Abstract
This chapter provides a complete model-based approach for analysis of lung nodules visibly observed in clinical low dose CT (LDCT) scans of the human chest. The purpose is to highlight elements of computer-assisted diagnosis (CAD) software that can be validated using multiple radiologists using modern computing and information technology. The front-end components of the proposed approach are the following: lung nodule modeling, nodule detection, nodule segmentation, and CAD system design and evaluation. The implicit steps involved in developing these components, include filtering of the LDCT scans to reduce noise artifacts and other uncertainties associated with the imaging protocol; segmentation of the lung tissue from the rest of organs appearing in the LDCT of the chest; and creating an ensemble of nodules by human experts. As nodules take various shapes, sizes and pathologies, we limit our treatment to small size nodule \(\le \)1 cm in diameter. Our ultimate goal is to create a robust system for early detection and classification, as well as tracking, of small-size nodules before they turn into cancerous. The entire development in the chapter is model-based and data-driven, allowing design, calibration and testing for the CAD system, based on archived data as well as data accrued from new patients. We provide standard development using two clinical datasets that are already available from the ELCAP and LIDC studies.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Kostis WJ et al (2004) Small pulmonary nodules: reproducibility of three-dimensional volumetric measurement and estimation of time to follow-up. Radiology 231:446–52
Farag AA (2009) Lung nodule modeling and detection for computerized image analysis of low dose CT imaging of the chest. Master of Engineering, University of Louisville
ELCAP public lung image database. www.via.cornell.edu/databases/lungdb.html
Armato G, McLennan G, McNitt-Gray MF, Meyer CR, Yankelevitz D, Aberle DR, Henschke CI, Hoffman EA, Kazerooni EA, MacMahon H, Reeves AP, Croft BY, Clarke LP (2004) Lung image database consortium: developing a resource for the medical imaging research community. Radiology 232(3):739–748
Kendall DG (1984) Shape manifolds, procrustean metrics, and complex projective spaces. Bull Lond Math Soc 16(2):81–121
Julesz B et al (1973) Inability of humans to discriminate between visual textures that agree in second-order statistics-revisited. Perception 2:391–405
Dryden IL, Mardia KV (1998) Statistical shape analysis. John Wiley & Sons, New York
Cootes TF, Taylor CJ (2004) Anatomical Statistical Models and their role in feature extraction. Br J Radiol 77:S133–S139
Mathews I, Baker S (2004) Active appearance models revisited. Int J Comput Vision 60(2):135–164
Farag AA, Graham J, Farag AA, Elshazly S, Falk R (2010) Parametric and non-parametric nodule models: design and Evaluation. Workshop on pulmonary image processing in conjunction with MICCAI-10, Beijing, pp 151–162
Farag AA, Abdelmunim H, Graham J, Farag AA, Carter C, Elshazly S, El-Mogy S, El-Mogy MS, Falk R (2012) An AAM-based approach for lung nodule detection from low dose CT (LDCT) scans, International symposium on biomedical imaging (ISBI 12), Barcelona, Spain, pp 1040–1043
Farag AA (2013) A variational approach for small-size lung Nodule segmentation. International symposium on biomedical imaging (ISBI 13), San Francisco, CA, pp 81–84
Zhao B, Yankelevitz D, Reeves A, Henschke C (1999) Two-dimensional multi-criterion segmentation of pulmonary nodules on helical CT images. Med Phys 26(6):889–95
Ko JP, Rusinek H, Jacobs EL, Babb JS, Betke M, McGuinness G, Naidich DP (2003) Small pulmonary nodules: volume measurement at chest CT-phantom study. Radiology 228(3):864–870
Kuhnigk JM, Dicken V, Bornemann L, Bakai A, Wormanns D, Krass S, Peitgen HO (2006) Morphological segmentation and partial volume analysis for volumetry of solid pulmonary lesions in thoracic CT scans. IEEE Trans Med Imaging 25(4):417434
Kubota T, Jerebko AK, Dewan M, Salganicoff M, Krishnan A (2011) Segmentation of pulmonary nodules of various densities with morphological approaches and convexity models. Med Image Anal 15(1):133–154
Dijia Wu, Le Lu, Jinbo Bi, Shinagawa Y, Boyer KL, Krishnan A, Salganicoff1 M (2010) Stratified learning of local anatomical context for lung nodules in ct images. The twenty-third IEEE conference on computer vision and pattern recognition, CVPR 2010, San Francisco, California, USA
Armato SG 3rd, Giger ML, Moran CJ, Blackburn JT, Doi K (1999) MacMahon H (1999) Computerized detection of pulmonary nodules on CT scans. J Radio Graph 19:1303–1311
Diciotti Stefano, Lombardo Simone, Falchini Massimo, Picozzi Giulia, Mascalchi Mario (2011) Automated segmentation refinement of small lung nodules in CT scans by local shape analysis. IEEE Trans Biomed Eng 58(12):3418–3428
Diciotti Stefano, Picozzi Giulia, Falchini Massimo, Mascalchi Mario, Villari Natale, Valli Guido (2008) 3-D segmentation algorithm of small lung nodules in spiral CT images. IEEE Trans Inf Technol Biomed 12(1):7–19
Munim HAE, Farag AA (2007) Curve/surface representation and evolution using vector level sets with application to the shape-based segmentation problem. IEEE Trans Pattern Anal Mach Intell 29(6):945–958
Farag A, Graham J, Farag A (2010) Robust segmentation of lung tissue in chest CT scanning. Proceedings of the 2010 IEEE international conference on image processing (ICIP), pp 2249–2252
Farag AA (2012) Modeling small objects under uncertainties: novel algorithms and applications. CVIP Lab, Ph.D. Dissertation, University of Louisville
Ojala T, Pietikainen M, Maenpaa T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mac Intell 24:971–987
Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110
Mikolajczyk K, Schmid C (2005) A performance evaluation of local descriptors. IEEE Trans Pattern Anal Mac Intell 27(10):1615–1630
Farag AA, Elhabian S, Graham J, Farag AA, Falk R (2010) Toward precise pulmonary nodule descriptors for nodule type classification. Proceedings of the 13th international conference on medical image computing and computer assisted intervention (MICCAI), pp 626–633
Koenderink JJ (1984) The structure of images. Biol Cybern 50:363–396
Lindeberg T (1993) Detecting salient blob-like image structures and their scales with a scale-space primal sketch: a method for focus-of-attention. Int J Comput Vis 11(3):283–318
Duda RO, Hart PE, Stork DG (2001) Pattern classification, 2nd edn. Wiley, New York
Farag Aly (2013) Biomedical image analysis: statistical and variational approaches. Cambridge University Press, Cambridge
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Farag, A.A., Farag, M., Graham, J., Elshazly, S., Mogy, M.a., Farag, A. (2014). Modeling of Lung Nodules from LDCT of the Human Chest: Algorithms and Evaluation for CAD Systems. In: Li, S., Tavares, J. (eds) Shape Analysis in Medical Image Analysis. Lecture Notes in Computational Vision and Biomechanics, vol 14. Springer, Cham. https://doi.org/10.1007/978-3-319-03813-1_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-03813-1_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-03812-4
Online ISBN: 978-3-319-03813-1
eBook Packages: EngineeringEngineering (R0)