Edge map analysis in chest X-rays for automatic pulmonary abnormality screening

  • K. C. SantoshEmail author
  • Szilárd Vajda
  • Sameer Antani
  • George R. Thoma
Original Article



Our particular motivator is the need for screening HIV+ populations in resource-constrained regions for the evidence of tuberculosis, using posteroanterior chest radiographs (CXRs).


The proposed method is motivated by the observation that abnormal CXRs tend to exhibit corrupted and/or deformed thoracic edge maps. We study histograms of thoracic edges for all possible orientations of gradients in the range \([0, 2\pi )\) at different numbers of bins and different pyramid levels, using five different regions-of-interest selection.


We have used two CXR benchmark collections made available by the U.S. National Library of Medicine and have achieved a maximum abnormality detection accuracy (ACC) of 86.36 % and area under the ROC curve (AUC) of 0.93 at 1 s per image, on average.


We have presented an automatic method for screening pulmonary abnormalities using thoracic edge map in CXR images. The proposed method outperforms previously reported state-of-the-art results.


Automation Thoracic edge map Pulmonary abnormalities Screening Tuberculosis Chest X-rays 



This research was supported by the Intramural Research Program of the National Institutes of Health (NIH), National Library of Medicine (NLM) and Lister Hill National Center for Biomedical Communications (LHNCBC).

Compliance with ethical standards

Conflict of interest

K.C. Santosh, Szilárd Vajda, Sameer Antani and George R Thoma declare that they have no conflicts of interest.

Ethical standards

This article does not contain any studies with human participants or animals performed by any of the authors.


  1. 1.
    World Health Organization (WHO), global tuberculosis report (2014)Google Scholar
  2. 2.
    Kumar V, Abbas A, Fausto N, Mitchell R (2007) Robbins BasicPathology. ser. Robbins Pathology. Elsevier Health SciencesGoogle Scholar
  3. 3.
    Panteix G, Gutierrez MC, Boschiroli ML, Rouviere M, Plaidy A, Pressac D, Porcheret H, Chyderiotis G, Ponsada M, Oortegem KV, Salloum S, Cabuzel S, Banuls AL, de Perre PV, Godreuil S (2010) Pulmonary tuberculosis due to Mycobacterium microti: a study of six recent cases in France. J Med Microbiol 59:984–989CrossRefPubMedGoogle Scholar
  4. 4.
    (2006) Diagnostics for tuberculosis : global demand and market potential. World Health Organization on behalf of the Special Programme for Research and Training in Tropical Diseases Geneva, p 36Google Scholar
  5. 5.
    (2011) Tuberculosis: clinical diagnosis and management of tuberculosis, and measures for its prevention and control. NICE Clinical Guideline 117: TuberculosisGoogle Scholar
  6. 6.
    Boehme CC, Nabeta P (2010) Rapid molecular detection of tuberculosis and rifampin resistance. N Engl J Med 363(11):1005–1015CrossRefPubMedPubMedCentralGoogle Scholar
  7. 7.
    Seoudi N, Mitchell S, Brown T, Dashti F, Amin A, Drobniewski F (2012) Rapid molecular detection of tuberculosis and rifampicin drug resistance: retrospective analysis of a national uk molecular service over the last decade. Thorax 67:361–367CrossRefPubMedGoogle Scholar
  8. 8.
    (2006) Improving the diagnosis and treatment of smear-negative pulmonary and extrapulmonary tuberculosis among adults and adolescents: recommendations for HIV-prevalent and resource-constrained settings. World Health Organization GenevaGoogle Scholar
  9. 9.
    Schaefer-Prokop C, Neitzel U, Venema H, Uffmann M, Prokop M (2008) Digital chest radiography: an update on modern technology, dose containment and control of image quality. Eur Radiol 18(9):1818–1830CrossRefPubMedPubMedCentralGoogle Scholar
  10. 10.
    van Ginneken B, Ter Haar Romeny B, Viergever M (2001) Computer-aided diagnosis in chest radiography: a survey. IEEE Trans Med Imaging 20(12):1228–1241CrossRefPubMedGoogle Scholar
  11. 11.
    van Ginneken B, Hogeweg L, Prokop M (2009) Computer-aided diagnosis in chest radiography: beyond nodules. Eur J Radiol 72(2):226–230CrossRefPubMedGoogle Scholar
  12. 12.
    Lodwick GS (1966) Computer-aided diagnosis in radiology: a research plan. Invest Radiol 1(1):72CrossRefPubMedGoogle Scholar
  13. 13.
    Sakai S, Soeda H, Takahashi N, Okafuji T, Yoshitake T, Yabuuchi H, Yoshino I, Yamamoto K, Honda H, Doi K (2006) Computer-aided nodule detection on digital chest radiography: validation test on consecutive T1 cases of resectable lung cancer. J Digit Imag 19(4):376–382CrossRefGoogle Scholar
  14. 14.
    Freedman MT, Lo S-CB, Seibel JC, Bromley CM (2011) Lung nodules: improved detection with software that suppresses the rib and clavicle on chest radiographs. Radiology 260(1):265–273Google Scholar
  15. 15.
    Shen R, Cheng I, Basu A (2010) A hybrid knowledge-guided detection technique for screening of infectious pulmonary tuberculosis from chest radiographs. IEEE Trans Biomed Eng 57(11):2646–2656CrossRefGoogle Scholar
  16. 16.
    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):139–149CrossRefPubMedGoogle Scholar
  17. 17.
    Hogeweg L, Mol C, de Jong PA, Dawson R, Ayles H, van Ginneken B (2010) Fusion of local and global detection systems to detect tuberculosis in chest radiographs. In: 13th international conference on medical image computing and computer-assisted intervention, pp 650–657Google Scholar
  18. 18.
    Jaeger S, Karargyris A, Candemir S, Folio L, Siegelman J, Callaghan FM, Xue Z, Palaniappan K, Singh RK, Antani S, Thoma GR, Wang Y, Lu P, McDonald CJ (2014) Automatic tuberculosis screening using chest radiographs. IEEE Trans Med Imaging 33(2):233–245CrossRefPubMedGoogle Scholar
  19. 19.
    Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: IEEE conference on computer visual and pattern recognition, pp 886–893Google Scholar
  20. 20.
    Chaisson RE, Martinson NA (2008) Tuberculosis in Africa combating an HIV-driven crisis. N Engl J Med 358(11):1089–1092CrossRefPubMedGoogle Scholar
  21. 21.
    Santosh KC, Vajda S, Antani S, Thoma G (2015) Automatic pulmonaryabnormality screening using thoracic edge map. IEEE, Sao Carlos, BrazilGoogle Scholar
  22. 22.
    Candemir S, Jaeger S, Musco J, Xue Z, Karargyris A, Antani S, Thoma G, Palaniappan K (2014) Lung segmentation in chest radiograps using anatomical atlases with non-rigid registration. IEEE Trans Med Imaging 33(2):577–590CrossRefPubMedGoogle Scholar
  23. 23.
    Jones R, Soille P (1996) Periodic lines: Definition, cascades, and application to granulometrie. Pattern Recognit Lett 17(8):1057–1063CrossRefGoogle Scholar
  24. 24.
    Canny J (1986) A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 8(6):679–698CrossRefPubMedGoogle Scholar
  25. 25.
    Opelt A, Pinz A, Zisserman A (2006) Incremental learning of object detectors using a visual shape alphabet. In: IEEE conference on computer visual and pattern recognition, vol 1, pp 3–10Google Scholar
  26. 26.
    Bosch A, Zisserman A, Munoz X (2007) Representing shape with a spatial pyramid kernel. In: ACM international conference on image and video retrieval, pp 401–408Google Scholar
  27. 27.
    Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: IEEE conference on computer visual and pattern recognition, pp 2169–2178Google Scholar
  28. 28.
    Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press Inc, New YorkGoogle Scholar
  29. 29.
    Fawcett T (2006) An introduction to ROC analysis. Pattern Recognit Lett 27(8):861–874CrossRefGoogle Scholar
  30. 30.
    Karargyris A, Siegelman J, Tzortzis D, Jaeger S, Candemir S, Xue Z, Santosh KC, Vajda S, Antani SK, Folio L, Thoma GR (2016) Combination of texture and shape features to detect pulmonary abnormalities in digital chest X-rays. Int J Comput Assist Radiol Surg 11(1):99–106Google Scholar
  31. 31.
    Chauhan A, Chauhan D, Rout C (2014) Role of Gist and PHOG features in computer-aided diagnosis of tuberculosis without segmentation. PLoS ONE 9(11):e112980CrossRefPubMedPubMedCentralGoogle Scholar
  32. 32.
    Santosh KC, Candemir S, Jaeger S, Karargyris A, Antani S, Thoma GR, Folio L (2015) Automatically detecting rotation in chest radiographs using principal rib-orientation measure for quality control. Intern J Pattern Recognit Artif Intell 29(2):1557001CrossRefGoogle Scholar

Copyright information

© CARS 2016

Authors and Affiliations

  • K. C. Santosh
    • 1
    • 3
    Email author
  • Szilárd Vajda
    • 2
  • Sameer Antani
    • 3
  • George R. Thoma
    • 3
  1. 1.Department of Computer ScienceThe University of South DakotaVermillionUSA
  2. 2.Department of Computer ScienceCentral Washington UniversityEllensburgUSA
  3. 3.US National Library of MedicineNational Institutes of HealthBethesdaUSA

Personalised recommendations