Abstract
Tuberculosis (TB) and lung cancer are major problems of the lung, and their occurrence as co-morbidities is dealt in many studies. World Health Organization (WHO) states that over 95% of deaths occur due to TB in low and middle income countries. This work presents a retrospective cohort study to derive the mathematical model characterizing the tissues like fibrosis, TB, and carcinoma. The cohort includes 113 normal cases, 103 fibrosis cases, 185 carcinoma cases, and 39 suspicious of tuberculosis cases. Multiple Regression Analysis (MRA) is performed on Gray-Level Co-occurrence Matrix (GLCM)- and Gray-Level Run Length Matrix (GLRLM)-based features extracted from CT images for the characterization of lung tissues. MRA of these 18 numbers of GLCM and 44 numbers of GLRLM-based features gives R2 value of 0.8827 and 0.9456 with mean square error (MSE) of 0.01979 and 0.009852, respectively.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
World Health Organization: WHO Report 2011 Global Tuberculosis Control, pp. 9–27. WHO Press, Geneva, Switzerland (2011)
Hopewell, P.C., Pai, M., Maher, D., Uplekar, M., Raviglione, M.C.: International standards for tuberculosis care. Lancet Infect. Dis. 6(11), 710–725 (2006)
World Health Organization1: Causes of Death 2008 Summary Tables. Global Health Observatory Data Repository (2011)
Levin, D.C., Rao, V.M., Parker, L.: The recent downturn in utilization of CT: the start of a new trend? Am. Coll. Radiol. 9, 795–798 (2012)
Chen, C., Lee, G.: Image segmentation using multiresolution wavelet analysis and expectation maximum (EM) algorithm for mammography. Int. J. Imaging Syst. Technol. 8(5), 491–504 (1997)
Wang, T., Karayaiannis, N.: Detection of microcalcification in digital mammograms using wavelets. IEEE Trans. Med. Imaging 17(4), 498–509 (1998)
Majid, A.S., de Paredes, E.S., Doherty, R.D., Sharma, N., Salvador, X.: Missed breast carcinoma: pitfalls and pearls. Radiogr. 23, 881–895 (2003)
Christiyanni, I., et al.: Fast detection of masses in computer aided mammography. IEEE Signal computer aided mammography. IEEE Signal
Devan, L., Santosham, R., Hariharan, R.: Automated texture based characterization of fibrosis and carcinoma using low-dose lung CT images. Int. J. Imaging Syst. Technol. 24(1), 39–44 (2014)
Chan, H.P., et al.: Computer-aided classification of mammographic masses and normal tissue: linear discriminant analysis in texture feature space. Phys. Med. Biol. 40, 857–876
Haralick, R.M., Shanmugam, K., Dinstein, I.: Textural features for image classification. IEEE Trans. Syst. Man. Cybernetics SMC-3, 610–621 (1973)
Tang, X., et al.: Texture information in run-length matrices. IEEE Trans. Image Process. 7(11), 1602–1609 (1998)
Chicklore, S., Goh, V., Siddique, M., Roy, A., Marsden, P.K., Cook, G.J.R.: Quantifying tumour heterogeneity in 18F-FDG PET/CT imaging by texture analysis. Eur. J. Nucl. Med. Mol. Imaging 40, 133–140 (2013)
Hajian-Tilaki, K.: Sample size estimation in diagnostic test studies of biomedical iinformatics. J. Biomed. Inform. 48, 193–204 (2014)
Acknowledgements
This research work was supported by Santhosham Chest Hospital, Chennai. We wish to thank Dr. Roy Santhosham and the technician of this hospital for giving us their support for the study.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Lakshmi, D., Niruban, R. (2019). Mathematical Model for Characterization of Lung Tissues Using Multiple Regression Analysis. In: Nayak, J., Abraham, A., Krishna, B., Chandra Sekhar, G., Das, A. (eds) Soft Computing in Data Analytics . Advances in Intelligent Systems and Computing, vol 758. Springer, Singapore. https://doi.org/10.1007/978-981-13-0514-6_12
Download citation
DOI: https://doi.org/10.1007/978-981-13-0514-6_12
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-0513-9
Online ISBN: 978-981-13-0514-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)