Diagnostic accuracy of computer-aided detection of pulmonary tuberculosis in chest radiographs: a validation study from sub-Saharan Africa

PLoS One. 2014 Sep 5;9(9):e106381. doi: 10.1371/journal.pone.0106381. eCollection 2014.

Abstract

Background: Chest radiography to diagnose and screen for pulmonary tuberculosis has limitations, especially due to inter-reader variability. Automating the interpretation has the potential to overcome this drawback and to deliver objective and reproducible results. The CAD4TB software is a computer-aided detection system that has shown promising preliminary findings. Evaluation studies in different settings are needed to assess diagnostic accuracy and practicability of use.

Methods: CAD4TB was evaluated on chest radiographs of patients with symptoms suggestive of pulmonary tuberculosis enrolled in two cohort studies in Tanzania. All patients were characterized by sputum smear microscopy and culture including subsequent antigen or molecular confirmation of Mycobacterium tuberculosis (M.tb) to determine the reference standard. Chest radiographs were read by the software and two human readers, one expert reader and one clinical officer. The sensitivity and specificity of CAD4TB was depicted using receiver operating characteristic (ROC) curves, the area under the curve calculated and the performance of the software compared to the results of human readers.

Results: Of 861 study participants, 194 (23%) were culture-positive for M.tb. The area under the ROC curve of CAD4TB for the detection of culture-positive pulmonary tuberculosis was 0.84 (95% CI 0.80-0.88). CAD4TB was significantly more accurate for the discrimination of smear-positive cases against non TB patients than for smear-negative cases (p-value<0.01). It differentiated better between TB cases and non TB patients among HIV-negative compared to HIV-positive individuals (p<0.01). CAD4TB significantly outperformed the clinical officer, but did not reach the accuracy of the expert reader (p = 0.02), for a tuberculosis specific reading threshold.

Conclusion: CAD4TB accurately distinguished between the chest radiographs of culture-positive TB cases and controls. Further studies on cost-effectiveness, operational and ethical aspects should determine its place in diagnostic and screening algorithms.

Publication types

  • Research Support, Non-U.S. Gov't
  • Validation Study

MeSH terms

  • Adult
  • Africa South of the Sahara
  • Female
  • HIV Seropositivity
  • Humans
  • Male
  • Middle Aged
  • ROC Curve
  • Radiography, Thoracic* / standards
  • Reproducibility of Results
  • Risk Factors
  • Sensitivity and Specificity
  • Tomography, X-Ray Computed
  • Tuberculosis, Pulmonary / diagnostic imaging*
  • Young Adult

Grant support

This study was supported by the European and Developing Countries Clinical Trials Partnership (EDCTP) as part of the project “Evaluation of new and emerging diagnostics for childhood tuberculosis in high burden countries” (TB CHILD) [IP.2009.32040.007]. The development of the CAD4TB software was supported by the EDCTP as part of the project “Evaluation of Multiple Novel and Emerging Technologies for TB Diagnosis in Smear negative and HIV infected Persons in High-burden Countries” (TB NEAT study) [IP.09.32040.009]. Delft Imaging Systems (CAD4TBII, http://www.delftimagingsystems.com/tb-solutions/cad4tb) provided a research grant to Bram van Ginneken and Rick HHM Philipsen for the development of CAD4TB. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.