Automatic Segmentation of Lung Areas in Magnetic Resonance Images

Segmenting the lungs in medical images is a challenging and important task for many applications. In particular, automatic segmentation of lung cavities from multiple magnetic resonance (MR) images is very useful for oncological applications such as radiotherapy treatment planning. However, distinguishing of the lung areas is not trivial due to largely changing lung shapes, low contrast and poorly defined boundaries. In this paper, we address lung segmentation problem from pulmonary magnetic resonance images and propose an automated method based on a robust regionaided geometric snake with a modified diffused region force into the standard geometric model definition. The extra region force gives the snake a global complementary view of the lung boundary information within the image which along with the local gradient flow, helps detect fuzzy boundaries. The proposed method has been successful in segmenting the lungs in every slice of 30 magnetic resonance images with 80 consecutive slices in each image. We present results by comparing our automatic method to manually segmented lung cavities provided by an expert radiologist and with those of previous works, showing encouraging results and high robustness of our approach.

Authors:

• Alireza Osareh
• Bita Shadgar

Keywords:

• Active contours
• breast cancer
• fuzzy c-means segmentation
• treatment planning.

References:

[1] Early Breast Cancer Trialists' Collaborative Group. Radiotherapy for
early breast cancer. Cochrane Database of Systematic Reviews 2002,
Issue 2.
[2] P. Evans, E. Donovan, M. Partridge, "The delivery of intensity
modulated radiotherapy to the breast using multiple static fields,"
Radiotherapy Oncology, vol. 57, pp. 79-89, 2000.
[3] B. Cho, C. Hurkmans, E. Damen, L. Zijp, "Intensity modulated versus
non-intensity modulated radiotherapy in the treatment of left breast and
upper internal mammary lympth node chauin: a comparative planning
study, " Radiotherapy Oncology, vol. 62, pp. 127-136, 2002.
[4] R. Kinhikar, S. Deshpande, U. Mahantshetty, R. Sarin, "HDR
brachytherapy combined with 3D conformal versus IMRT in left-sided
breast cancer patients including internal mammary chain: comparative
analysis of dosimetric and technical parameters," Journal of Applied
Clinical Medical Physics, vol. 6, pp. 1-12, 2005.
[5] S. Hu, E. Hoffman, J. Reinhardt, "Automatic lung segmentation for
accurate quantitation of volumetric X-ray CT images," IEEE
Transactions on Medical Imaging, vol. 20, pp. 490-498, 2001.
[6] Y. Itai, H. Kim and S. Ishikawa, "A segmentation method of lung areas
by using snakes and automatic detection of abnormal shadow on the
areas," Int. J. Inov. Comput. Info. Control, vol. 3, pp. 277-284, 2007.
[7] M. Silveria and J. Marques, "Automatic segmentation of the lungs using
multiple active contours and outlier model," Proc. International
Conference of the IEEE Engineering in Medicine and Biology, 3122-
3125, 2006.
[8] M. Brown, M. McNitt-Gray and N. Mankovich, "Method for segmenting
chest CT image data using an anatomical model: preliminary results,"
IEEE Trans. Medical Imaging, vol. 16, pp. 828-839, 1997.
[9] P. A. Yushkevich, J. Piven, H. C. Hazlett, "User-guided 3D active
contour segmentation of anatomical structures: significantly improved
efficiency and reliability," Neuroimage, vol. 31, pp.1116-1128, 2006.
[10] I. Middleton and R. Damper, "Segmentation of magnetic resonance
images using a combination of neural networks and active contour
models," Medical Engineering and Physics, vol. 26, pp. 71-86, 2004.
[11] N. Ray, S. Acton, T. Altes, E. Lange, J. Brookeman, "Merging
parametric active contours within homogeneous image regions for MRIBased
lung segmentation," IEEE Trans. Medical Imaging, vol. 22, pp.
189-199, 2003.
[12] V. Caselles, F. Catte, T. Coll, F. Dibos, "A geometric model for active
contours," Numerische Mathematik, vol. 66, pp. 1-31, 1993.
[13] M. Kass, A. Witkin, D. Terzopoulos, "Snakes: active contour models,"
International Journal of Computer Vision, vol. 1, pp. 321-331, 1988.
[14] X. Xie, M. Mirmehdi, "RAGS: Region-aided geometric snake", IEEE
Trans. Image Processing, vol. 13, pp. 640-652, 2004.
[15] D. Comaniciu, P. Meer, "Mean shift: A robust approach toward feature
space analysis," IEEE Trans. Pattern Analysis and Machine Intelligence,
vol. 24, pp. 603-619, 2002.
[16] S. Webb, The Physics of Medical Imaging, Adam Hilger, Bristol, UK,
1988.
[17] K. Siddiqi, Y. Lauziere, A. Tannenbaum, and S. Zucker, "Area and
length minimizing flows for shape segmentation," IEEE Trans. Image
Processing, vol. 7, pp. 433-443, 1998.
[18] C. Xu, J. Prince, "Generalized gradient vector flow external forces for
active contours," Signal Processing, vol. 71, pp. 131-139, 1998.
[19] D. Pham, J. Prince, "Adaptive fuzzy segmentation of magnetic
resonance images," IEEE Trans. Medical Imaging, vol. 18, pp. 737-752,
1999.
[20] G. Sapiro, "Color snakes," Computer Vision and Image Understanding,
vol. 68, pp. 247-253, 1997.
[21] J. Bezdek, J. Keller, R. Krisnapuram, N. Pal, Fuzzy Models and
Algorithms for Pattern Recognition and Image Processing, Kluwer
Academic, Boston, 1999.
[22] D. Pham, J. Prince, A. Dagher, C. Xu, "An automated technique for
statistical characterization of brain tissues in magnetic resonance
imaging," International Journal of Pattern Recognition, Artificial
Intelligence, vol. 11, pp. 1189-1211, 1997.
[23] L. Hall, A. Bensaid, L. Clarke, P. Velthuizen, M. Silbiger, J. Bezdek, "A
comparison of neural networks and fuzzy clustering techniques in
segmenting magnetic resonance images of the brain," IEEE Trans.
Neural Networks, vol. 3, pp. 672-682, 1992.
[24] J. Bezdek, "A convergence theorem for the fuzzy ISODATA clustering
algorithms," IEEE Trans. Pattern Analysis and Machine Intelligence,
vol. 2, pp. 1-8, 1980.
[25] M. Sonka, V. Hlavac, R. Boyle, Image Processing, Analysis, and
Machine Vision, PWS Publishing, 1999.
[26] W. Pratt, Digital Image Processing, Wiley, New York, 1991.
[27] V. Rijsbergen, Information retrieval, Butterworth, London, 1979.