Original Article
Quantitative texture analysis on pre-treatment computed tomography predicts local recurrence in stage I non-small cell lung cancer following stereotactic radiation therapy
Abstract
Background: The prediction of local recurrence (LR) of stage I non-small cell lung cancer (NSCLC) after de nitive stereotactic body radiotherapy (SBRT) remains elusive. The purpose of this study was to assess whether quantitative imaging features on pre-treatment computed tomography (CT) can predict LR beyond 18 (18F) uorodeoxyglucose (18F-FDG) positron emission tomography (PET)/CT maximum standard uptake value (SUVmax).
Methods: This retrospective study evaluated 36 patients with 37 stage I NSCLC who had local tumor control (LC; n=19) and (LR; n=18). Textural features were extracted on pre-treatment CT. Mann-Whitney U tests were used to compare LC and LR groups. Receiver-operating characteristic (ROC) curves were constructed and the area under the curve (AUC) calculated with LR as outcome.
Results: Gray-level correlation and sum variance were greater in the LR group, compared with the LC group (P=0.02 and P=0.04, respectively). Gray-level difference variance was lower in the LR group (P=0.004). The logistic regression model generated using gray-level correlation and difference variance features resulted in AUC (SE) 0.77 (0.08) (P=0.0007). The addition of 18F-FDG PET/CT SUVmax did not improve the AUC (P=0.75).
Conclusions: CT textural features were found to be predictors of LR of early stage NSCLC on baseline CT prior to SBRT.
Methods: This retrospective study evaluated 36 patients with 37 stage I NSCLC who had local tumor control (LC; n=19) and (LR; n=18). Textural features were extracted on pre-treatment CT. Mann-Whitney U tests were used to compare LC and LR groups. Receiver-operating characteristic (ROC) curves were constructed and the area under the curve (AUC) calculated with LR as outcome.
Results: Gray-level correlation and sum variance were greater in the LR group, compared with the LC group (P=0.02 and P=0.04, respectively). Gray-level difference variance was lower in the LR group (P=0.004). The logistic regression model generated using gray-level correlation and difference variance features resulted in AUC (SE) 0.77 (0.08) (P=0.0007). The addition of 18F-FDG PET/CT SUVmax did not improve the AUC (P=0.75).
Conclusions: CT textural features were found to be predictors of LR of early stage NSCLC on baseline CT prior to SBRT.
