Predictive [18F]-FDG PET/CT-Based Radiogenomics Modelling of Driver Gene Mutations in Non-small Cell Lung Cancer

Abstract

Rationale and Objectives To investigate whether [ 18 F]-FDG PET/CT-derived radiomics may correlate with driver gene mutations in non-small cell lung cancer (NSCLC) patients. Materials and Methods In this IRB-approved retrospective study, 203 patients with surgically treated NSCLC who underwent subsequent genomic analysis of the primary tumour at our institution between December 2004 and January 2014 were identified. Of those, 128 patients (mean age 62.4 ± 10.8 years; range: 35–84) received preoperative [ 18 F]-FDG PET/CT as part of their initial staging and thus were included in the study. PET and CT image segmentation and feature extraction were performed semi-automatically with an open-source software platform (LIFEx, Version 6.30, lifexsoft.org). Molecular profiles using different next-generation sequencing (NGS) panels were collected from a web-based resource (cBioPortal.ca for Cancer genomics). Two statistical models were then built to evaluate the predictive ability of [ 18 F]-FDG PET/CT-derived radiomics features for driver gene mutations in NSCLC. Results More than half (68/128, 53%) of all tumour samples harboured three or more gene mutations. Overall, 55% of tumour samples demonstrated a mutation in TP53, 26% of samples had alterations in KRAS and 17% in EGFR. Extensive statistical analysis resulted in moderate to good predictive ability. The highest Youden Index for TP53 was achieved using combined PET/CT features (0.70), for KRAS using PET features only (0.57) and for EGFR using CT features only (0.60). Conclusion Our study demonstrated a moderate to good correlation between radiomics features and driver gene mutations in NSCLC, indicating increased predictive ability of genomic profiles using combined [ 18 F]-FDG PET/CT-derived radiomics features.