Advertisement

Combination of texture and shape features to detect pulmonary abnormalities in digital chest X-rays

  • Alexandros KarargyrisEmail author
  • Jenifer Siegelman
  • Dimitris Tzortzis
  • Stefan Jaeger
  • Sema Candemir
  • Zhiyun Xue
  • K. C. Santosh
  • Szilárd Vajda
  • Sameer Antani
  • Les Folio
  • George R. Thoma
Original Article

Abstract

Purpose

To improve detection of pulmonary and pleural abnormalities caused by pneumonia or tuberculosis (TB) in digital chest X-rays (CXRs).

Methods

A method was developed and tested by combining shape and texture features to classify CXRs into two categories: TB and non-TB cases. Based on observation that radiologist interpretation is typically comparative: between left and right lung fields, the algorithm uses shape features to describe the overall geometrical characteristics of the lung fields and texture features to represent image characteristics inside them.

Results

Our algorithm was evaluated on two different datasets containing tuberculosis and pneumonia cases.

Conclusions

Using our proposed algorithm, we were able to increase the overall performance, measured as area under the (ROC) curve (AUC) by 2.4 % over our previous work.

Keywords

Tuberculosis Screen Software Remote Telemedicine 

Notes

Compliance with ethical standards

Conflict of interest

Alexandros Karargyris, Jenifer Siegelman, Dimitris Tzortzis, Stefan Jaeger, Sema Candemir, Zhiyun Xue, KC Santosh, Szilárd Vajda, Sameer Antani, Les Folio and George R. Thoma declare that they have no conflict of interest.

References

  1. 1.
  2. 2.
    Centers for Disease Control and Prevention—Testing for TB Infection. http://www.cdc.gov/tb/topic/testing/default.htm. Viewed in Dec 2014
  3. 3.
    Van Cleeff M, Kivihya-Ndugga L, Meme H, Odhiambo J, Klatser P (2005) The role and performance of chest X-ray for the diagnosis of tuberculosis: a cost-effectiveness analysis in Nairobi, Kenya. BMC Infect Dis 5:111. doi: 10.1186/1471-2334-5-111 PubMedCentralCrossRefPubMedGoogle Scholar
  4. 4.
    Jaeger S, Karargyris A, Candemir S, Siegelman J, Folio L, Antani S, Thoma G (2013) Automatic screening for tuberculosis in chest radio-graphs: a survey. Quant Imaging Med Surg 3(2):89–99PubMedCentralPubMedGoogle Scholar
  5. 5.
    Ginneken B, Hogeweg L, Prokop M (2009) Computer-aided diagnosis in chest radiography: beyond nodules. Eur J Radiol 72(2):226–230CrossRefPubMedGoogle Scholar
  6. 6.
    Karargyris A, Antani S, Thoma G (2011) Segmenting anatomy in chest X-rays for tuberculosis screening. In: Engineering in Medicine and Biology Society, EMBC, 2011 Annual International Conference of the IEEE, pp 7779–7782, Aug 30, 2011–Sept 3, 2011. doi: 10.1109/IEMBS.2011.6091917
  7. 7.
    Candemir S, Jaeger S, Palaniappan K, Musco JP, Singh RK, Xue Z, Karargyris A, Antani S, Thoma G, McDonald CJ (2014) Lung segmentation in chest radiographs using anatomical atlases with nonrigid registration. IEEE Trans Med Imaging 33(2):577–590CrossRefPubMedGoogle Scholar
  8. 8.
    Jaeger S, Karargyris A, Candemir S, Folio L, Siegelman J, Callaghan F, Xue Z, Palaniappan K, Singh RK, Antani S, Thoma G, Wang Y-X, Pu-Xuan L, McDonald CJ (2014) Automatic tuberculosis screening using chest radiographs. IEEE Trans Med Imaging 33(2):233–245CrossRefPubMedGoogle Scholar
  9. 9.
    Santosh KC, Candemir S, Jaeger S, Karargyris A, Antani S, Folio L, Thoma G (2015) Automatically detecting rotation in chest radiographs using principal rib-orientation measure for quality control. Int J Pattern Recognit Artif Intell. doi: 10.1142/S0218001415570013
  10. 10.
    Radon Transform. http://mathworld.wolfram.com/RadonTransform.html. Viewed in Jan 2015
  11. 11.
    Bhattacharyya distance. http://en.wikipedia.org/wiki/Bhattacharyya_distance. Viewed in Jan 2015
  12. 12.
    Beard D (2009) Firefly—web-based interactive tool for the visualization and validation of image processing algorithms. M.S. thesis, Univ. Missouri, ColumbiaGoogle Scholar
  13. 13.
    Folio LR (2012) Chest imaging: an algorithmic approach to learning. Springer, BerlinCrossRefGoogle Scholar
  14. 14.
    The MathWorks, Inc., Matlab—measure properties of image regions. http://www.mathworks.com/help/images/ref/regionprops.html
  15. 15.

Copyright information

© CARS 2015

Authors and Affiliations

  • Alexandros Karargyris
    • 1
    Email author
  • Jenifer Siegelman
    • 2
    • 3
  • Dimitris Tzortzis
    • 4
  • Stefan Jaeger
    • 1
  • Sema Candemir
    • 1
  • Zhiyun Xue
    • 1
  • K. C. Santosh
    • 1
  • Szilárd Vajda
    • 1
  • Sameer Antani
    • 1
  • Les Folio
    • 5
  • George R. Thoma
    • 1
  1. 1.Communications Engineering Branch, Lister Hill National Center for Biomedical Communications, National Library of MedicineNational Institutes of HealthBethesdaUSA
  2. 2.Division of Emergency Radiology, Department of RadiologyBrigham and Women’s HospitalBostonUSA
  3. 3.Center for Evidence Based ImagingHarvard Medical SchoolBostonUSA
  4. 4.Ugeianet Diagnostic CenterGeneral Hospital of Athens KATAthensGreece
  5. 5.Radiology Department, Clinical CenterNational Institutes of HealthBethesdaUSA

Personalised recommendations