biostudies-literatureUnknown53(3)Jiang ZMedical University of Vienna<h4>Purpose</h4>Accurate non-invasive prediction of histopathologic invasiveness and recurrence risk remains a clinical challenge in resectable non-small cell lung cancer (NSCLC). We developed and validated the Edge Proximity Score (EPS), a novel [¹⁸F]FDG PET/CT-based spatial imaging feature that quantifies the displacement of SUVmax relative to the tumor centroid and perimeter, to assess tumor aggressiveness and predict progression-free survival (PFS).<h4>Methods</h4>This retrospective study included 244 NSCLC patients with preoperative [¹⁸F]FDG PET/CT. EPS was computed from normalized SUVmax-to-centroid and SUVmax-to-perimeter distances. A total of 115 PET radiomics features were extracted and standardized. Eight machine learning models (80:20 split) were trained toEuropean journal of nuclear medicine and molecular imaging1458-1468https://www.ebi.ac.uk/biostudies/studies/S-EPMC12860873biostudies-literatureSpatial imaging features derived from SUVmax location in resectable NSCLC are associated with tumor aggressiveness.PMC12860873Aigner CHorvath LRenyi-Vamos FHaberl DLang CSpielvogel CYu JKrisch MMegyesfalvi ZHacker MMolnar PJiang ZFillinger JKenner LSzakall SDome BfalseSpatial imaging features derived from SUVmax location in resectable NSCLC are associated with tumor aggressiveness.<h4>Purpose</h4>Accurate non-invasive prediction of histopathologic invasiveness and recurrence risk remains a clinical challenge in resectable non-small cell lung cancer (NSCLC). We developed and validated the Edge Proximity Score (EPS), a novel [¹⁸F]FDG PET/CT-based spatial imaging feature that quantifies the displacement of SUVmax relative to the tumor centroid and perimeter, to assess tumor aggressiveness and predict progression-free survival (PFS).<h4>Methods</h4>This retrospective study included 244 NSCLC patients with preoperative [¹⁸F]FDG PET/CT. EPS was computed from normalized SUVmax-to-centroid and SUVmax-to-perimeter distances. A total of 115 PET radiomics features were extracted and standardized. Eight machine learning models (80:20 split) were trained to2026-01-01T00:00:00Z2026 Feb2026-07-15T00:48:49.477Z2026-06-27T03:05:28.948ZS-EPMC128608734083930910.1007/s00259-025-07528-0