An automated tuberculosis screening strategy combining X-ray-based computer-aided detection and clinical information

Scientific Reports

Volumn 6, Issue , 2016, Pages

  Melendez, Jaime ^a   Sánchez, Clara I ^a   Philipsen, Rick H H M ^a   Maduskar, Pragnya ^a   Dawson, Rodney ^b   Theron, Grant ^b,c   Dheda, Keertan ^b   Van Ginneken, Bram ^a  

^a RADBOUD UNIVERSITY MEDICAL CENTER   (Netherlands)

^b UNIVERSITY OF CAPE TOWN   (South Africa)

^c UNIVERSITY OF STELLENBOSCH   (South Africa)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHM; AUTOMATION; COMPUTER ASSISTED DIAGNOSIS; DIAGNOSTIC IMAGING; EVALUATION STUDY; HUMAN; LUNG TUBERCULOSIS; MACHINE LEARNING; MASS SCREENING; PATHOLOGY; PROCEDURES; PROSPECTIVE STUDY; RECEIVER OPERATING CHARACTERISTIC; SENSITIVITY AND SPECIFICITY; SOUTH AFRICA; THORAX RADIOGRAPHY;

ALGORITHMS; AUTOMATION; HUMANS; MACHINE LEARNING; MASS SCREENING; PROSPECTIVE STUDIES; RADIOGRAPHIC IMAGE INTERPRETATION, COMPUTER-ASSISTED; RADIOGRAPHY, THORACIC; ROC CURVE; SENSITIVITY AND SPECIFICITY; SOUTH AFRICA; TUBERCULOSIS, PULMONARY;

EID: 84964906479     PISSN: None     EISSN: 20452322     Source Type: Journal    
DOI: 10.1038/srep25265     Document Type: Article

References (26)

1. World Health Organization. Global tuberculosis report 2014. (2014).
2. World Health Organization. Systematic screening for active tuberculosis: principles and recommendations. (2013).
3. van't Hoog, A. H. et al. A systematic review of the sensitivity and specifcity of symptom-and chest-radiography screening for active pulmonary tuberculosis in HIV-negative persons and persons with unknown HIV status. (2013).
4. Corbett, E. L. & MacPherson, P. Tuberculosis screening in high human immunodefciency virus prevalence settings: turning promise into reality. Int. J. Tuberc. Lung. Dis. 17, 1125-1138 (2013).
5. van't Hoog, A. H. et al. High sensitivity of chest radiograph reading by clinical ofcers in a tuberculosis prevalence survey. Int. J. Tuberc. Lung. Dis. 15, 1308-1314 (2011).
6. Maduskar, P. et al. Detection of tuberculosis with digital chest radiography: automatic reading versus interpretation by clinical ofcers. Int. J. Tuberc. Lung. Dis. 17, 1613-1620 (2013).
7. Breuninger, M. et al. Diagnostic accuracy of computer-aided detection of pulmonary tuberculosis in chest radiographs: a validation study from sub-Saharan Africa. PLoS One 9, e106381 (2014).
8. Muyoyeta, M. et al. The sensitivity and specifcity of using a computer aided diagnosis program for automatically scoring chest X-rays of presumptive TB patients compared with Xpert MTB/RIF in Lusaka Zambia. PLoS One 9, e93757 (2014).
9. World Health Organization. Tuberculosis Prevalence Surveys: A Handbook, 2nd ed. (prepublication copy). Geneva: World Health Organization (2010).
10. van't Hoog, A. H. et al. Screening strategies for tuberculosis prevalence surveys: the value of chest radiography and symptoms. PLoS One 7, e38691 (2012).
11. Teron, G. et al. Feasibility, accuracy, and clinical efect of point-of-care Xpert MTB/RIF testing for tuberculosis in primary-care settings in Africa: a multicentre, randomised, controlled trial. Lancet 383, 424-435 (2014).
12. World Health Organization. Improving the diagnosis and treatment of smear-negative pulmonary and extrapulmonary tuberculosis among adults and adolescents: recommendations for HIV-prevalent and resource-constrained settings (2007).
13. van Ginneken, B. et al. Automated scoring of chest radiographs for tuberculosis prevalence surveys: a combined approach. In: Fifh International Workshop on Pulmonary Image Analysis 9-19 (2013).
14. Wejse, C. et al. TBscore: signs and symptoms from tuberculosis patients in a low-resource setting have predictive value and may be used to assess clinical course. Scand. J. Infect. Dis. 40, 111-120 (2008).
15. Peng, H., Long, F. & Ding, C. Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans. Pattern Anal. Mach. Intell. 27, 1226-1238 (2005).
16. Jain, A. K., Duin, R. P. W. & Mao, J. Statistical pattern recognition: a review. IEEE Trans. Pattern Anal. Mach. Intell. 22, 4-37 (2000).
17. Kittler, J., Hatef, M., Duin, R. P. W. & Matas, J. On combining classifers. IEEE Trans. Pattern Anal. Mach. Intell. 20, 226-239 (1998).
18. Warren, R. M. & Dufy, S. W. Comparison of single reading with double reading of mammograms, and change in efectiveness with experience. Br. J. Radiol. 68, 958-962 (1995).
19. Wormanns, D., Ludwig, K., Beyer, F., Heindel, W. & Diederich, S. Detection of pulmonary nodules at multirow-detector CT: efectiveness of double reading to improve sensitivity at standard-dose and low-dose chest C T. Eur. Radiol. 15, 14-22 (2005).
20. Breiman, L. Random forests. Mach. Learn. 45, 5-32 (2001).
21. Geurts, P., Ernst, D. & Wehenkel, L. Extremely randomized trees. Mach. Learn. 63, 3-42 (2006).
22. Rutter, C. M. Bootstrap estimation of diagnostic accuracy with patient-clustered data. Acad. Radiol. 7, 413-419 (2000).
23. Samuelson, F., Petrick, N. & Paquerault, S. Advantages and examples of resampling for CAD evaluation. In: Proc. IEEE International Symposium on Biomedical Imaging 492-495 (2007).
24. World Health Organization. High-priority target product profiles for new tuberculosis diagnostics: report of a consensus meeting. (2014).
25. World Health Organization. Guidelines for intensifed tuberculosis case-fnding and isoniazid preventive therapy for people living with HIV in resource-constrained settings. (2011).
26. den Boon, S. et al. An evaluation of symptom and chest radiographic screening in tuberculosis prevalence surveys. Int. J. Tuberc. Lung. Dis. 10, 876-882 (2006).