Advertisement

Computer Analysis of Chest X-Ray Images to Highlight Pathological Objects

  • Łukasz WalusiakEmail author
  • Aleksander Lamża
  • Zygmunt Wróbel
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 925)

Abstract

New methods of analysis and processing the digital images create unique possibilities and prospects in modern medicine because the results of many medical examinations are in the form of images. The paper presents research aimed at creating methods supporting the diagnostic process related to lung diseases diagnosed with X-ray images, such as tuberculosis and pneumoconiosis. Due to the specificity of X-ray images, i.e. the occurrence of distortions in the image, possible poor quality of these photographs, these studies have their solid grounds. An original method was proposed, thanks to which it is possible to obtain an X-ray image with better diagnostic properties. Such results were obtained because the resultive image was transformed using methods such as filtration, original solution for histogram alignment as well as point transformations of the image, and determination of object boundaries.

Keywords

X-ray Histogram Segmentation Object boundaries Lungs Tuberculosis 

References

  1. 1.
    Ogiela, M., Tadeusiewicz, R.: Image understanding methods in biomedical informatics and digital imaging. J. Biomed. Inf. 34(6), 377–386 (2001)CrossRefGoogle Scholar
  2. 2.
    Pruszyński, B.: Radiologia diagnostyka obrazowa Rtg, TK, USG. MR i radioizotopy. Wydawnictwo Lekarskie PZWL (2001)Google Scholar
  3. 3.
    Bilir, M., Sipahi, S., Mert, A., Yanardag, H., Ozaras, R., Aki, H., Karayel, T.: Sarcoidosis presenting with isolated right paratracheal mass on chest X-ray. Eur. J. Intern. Med. 15(3), 198–199 (2004)CrossRefGoogle Scholar
  4. 4.
    Gatey, C., Tattevin, P., Rioux, C., Ducot, B., Meyer, L., Bouvet, E.: Impact of early chest radiography and empirical antibiotherapy on delay in the diagnosis of pulmonary tuberculosis. Médecine et Maladies Infectieuses. 42(3), 110–113 (2012)CrossRefGoogle Scholar
  5. 5.
    Lu, C.T., Chen, M.Y., Shen, J.H., Wang, L.L., Hsu, C.C.: Removal of salt-and-pepper noise for X-ray bio-images using pixel-variation gain factors. Comput. Electric. Eng. 71, 862–876 (2017)CrossRefGoogle Scholar
  6. 6.
    Lee, M.S., Park, C.H., Kang, M.G.: Edge enhancement algorithm for low-dose X-ray fluoroscopic imaging. Comput. Methods Programs Biomed. 152, 45–52 (2017)CrossRefGoogle Scholar
  7. 7.
    Zhang, X., Jia, F., Luo, S., Liu, G., Hu, Q.: A marker-based watershed method for X-ray image segmentation. Comput. Methods Programs Biomed. 113(3), 894–903 (2014)CrossRefGoogle Scholar
  8. 8.
    Brown, M., Wilson, L., Doust, B., Gill, R., Sun, C.: Knowledge-based method for segmentation and analysis of lung boundaries in chest X-ray images. Comput. Med. Imaging Graph. 22(6), 463–477 (1998)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Łukasz Walusiak
    • 1
    • 2
    Email author
  • Aleksander Lamża
    • 1
  • Zygmunt Wróbel
    • 1
  1. 1.Department of Computer Biomedical SystemsUniversity of Silesia, Institute of Computer ScienceSosnowiecPoland
  2. 2.Institute of TechnologyPedagogical UniversityCracowPoland

Personalised recommendations