Artificial Intelligence for Explainable signs of Emphysema on Chest X-Ray

We collected 281,000 CXR studies from our hospital archive (2006 to 2019). Only those with a frontal (posteroanterior) and a lateral CXR were retained, resulting in 97,000 studies. Studies where the radiology report mentioned ‘emphysema’ without the words ‘interstitial’ or ‘subcutaneous’ (16,000) were selected for potential inclusion. The dataset was obtained by a random selection of 2000 studies from the potential emphysema studies and 1000 studies from the remaining 81,000 studies. We created two random groups of 1750 studies with 500 studies common to both. Each of these groups was annotated by a chest radiologist, one with over 30 years of experience (ETS) (R1) and the other with over 7 (SS) (R2). The 500 studies were annotated by both radiologists as the test set. Reader studies on grand-challenge.org were used to annotate images. The radiologists were asked to indicate (yes/no) whether the visual signs of emphysema described by Sutinen et al. (1965) were present on the images they viewed. They worked independently, scored frontals and laterals separately, and could not link the frontal and lateral image of a subject with each other. Line drawing and measurement tools were provided, as well as a free-text comment box. Subjects who had two or more of the four visual signs indicated present by the radiologist were considered emphysema positive as proposed by Sutinen et al. (1965)