The use of the International Labor Office (ILO) digitized standard images for classification of small pneumoconiotic opacities has been validated, according to a study published in the March issue of Academic Radiology.
Interpretations of chest radiographs for epidemiologic studies of pneumoconiosis have been standardized with the release of the ILO classification guidelines that were revised in 2011. Before this update, several research studies were conducted to assess the potential impact of image modality on the outcomes of ILO classifications of chest radiographs. Lead author Cara N. Halldin, PhD, of the Centers for Disease Control and Prevention in Morgantown, W.Va., and colleagues aimed to compare the results of the classifications of digital chest images performed using the 2011 ILO digitized standard images to previous classification approaches.
The study included 172 underground coal miners who were examined with both digital and film-screen radiography. Seven readers independently classified the images by using the ILO classification guidelines and the digital standardized images from previous research. They also classified all chest films using the ILO’s film-based standards.
Results revealed identical agreement between classifications of film-screen radiography and digital radiography. The overall weighted κ value was 0.58. Intrareader variability was similar to published values and was not affected by the use of the 2011 ILO digitized standard images.
“The results of the present study demonstrate that, when chest radiographs are obtained and displayed using appropriate equipment, methods, and conditions, the results of classification of digital chest radiographs performed using 2011-D standards should be quite comparable to results based on the previous digitized research standards and also to the film-based ILO 2000 classification,” wrote Halldin and colleagues. “The current challenge for the ILO is to complete development and testing of a set of reference standards for the classification of digital chest images that are digitally acquired.”