Detection of Lung Boundary in Chest X-rays using Adaptive Lung Atlas and Graph Cuts

Authors(2) :-Jeevitha Sivasamy, Dr. T. S. Subashini

In contrast to film X-rays the advent of digital X-rays has led to the use of computer assisted systems to automatically detect and diagnose diseases. Though CT and MRI are known for its diagnostic superiority Chest X-rays still remains the mainstay of chest imaging and is widely used by doctors to access various chest related ailments which includes pathologies related to lungs, esophagus, blood vessel, diaphragm, trachea, bronchia etc. The applicability of any computer aided diagnosis system (CAD) mainly depends on the accurate segmentation of the region of interest (ROI). In this work we have attempted to accurately segment the lung boundary using atlas based methods and non-rigid registration of atlases to patient specific adaptive lung models. The proposed work first applies a content based retrieval approach to select similar X-rays (lung masks) to that of the test X-ray using similarity measures and then an atlas of the test lung is obtained by SIFT-flow registration of the test X-ray with that of the retrieved masks. Finally graph-cut optimization is applied to extract the exact lung boundary.

Authors and Affiliations

Jeevitha Sivasamy
Ph.D., Scholar, Dept.of Computer and Information Science, Annamalai University, Annamalai Nagar,Tamilnadu, India.
Dr. T. S. Subashini
Associate Professor, Department of Computer Science & Engg., Annamalai University, Annamalai Nagar, Tamilnadu, India

CAD, Content Based Image Retrieval, Image Registration, Radon Transform, SIFT-Flow, Graph cut segmentation.

  1. B. Ginneken, Bart M terHaarRomeny, and Max A Viergever. Computer-aided diagnosis in chest radiography: a survey. IEEE TMI, 20(12):1228–1241, 2001.
  2. A. Dawoud,” Lung segmentation in chest radiographs by fusing shape information in iterative thresholding”, IET Comput. Vision, Vol. 5, Iss. 3, pp. 185–190,2011.
  3. Duryea J, Boone JM. A fully automated algorithm for the segmentation of lung fields on digital chest radiographic images. Medical Physics 1995;22(2):183–191.
  4. McNitt-Gray MF, Huang HK, Sayre JW. Feature selection in the pattern classification problem of digital chest radiograph segmentation. IEEE Transactions on Medical Imaging 1995;14(3):537–547
  5. S. Hu, E. Hoffman, and J. Reinhardt, “Automatic lung segmentation for accurate quantitation of volumetric x-ray ct images,” Medical Imaging, IEEE Transactions on, vol. 20, pp. 490–498, June 2001.
  6. Armato SG, Giger ML, MacMahon H. “Automated lung segmentation in digitized posteroanterior chest radiographs”. Academic Radiology 1998;5:245–255.
  7. H. Becker,W. Nettleton, P. Meyers, J. Sweeney, and C. Nice, “Digital computer determination of a medical diagnostic index directly from chest X-ray images,” IEEE Trans. Biomed. Eng., vol. 11, pp. 67–72, 1964.
  8. P.Meyers, C. Nice, H. Becker,W. Nettleton, J. Sweeney, and G.Meckstroth, “Automated computer analysis of radiographic images,” Radiology, vol. 83, pp. 1029–1034, 1964.
  9. A. Mansoor, U. Bagci, Z. Xu, B. Foster, K. N. Olivier, J. M. Elinoff, A. F. Suffredini, J. K. Udupa, and D. J. Mollura, “A generic approach to pathological lung segmentation,” IEEE transactions on medical imaging, vol. 33, no. 12, pp. 2293–2310, 2014.
  10. I. Sluimer, M. Prokop, and B. Van Ginneken, “Toward automated segmentation of the pathological lung in ct,” IEEE transactions on medical imaging, vol. 24, no. 8, pp. 1025–1038, 2005.
  11. E. Hosseini-Asl, J. M. Zurada, and A. El-Baz, “Lung segmentation based on nonnegative matrix factorization,” in 2014 IEEE International Conference on Image Processing (ICIP), pp. 877–881, IEEE, 2014.
  12. Shanhui Sun, Christian Bauer, ReinhardBeichel, “Automated 3-D Segmentation of Lungs With Lung Cancer in CT Data Using a Novel Robust Active Shape Model Approach”, IEEE transactions on medical imaging, vol. 31, no. 2, 2012.
  13. J. Long, E. Shelhamer, and T. Darrell, “Fully convolutional networks for semantic segmentation,” in Computer Vision and Pattern Recognition (CVPR 2015), 2015.
  14. Candemir S., Jaeger S. , PalaniappanK.etc. "Lung segmentation in chest radiographs using anatomical atlases with non-rigid registration", IEEE Transactions on Medical Imaging Vol. 33, No. 2, pp. 577–590, 2013
  15. Jun Lai, Ming Ye, “Active Contour Based Lung Field Segmentation”, IEEE International Conference on Intelligent Human-Machine Systems and Cybernetics, pp. 288-291, 2009
  16. Cai, Yufang & Shen, Kuan & Wang, Jue, “Application of Radon Transform in CT image matching”, 2004
  17. Nwe Nwe Soe, ”Image Matching Scheme by using Bhattacharyya Coefficient Algorithm”, International Journal of Innovative Research in Computer and Communication Engineering, Vol. 3, Issue 7, July 2015.
  18. C. Liu, J. Yuen, and A. Torralba, “SIFT Flow: Dense Correspondence across Scenes and its Applications,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 33, no. 5, pp. 978–994, 2010.
  19. Sema Candemir, Stefan Jaeger, Kannappan Palaniappan, Sameer Antani, and George Thoma, “Graph Cut Based Automatic Lung Boundary Detection in Chest Radiographs”, 1st Annual IEEE Healthcare Innovation Conference, Houston, Texas USA, pp. 7 – 9, 2012
  20. Y. Boykov and V. Kolmogorov, An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 26, No. 9, pp. 1124 – 1137, 2004

Publication Details

Published in : Volume 3 | Issue 5 | May-June 2018
Date of Publication : 2018-06-30
License:  This work is licensed under a Creative Commons Attribution 4.0 International License.
Page(s) : 179-185
Manuscript Number : CSEIT183551
Publisher : Technoscience Academy

ISSN : 2456-3307

Cite This Article :

Jeevitha Sivasamy, Dr. T. S. Subashini , "Detection of Lung Boundary in Chest X-rays using Adaptive Lung Atlas and Graph Cuts", International Journal of Scientific Research in Computer Science, Engineering and Information Technology (IJSRCSEIT), ISSN : 2456-3307, Volume 3, Issue 5, pp.179-185, May-June.2018

Follow Us

Contact Us