Advertisement

Segmentation of Chest Radiographs for Tuberculosis Screening Using Kernel Mapping and Graph Cuts

  • Ayesha Fatima
  • Anam Tariq
  • Mahmood Akhtar
  • Hira Zahid
Chapter
Part of the EAI/Springer Innovations in Communication and Computing book series (EAISICC)

Abstract

Segmentation of lung region is specifically difficult because of the large variation in quality of an image. Accurate identification of lung region is very important for clinical applications. The aim of this paper is to make segmentation of lung region accurately. In this paper, lung mask is calculated by taking the average of manual masks of most similar training images, and graph cut segmentation is applied with kernel energy to extract accurate boundaries. Kernel function is used to transform image data into higher dimension data in order to make piecewise constant model of graph cut formulation that becomes applicable then. Minimization of energy function contains graph cut iterations of image partitioning and iterations of updating the region parameters. Performance is evaluated by Dice coefficient. Dice coefficient is used to measure the similarity between manual and segmented mask. Experimental results of proposed methodology state the accuracy of 92.19%. It is observed that all the cases obtain the score more than 0.88 which is sufficient to detect lung region efficiently.

References

  1. 1.
    Arbabshirani, M. R., Dallal, A. H., Agarwal, C., Patel, A., & Moore, G. (2017). Accurate segmentation of lung fields on chest radiographs using deep convolutional networks. In SPIE Medical Imaging (pp. 1013305–1013305). International Society for Optics and Photonics.Google Scholar
  2. 2.
    Candemir, S., Jaeger, S., Palaniappan, K., Antani, S., & Thoma, G. (2012). Graph-cut based automatic lung boundary detection in chest radiographs. In IEEE Healthcare Technology Conference: Translational Engineering in Health & Medicine (pp. 31–34).Google Scholar
  3. 3.
    Cootes, T. F., Hill, A., Taylor, C. J., & Haslam, J. (1994). Use of active shape models for locating structures in medical images. Image and Vision Computing, 12(6), 355–365.CrossRefGoogle Scholar
  4. 4.
    Dai, W., Doyle, J., Liang, X., Zhang, H., Dong, N., Li, Y., & Xing, E. P. (2017). SCAN: Structure correcting adversarial network for chest X-rays organ segmentation. arXiv preprint arXiv:1703.08770.Google Scholar
  5. 5.
    Dawoud, A. (2010). Fusing shape information in lung segmentation in chest radiographs. Image Analysis and Recognition, 6112, 70–78.Google Scholar
  6. 6.
    Dice, L. R. (1945). Measures of the amount of ecologic association between species. Ecology, 26(3), 297–302.CrossRefGoogle Scholar
  7. 7.
    Duncan, J. S., & Ayache, N. (2000). Medical image analysis: Progress over two decades and the challenges ahead. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(1), 85–106.CrossRefGoogle Scholar
  8. 8.
    Gill, G., & Beichel, R. R. (2015). Lung segmentation in 4D CT volumes based on robust active shape model matching. Journal of Biomedical Imaging, 2015, 10.Google Scholar
  9. 9.
    Hu, S., Hoffman, E. A., & Reinhardt, J. M. (2001). Automatic lung segmentation for accurate quantitation of volumetric X-ray CT images. IEEE Transactions on Medical Imaging, 20(6), 490–498.CrossRefGoogle Scholar
  10. 10.
    Jaeger, S., Karargyris, A., Antani, S., & Thoma, G. (2012 August). Detecting tuberculosis in radiographs using combined lung masks. In 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 4978–4981). IEEE.Google Scholar
  11. 11.
    Lee, W. L., Chang, K., & Hsieh, K. S. (2016). Unsupervised segmentation of lung fields in chest radiographs using multiresolution fractal feature vector and deformable models. Medical & Biological Engineering & Computing, 54(9), 1409–1422.CrossRefGoogle Scholar
  12. 12.
    Muller, K. R., Mika, S., Ratsch, G., Tsuda, K., & Scholkopf, B. (2001). An introduction to kernel-based learning algorithms. IEEE Transactions on Neural Networks, 12(2), 181–201.CrossRefGoogle Scholar
  13. 13.
    Naing, W. Y. N., & Htike, Z. Z. (2014). Advances in automatic tuberculosis detection in chest x-ray images. Signal & Image Processing, 5(6), 41.Google Scholar
  14. 14.
    Priyanka, S. M., & Minu, R. I. (2014 February). Improving the conspicuity of lung nodules by use of” Virtual Dual-Energy” radiography. In 2014 International Conference on Information Communication and Embedded Systems (ICICES) (pp. 1–6). IEEE.Google Scholar
  15. 15.
    Saad, M. N., Muda, Z., Ashaari, N. S., & Hamid, H. A. (2014 November). Image segmentation for lung region in chest X-ray images using edge detection and morphology. In 2014 IEEE International Conference on Control System, Computing and Engineering (ICCSCE) (pp. 46–51). IEEE.Google Scholar
  16. 16.
    Salah, M. B., Mitiche, A., & Ayed, I. B. (2010 September). Image partitioning with kernel mapping and graph cuts. In 2010 17th IEEE International Conference on Image Processing (ICIP) (pp. 245–248). IEEE.Google Scholar
  17. 17.
    Salah, M. B., Mitiche, A., & Ayed, I. B. (2011). Multiregion image segmentation by parametric kernel graph cuts. IEEE Transactions on Image Processing, 20(2), 545–557.MathSciNetCrossRefGoogle Scholar
  18. 18.
    Van Ginneken, B., & Ter Haar Romeny, B. M. (2000). Automatic segmentation of lung fields in chest radiographs. Medical Physics, 27(10), 2445–2455.CrossRefGoogle Scholar
  19. 19.
    Van Ginneken, B., Katsuragawa, S., Ter Haar Romeny, B. M., Doi, K., & Viergever, M. A. (2002). Automatic detection of abnormalities in chest radiographs using local texture analysis. IEEE Transactions on Medical Imaging, 21(2), 139–149.CrossRefGoogle Scholar
  20. 20.
    Van Ginneken, B., Stegmann, M. B., & Loog, M. (2006). Segmentation of anatomical structures in chest radiographs using supervised methods: A comparative study on a public database. Medical Image Analysis, 10(1), 19–40.CrossRefGoogle Scholar
  21. 21.
    Wang, C., Guo, S., & Wu, X. (2009 June). Segmentation of lung region for chest X-ray images based on medical registration and ASM. In 3rd International Conference on Bioinformatics and Biomedical Engineering, ICBBE 2009 (pp. 1–4). IEEE.Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Ayesha Fatima
    • 1
  • Anam Tariq
    • 1
  • Mahmood Akhtar
    • 1
  • Hira Zahid
    • 1
  1. 1.Department of Computer EngineeringCollege of Electrical and Mechanical Engineering, NUSTIslamabadPakistan

Personalised recommendations