Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Spatial imaging features derived from SUVmax location in resectable NSCLC are associated with tumor aggressiveness

Jiang, Zewen ; Spielvogel, Clemens ; Haberl, David ; Yu, Josef ; Krisch, Maximilian ; Szakall, Szabolcs ; Molnar, Peter ; Fillinger, Janos ; Horvath, Lilla and Renyi-Vamos, Ferenc , et al. (2025) In European Journal of Nuclear Medicine and Molecular Imaging
Abstract

Purpose: 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). Methods: 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... (More)

Purpose: 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). Methods: 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 to predict lymphovascular invasion (LVI), visceral pleural invasion (VPI), and spread through air spaces (STAS), with feature importance assessed using SHAP. Prognostic analysis was conducted using multivariable Cox regression. A survival prediction model incorporating EPS was externally validated in the TCIA cohort. RNA sequencing data from 76 TCIA patients were used for transcriptomic and immune profiling. Results: EPS was significantly elevated in tumors with LVI, VPI, and STAS (P < 0.001), consistently ranked among the top SHAP features, and was an independent predictor of PFS (HR = 2.667, P = 0.015). The EPS-based nomogram achieved AUCs of 0.67, 0.70, and 0.68 for predicting 1-, 3-, and 5-year PFS in the TCIA validation cohort. High EPS was associated with proliferative and metabolic gene signatures, whereas low EPS was linked to immune activation and neutrophil infiltration. Conclusion: EPS is a biologically relevant, non-invasive imaging biomarker that may improve risk stratification in NSCLC.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and , et al. (More)
; ; ; ; ; ; ; ; ; ; ; ; ; ; and (Less)
organization
publishing date
type
Contribution to journal
publication status
epub
subject
keywords
NSCLC, Radiomics, Tumor invasiveness, [F]FDG PET/CT
in
European Journal of Nuclear Medicine and Molecular Imaging
publisher
Springer
external identifiers
  • scopus:105013748919
ISSN
1619-7070
DOI
10.1007/s00259-025-07528-0
language
English
LU publication?
yes
id
67665a03-4fa0-4dbe-86e1-1600cd1b0b4c
date added to LUP
2025-11-19 09:27:57
date last changed
2025-11-19 09:29:16
@article{67665a03-4fa0-4dbe-86e1-1600cd1b0b4c,
  abstract     = {{<p>Purpose: 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 [<sup>18</sup>F]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). Methods: This retrospective study included 244 NSCLC patients with preoperative [<sup>18</sup>F]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 to predict lymphovascular invasion (LVI), visceral pleural invasion (VPI), and spread through air spaces (STAS), with feature importance assessed using SHAP. Prognostic analysis was conducted using multivariable Cox regression. A survival prediction model incorporating EPS was externally validated in the TCIA cohort. RNA sequencing data from 76 TCIA patients were used for transcriptomic and immune profiling. Results: EPS was significantly elevated in tumors with LVI, VPI, and STAS (P &lt; 0.001), consistently ranked among the top SHAP features, and was an independent predictor of PFS (HR = 2.667, P = 0.015). The EPS-based nomogram achieved AUCs of 0.67, 0.70, and 0.68 for predicting 1-, 3-, and 5-year PFS in the TCIA validation cohort. High EPS was associated with proliferative and metabolic gene signatures, whereas low EPS was linked to immune activation and neutrophil infiltration. Conclusion: EPS is a biologically relevant, non-invasive imaging biomarker that may improve risk stratification in NSCLC.</p>}},
  author       = {{Jiang, Zewen and Spielvogel, Clemens and Haberl, David and Yu, Josef and Krisch, Maximilian and Szakall, Szabolcs and Molnar, Peter and Fillinger, Janos and Horvath, Lilla and Renyi-Vamos, Ferenc and Aigner, Clemens and Dome, Balazs and Lang, Christian and Megyesfalvi, Zsolt and Kenner, Lukas and Hacker, Marcus}},
  issn         = {{1619-7070}},
  keywords     = {{NSCLC; Radiomics; Tumor invasiveness; [F]FDG PET/CT}},
  language     = {{eng}},
  publisher    = {{Springer}},
  series       = {{European Journal of Nuclear Medicine and Molecular Imaging}},
  title        = {{Spatial imaging features derived from SUVmax location in resectable NSCLC are associated with tumor aggressiveness}},
  url          = {{http://dx.doi.org/10.1007/s00259-025-07528-0}},
  doi          = {{10.1007/s00259-025-07528-0}},
  year         = {{2025}},
}