regions Identification in Composite Strain-Encoded (C-SENC) Images Using Machine Learning Techniques

  • Abdallah G. Motaal
  • Neamat El-Gayar
  • Nael F. Osman
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5998)


Different heart tissue identification is important for therapeutic decision-making in patients with myocardial infarction (MI), this provides physicians with a better clinical decision-making tool. Composite Strain Encoding (C-SENC) is an MRI acquisition technique that is used to acquire cardiac tissue viability and contractility images. It combines the use of blackblood delayed-enhancement (DE) imaging to identify the infracted (dead) tissue inside the heart muscle and the ability to image myocardial deformation from the strain-encoding (SENC) imaging technique. In this work, various machine learning techniques are applied to identify the different heart tissues and the background regions in the C-SENC images. The proposed methods are tested using numerical simulations of the heart C-SENC images and real images of patients. The results show that the applied techniques are able to identify the different components of the image with a high accuracy.


Support Vector Machine Radial Basis Function Confusion Matrix Region Identification Slice Profile 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Ibrahim, E.-S.H., Stuber, M., Kraitchman, D.L., Weiss, R.G., Osman, N.F.: Combined Functional and Viability Cardiac MR Imaging in a Single Breathhold. Magn. Reson. Med. 58, 843–849 (2007)CrossRefGoogle Scholar
  2. 2.
    Watzinger, N., Saeed, M., Wendland, M.F., Akbari, H., Lund, G., Higgins, C.B.: Myocardial viability: magnetic resonance assessment of functional reserve and tissue characterization. J. Cardiovasc. Magn. Reson. 3, 195–208 (2001)CrossRefGoogle Scholar
  3. 3.
    Kim, R.J., Wu, E., Rafael, A., Chen, E., Parker, M.A., Simonetti, O., Klocke, F.J., Bonow, R.O., Judd, R.M.: The use of contrast-enhanced magnetic resonance imaging to identify reversible myocardial dysfunction. N. Engl. J. Med. 343, 1445–1453 (2000)CrossRefGoogle Scholar
  4. 4.
    Osman, N.F., Sampath, S., Atalar, E., Prince, J.L.: Imaging longitudinal cardiac strain on short-axis images using strain-encoding MRI. Magn. Reson. Med. 46, 324–334 (2001)CrossRefGoogle Scholar
  5. 5.
    Ibrahim, E.-S.H., Weiss, R.G., Stuber, M., Spooner, A.E., Osman, N.F.: Identification of Different Heart Tissues from MRI C-SENC Images Using an unsupervised Multi-Stage Fuzzy Clustering Technique. J. Magn. Reson. Imaging 28(2), 519–526 (2008)CrossRefGoogle Scholar
  6. 6.
    Motaal, A.G., El Gayar, N., Osman, N.F.: Automated Cardiac-Tissue Identification in Composite Strain-Encoded (C-SENC) Images Using Fuzzy C-means and Bayesian Classifier. Accepted in 4th International Conference on Bioinformatics and Biomedical Engineering (iCBBE 2010), Chengdu, China (2010)Google Scholar
  7. 7.
    Sharma, P., Socolow, J., Patel, S., Pettigrew, R., Oshinski, J.: Effect of Gd-DTPA-BMA on blood and myocardial T1 at 1.5T and 3T in humans. Magn. Reson. Imaging 23, 323–330 (2006)CrossRefGoogle Scholar
  8. 8.
    Witten, L.I., Frank, E.: Data Mining: Practical Machine Learning Tools and Techniques with Java Implmentations. Morgan Kaufmann, San Francisco (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Abdallah G. Motaal
    • 1
  • Neamat El-Gayar
    • 1
    • 2
  • Nael F. Osman
    • 1
    • 3
  1. 1.Center for Informatics SciencesNile UniversityEgypt
  2. 2.Faculty of Computers and InformationCairo UniversityGizaEgypt
  3. 3.Radiology Department, School of MedicineJohns Hopkins UniversityUSA

Personalised recommendations