CT image feature analysis in distinguishing radiation fibrosis from tumour recurrence after stereotactic ablative radiotherapy (SABR) for lung cancer: a preliminary study

Abstract

Radiation induced lung injury (RILI) is a common finding following lung radiotherapy and results in radiographic changes on computed tomography (CT). Stereotactic ablative radiotherapy (SABR) treats the tumour to a highly conformal dose with large doses/fraction, which can result in benign, tumour-mimicking radiographic changes. Our purpose was to determine the ability of quantitative measures of post-SABR radiographic changes to distinguish the subject groups (recurrence vs. RILI) at several time points. Two regions were manually contoured on each follow-up CT: consolidative changes and ground glass opacity (GGO). A peri-tumoural region of GGO was also taken around the consolidative changes. At 9 months, patients with recurrence had significantly denser consolidative areas compared to patients with RILI (p=.046) and significantly increased variability of CT densities in the GGO areas (p=.0078). The variability of CT density in a peri-tumoural region of 4 mm thickness was also significant at 9 months post-treatment (p=.0499). Our preliminary study of classification accuracy based on these measures showed that variability of the GGO CT density was the best predictor with a cross validation error of 26.1%, demonstrating that further refinement of the features and classifier may soon lead to a clinically useful computer-aided diagnosis tool. These results suggest the future potential to distinguish patients with recurrence from those RILI at 9 months post-SABR based on appearance characteristics within the consolidative, GGO, and peri-tumoural regions. This could potentially allow for earlier salvage of patients with recurrence, and result in fewer investigations of benign RILI.