Format

Send to

Choose Destination
Int J Tuberc Lung Dis. 2018 May 1;22(5):567-571. doi: 10.5588/ijtld.17.0492.

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

Author information

1
Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, Thirona, Nijmegen, The Netherlands.
2
Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, The Netherlands.
3
Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, The Netherlands; Thirona, Nijmegen, The Netherlands.
4
Department of Infectious Disease Informatics, Institute of Health Informatics, University College London, London, UK.
5
Department of Infectious Disease Informatics, Institute of Health Informatics, University College London, London, UK; Institute of Epidemiology and Health Care, University College London, UK.
6
Institute for Global Health, University College London, UK.

Abstract

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.

Supplemental Content

Full text links

Icon for Ingenta plc Icon for PubMed Central
Loading ...
Support Center