Advertisement

Tuberculosis Detection Using Shape and Texture Features of Chest X-Rays

  • Niharika SinghEmail author
  • Satish Hamde
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 65)

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.

Keywords

Features CXR image TB Support vector machine (SVM) Classifier 

References

  1. 1.
    World Health Org (2017) Global tuberculosis reportGoogle Scholar
  2. 2.
    Daley CL, Gotway MB, Jasmer RM (2011) Radiographic manifestations of tuberculosis. In: A primer for clinicians, Second edn. Francis J. Curry National Tuberculosis CentreGoogle Scholar
  3. 3.
    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)CrossRefGoogle Scholar
  4. 4.
    Candemir S (2014) Lung segmentation in chest radiographs using anatomical at-lases with nonrigid registration. IEEE Trans Med Imaging 33(2)CrossRefGoogle Scholar
  5. 5.
    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 USAGoogle Scholar
  6. 6.
    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)Google Scholar
  7. 7.
    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 USAGoogle Scholar
  8. 8.
    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 USAGoogle Scholar
  9. 9.
    Jaeger S (2014) Automatic tuberculosis screening using chest radiographs. IEEE Trans Med Imaging 33(2)CrossRefGoogle Scholar
  10. 10.
    Mohanaiah P, Sathyanarayana P, GuruKumar L (2013) Image texture feature extraction using GLCM approach. Int J Sci Res Publ 3(5)Google Scholar
  11. 11.
    Srinivasan GN, Shobha G (2008) Statistical texture analysis. In: Proceedings of world academy of science, engineering and technology, vol.36Google Scholar
  12. 12.
    Arrospide J, Salgado L (2013) Log—gabor filters for image based vehicle verification. IEEE Trans Image Process 22(6)MathSciNetCrossRefGoogle Scholar
  13. 13.
    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)Google Scholar
  14. 14.
    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 1496CrossRefGoogle Scholar
  15. 15.
    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 technologiesGoogle Scholar
  16. 16.
    Tamura H, Mori S, Yamawaki T (1978) Textural features corresponding to visual perception. IEEE Trans Syst Man Cybern SMC-8(6)Google Scholar
  17. 17.
    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)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Department of Instrumentation EngineeringSGGSIE&TNandedIndia

Personalised recommendations