Abstract
Tuberculosis (TB) is a major life-threatening hazard, globally. Mortality rate increases if the disease remains undiagnosed and untreated. Detection of disease in the early stage is the most promising way to increase the lifespan of patients, especially in the regions with limited resources worldwide. We present an automatic TB detection method which uses conventional digital chest radiographs. The method consists of three main stages. We first extract the lung region from the Chest X-Ray (CXR) image using log Gabor filtering technique followed by morphological methods. A set of texture and shape features of segmented dataset is computed. The feature vector thus computed enables the support vector machine to classify the input CXR into healthy and TB-infected. ROC curve and confusion matrix of classifier show its exceptionally good performance. We attain an AUC of 0.98 and 0.96 on MC and CHN dataset, respectively, with 100% specificity.
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
World Health Org (2017) Global tuberculosis report
Daley CL, Gotway MB, Jasmer RM (2011) Radiographic manifestations of tuberculosis. In: A primer for clinicians, Second edn. Francis J. Curry National Tuberculosis Centre
Melendez J (2015) A novel multiple-instance learning-based approach to computer-aided detection of tuberculosis on chest X-rays. IEEE Trans Med Imaging 34(1)
Candemir S (2014) Lung segmentation in chest radiographs using anatomical at-lases with nonrigid registration. IEEE Trans Med Imaging 33(2)
Karargyris A, Antani S, Thoma G (2011) Segmenting anatomy in chest X-rays for tuberculosis screening. In: 33rd annual international conference of the IEEE EMBS, Boston, Massachusetts USA
van Ginneken B, Katsuragawa S, ter Haar Romeny BM, Doi K, Viergever MA (2002) Automatic detection of abnormalities in chest radiographs using local texture analysis. IEEE Trans Med Imaging 21(2)
Xu T, Cheng I, Senior Member IEEE, Mandal M (2011) Automated cavity detection of infectious pulmonary tuberculosis in chest radiographs. In: 33rd annual international conference of the IEEE EMBS, Boston, Massachusetts USA
Jaeger S, Karargyris A, Antani S, Thoma G (2012) Detecting tuberculosis in radiographs using combined lung masks. In: 34th annual international conference of the IEEE EMBS San Diego, California USA
Jaeger S (2014) Automatic tuberculosis screening using chest radiographs. IEEE Trans Med Imaging 33(2)
Mohanaiah P, Sathyanarayana P, GuruKumar L (2013) Image texture feature extraction using GLCM approach. Int J Sci Res Publ 3(5)
Srinivasan GN, Shobha G (2008) Statistical texture analysis. In: Proceedings of world academy of science, engineering and technology, vol.36
Arrospide J, Salgado L (2013) Log—gabor filters for image based vehicle verification. IEEE Trans Image Process 22(6)
Joykutty B, Samuvel B (2016) A three stage detection of tuberculosis using adaptive thresholding in chest radiographs. Int J f Eng Res Technol 5(08)
Frangi AF, Niessen WJ, Vincken KL, Viergever MA (1998) Multiscale vessel enhancement filtering. In: Medical image computing 7 computer assisted interventions, Boston USA. Lecture Notes in Computer Science, vol 1496
Nazir A, Ashraf R, Hamdani T (2018) Content based image retrieval system by using HSV color histogram, discrete wavelet transform and edge histogram descriptor. In: International conference on computing, mathematics and engineering technologies
Tamura H, Mori S, Yamawaki T (1978) Textural features corresponding to visual perception. IEEE Trans Syst Man Cybern SMC-8(6)
Wang W, Li J, Huang F, Feng H (2008) Design and implementation of Log-Gabor filter in fingerprint image enhancement. Pattern Recognit Lett 29:301–308 (Elsevier)
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
Singh, N., Hamde, S. (2019). Tuberculosis Detection Using Shape and Texture Features of Chest X-Rays. In: Saini, H., Singh, R., Kumar, G., Rather, G., Santhi, K. (eds) Innovations in Electronics and Communication Engineering. Lecture Notes in Networks and Systems, vol 65. Springer, Singapore. https://doi.org/10.1007/978-981-13-3765-9_5
Download citation
DOI: https://doi.org/10.1007/978-981-13-3765-9_5
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-3764-2
Online ISBN: 978-981-13-3765-9
eBook Packages: EngineeringEngineering (R0)