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

• DOI: 10.1016/j.acra.2024.06.038
• Publication Date: 2024-07-14T04:03:04Z
• Authors: Ricarda Hinzpeter; Roshini Kulanthai...; Andres Kohan; Vanessa Murad; Seyed Ali Mirshah...; Lisa Avery; Claudia Ortega; Ur Metser; Andrew Hope; Jonathan Yeung; Micheal McInnis; Patrick Veit-Haibach
• Keywords: Radiogenomics

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