Accuracy of an automated system for tuberculosis detection on chest radiographs in high-risk screening

SETTING: Tuberculosis (TB) screening programmes can be optimised by reducing the number of chest radiographs (CXRs) requiring interpretation by human experts. OBJECTIVE: To evaluate the performance of computerised detection software in triaging CXRs in a high-throughput digital mobile TB screening programme. DESIGN: A retrospective evaluation of the software was performed on a database of 38 961 postero-anterior CXRs from unique individuals seen between 2005 and 2010, 87 of whom were diagnosed with TB. The software generated a TB likelihood score for each CXR. This score was compared with a reference standard for notified active pulmonary TB using receiver operating characteristic (ROC) curve and localisation ROC (LROC) curve analyses. RESULTS: On ROC curve analysis, software specificity was 55.71% (95%CI 55.21–56.20) and negative predictive value was 99.98% (95%CI 99.95–99.99), at a sensitivity of 95%. The area under the ROC curve was 0.90 (95%CI 0.86–0.93). Results of the LROC curve analysis were similar. CONCLUSION: The software could identify more than half of the normal images in a TB screening setting while maintaining high sensitivity, and may therefore be used for triage.

[1]  Ying Wah Teh,et al.  RAIRS2 a new expert system for diagnosing tuberculosis with real-world tournament selection mechanism inside artificial immune recognition system , 2015, Medical & Biological Engineering & Computing.

[2]  A. Story,et al.  Diagnostic accuracy of digital chest radiography for pulmonary tuberculosis in a UK urban population , 2010, European Respiratory Journal.

[3]  R. Hayes,et al.  HIV infection does not affect active case finding of tuberculosis in South African gold miners. , 2009, American journal of respiratory and critical care medicine.

[4]  B. van Ginneken,et al.  Automated chest-radiography as a triage for Xpert testing in resource-constrained settings: a prospective study of diagnostic accuracy and costs , 2015, Scientific Reports.

[5]  Xavier Robin,et al.  pROC: an open-source package for R and S+ to analyze and compare ROC curves , 2011, BMC Bioinformatics.

[6]  P. Sen.  Diagnosis of pulmonary tuberculosis. , 1955, Journal of the Indian Medical Association.

[7]  A. Story,et al.  Active case finding for pulmonary tuberculosis using mobile digital chest radiography: an observational study. , 2012, The international journal of tuberculosis and lung disease : the official journal of the International Union against Tuberculosis and Lung Disease.

[8]  Bram van Ginneken,et al.  Localized Energy-Based Normalization of Medical Images: Application to Chest Radiography , 2015, IEEE Transactions on Medical Imaging.

[9]  B. Marston,et al.  Screening Strategies for Tuberculosis Prevalence Surveys: The Value of Chest Radiography and Symptoms , 2012, PloS one.

[10]  E. Bateman,et al.  Chest radiograph reading and recording system: evaluation for tuberculosis screening in patients with advanced HIV. , 2010, The international journal of tuberculosis and lung disease : the official journal of the International Union against Tuberculosis and Lung Disease.

[11]  T. Frieden,et al.  Toman's Tuberculosis: Case Detection, Treatment and Monitoring: Questions and Answers , 2004 .

[12]  B van Ginneken,et al.  Automatic versus human reading of chest X-rays in the Zambia National Tuberculosis Prevalence Survey. , 2017, The international journal of tuberculosis and lung disease : the official journal of the International Union against Tuberculosis and Lung Disease.

[13]  J. Richardus,et al.  Impact of mobile radiographic screening on tuberculosis among drug users and homeless persons. , 2007, American journal of respiratory and critical care medicine.

[14]  Bram van Ginneken,et al.  Static posterior probability fusion for signal detection: applications in the detection of interstitial diseases in chest radiographs , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[15]  P. Maduskar,et al.  Automated analysis of tuberculosis in chest radiographs: development and validation , 2015 .

[16]  Shahaboddin Shamshirband,et al.  Tuberculosis Disease Diagnosis Using Artificial Immune Recognition System , 2014, International journal of medical sciences.

[17]  M. Jit,et al.  Dedicated outreach service for hard to reach patients with tuberculosis in London: observational study and economic evaluation , 2011, BMJ : British Medical Journal.

[18]  Z. Qin,et al.  An evaluation of automated chest radiography reading software for tuberculosis screening among public- and private-sector patients , 2017, European Respiratory Journal.

[19]  E. Bateman,et al.  Development of a Simple Reliable Radiographic Scoring System to Aid the Diagnosis of Pulmonary Tuberculosis , 2013, PloS one.

[20]  E. Bateman,et al.  Development and evaluation of a new chest radiograph reading and recording system for epidemiological surveys of tuberculosis and lung disease. , 2005, The international journal of tuberculosis and lung disease : the official journal of the International Union against Tuberculosis and Lung Disease.

[21]  M. Borgdorff,et al.  High sensitivity of chest radiograph reading by clinical officers in a tuberculosis prevalence survey. , 2011, The international journal of tuberculosis and lung disease : the official journal of the International Union against Tuberculosis and Lung Disease.

[22]  D Zachary,et al.  Changes in tuberculosis notifications and treatment delay in Zambia when introducing a digital X-ray service. , 2012, Public health action.

[23]  A. Story,et al.  Tuberculosis in London: the importance of homelessness, problem drug use and prison , 2007, Thorax.

[24]  N. Dendukuri,et al.  Xpert® MTB/RIF assay for pulmonary tuberculosis and rifampicin resistance in adults , 2014, The Cochrane database of systematic reviews.

[25]  Bram van Ginneken,et al.  Segmentation of anatomical structures in chest radiographs using supervised methods: a comparative study on a public database , 2006, Medical Image Anal..

[26]  Results of the international study on x-ray classification. , 1968, Bulletin of the International Union against Tuberculosis.