Park S, Lee SM, Noh HN, et al. - Using CT radiomic features, researchers wanted to construct a model for categorizing the most common subtype-based prognostic groups of lung adenocarcinoma, and to compare these results with radiologists’ assessments. They included 993 patients who presented with invasive lung adenocarcinoma between March 2010 and June 2016. The three histologic subtypes according to their prognosis were seperated into group 0 (lepidic), group 1 (acinar/papillary), and group 2 (solid/micropapillary). Receiver operating characteristic curve analysis was applied to assess the performance of the radiomic model; the test set was then compared with that of three radiologists with varying experiences (6, 7, and 19 years in chest CT) to determine accuracy. The results of this study suggested that the most common subtype-based prognostic groups of lung adenocarcinoma could be categorized by a CT-based radiomic model, and its performance was comparable to that of radiologists.