An advanced segmentation using area and boundary tracing technique in extraction of lungs region

Abstract

A new method is presented for the segmentation of pulmonary parenchyma. The proposed method is based on the area calculation of different objects in the image. The main purpose of the proposed algorithm is the segment of the lungs images from the computer tomography (CT) images. The original image is binarized using the bit-plane slicing technique and among the different images the best binarized image is chosen. After binarization, the labeling is done and the area of each label is calculated from which the next level of binarized image is obtained. Then, the boundary tracing algorithm is applied to get another level of binarized image. The proposed method is able to extract lung region from the original images. The experimental results show the significance of the proposed method.

Keywords

bit-plane slicing technique / connected component labeling / area tracing / boundary tracing

References

[1] ArmatoS GIII, SensakovicW F. Automated lung segmentation for thoracic CT: Impact on computer-aided diagnosis [J]. Academic Radiology, 2004, 11: 1011-1021

[2] BrownM S, McnittgrayM F, MankovichN J, GoldinJ G, HillerJ, WilsonL S. Method for segmentation chest CT image data using an anatomical model-preliminary results [J]. IEEE Trans Medical Imaging, 1997, 16(6): 828-839

[3] HuS Y, HoffmanE A, ReinhardtJ M. Automatic lung segmentation for accurate quantization of volumetric X-ray CT images [J]. IEEE Trans Medical Imaging, 2001, 20(6): 490-498

[4] ShojaiiR, AlierezaieJ, BabynP. Automatic lung segmentation in CT images using watershed transform [C]. Proceedings of the 8th IEEE International Symposium on Computers and Communication. Italy, 2005II-1270-3

[5] KimH, NakashimeT, ItaiY, MaedaS, TanJ K, IshikawaS. Automated detection of ground glass opacity from the thoracic MDCT images by using density features [C]. International Conference on Control, Automation and Systems. Seoal, 20071274-1277

[6] KanazawaK, KawataY, NikiN, SatohH, OhmatsuH, KakinumaR, KanekoM, EguchiK, MoriyamaN. Computer-aided diagnosis for pulmonary nodules based oh helical CT images [J]. IEEE, Computerized Medical Image and Graphics, 1998, 22(2): 157-167

[7] El-bazA, FaragA A, FalkR, RoccoR L. A unified approach for detection, visualization, and identification of lung abnormalities in chest spiral CT scans [J]. International Congress Series, 2003, 1256: 998-1004

[8] JulianK. The TRACE method for segmentation of lungs from chest CT images by deterministic edge inking [D]. Department of Artificial Intelligence, University of New South Wales. Australia, 2000

[9] ChenZ-x, SunX-w, NieS-dong. An efficient method of automatic pulmonary Parenchyma segmentation in ct images [C]. Proceedings of the 29th IEEE International Conference. Lyon, France, 200723-26

[10] AmalA, FaragS Y, ElhabianS A, Elshazly, FaragA A. Quantification of nodule detection in chest CT: A clinical investigation based on the ELCAP study [C]. Proceedings of 2nd International Workshop on Pulmonary Image Processing in Conjunction with MICCAI-09. London, 2009149-160

[11] WeiQ, HuY, GelfandG, MacgregorJ H. Segmentation of lung lobes in high resolution isotropic CT images [J]. IEEE Trans Medical Imaging, 2009, 56(5): 1-11

[12] AnithaS, SridharS. Segmentation of lung lobes and nodules in CT images [J]. An International Journal (SIPIJ), 2010, 1(1): 1-12

[13] XiaoY, CaoZ G, ZhongS. New entropic thresholding approach using gray-level spatial correlation histogram [J]. Opt Eng, 2010, 49(12): 127007-1-12

[14] LooB, ParvinB, RothamS. Two and three-dimensional segmentation for measurement of particles in the analysis of microscopic digital images of biological samples [J]. Proc SPIE, 1996, 2655: 209-215

[15] SebastianR, DiazM E, AyalaG, LetinicK, Moncho-boganiJ, ToomreD. Spatio-temporal analysis of constitutive exocytosis in Epitelial cell [J]. IEEE/ACM Trans Computational Biology and Informatics, 2006, 3(1): 17-32

[16] DehmeshkiJ, AminH, ValdiviesoM, YeX. Segmentation of pulmonary nodules in thoracic CT scans: A region growing approach [J]. IEEE Trans Medical Imaging, 2008, 27(4): 467-480

[17] HardieR C, RogarsS K, WilsonT, RogersA. Performance analysis of a new computer aided detection system for identifying lung nodules on chest radiographs [J]. Med Image Anal, 2008, 12: 240-258

[18] ChenS, CaoL, LiuJ, TangX. Automatic segmentation of lung fields from radiographic images of scars patients using a new graph cuts algorithm [C]. Proc International Conference on Pattern Recognition, ICPR-06. Hong Kong, 2006271-274

[19] PradhanR, Shikhar KumarL, AgarwalR, PradhanM P, GhoseM K. Contour line tracing algorithm for digital topographic maps [J]. International Journal of Image Processing (IJIP), 2010, 4(2): 232-237