Nucl Med Mol Imaging.  2022 Dec;56(6):306-312. 10.1007/s13139-022-00774-2.

Association of Fluorodeoxyglucose Positron Emission Tomography Radiomics Features with Clinicopathological Factors and Prognosis in Lung Squamous Cell Cancer

Affiliations
  • 1Department of Nuclear Medicine, Konya City Hospital, University of Health Sciences Turkey, Konya, Turkey
  • 2Department of Nuclear Medicine, Medical Faculty, Selcuk University, Konya, Turkey
  • 3Department of Pathology, Konya City Hospital, University of Health Sciences Turkey, Konya, Turkey

Abstract

Aim To evaluate the role of fluorine-18 fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) radiomics features (RFs) for predicting clinicopathological factors (CPFs) and prognosis in patients with resected lung squamous cell cancer (LSCC). Material and Methods Patients with early-stage (stage I–III) LSCC who underwent 18F-FDG PET/CT before surgical resection between August 2012 and February 2020 were analyzed. Patients who received neoadjuvant chemotherapy or radiotherapy were excluded from the study. The maximum standard uptake value (SUVmax) and RFs were extracted from PET images for primary tumors. The diagnostic performances of PET parameters in groups of tumor differentiation, stage, and mediastinal lymph node metastasis (MLNM) status were evaluated. The study endpoints were overall survival (OS) and progression-free survival (PFS). Univariate and multivariate analyses were performed with RFs, SUVmax, and CPFs to find independent predictors of PFS and OS.
Results
A total of 77 patients (5 female, 72 male) were included in the study. SUVmax and GLCM entropy were independently associated with tumor differentiation. The only parameter with significant diagnostic performance for MLNM was GLZLM-SLZGE. Tumor diameter and NGLDM busyness were independently associated with the stage. MLNM and tumor differentiation were found to be independent predictors of PFS. NGLDM contrast and MLNM were independently associated with OS.
Conclusion
Using radiomic features in addition to CPFs to predict disease recurrence and shorter overall survival can guide precision medicine in patients with LSCC.

Keyword

Squamous cell lung cancer; Radiomics; Fluorodeoxyglucose; Positron emission tomography
Full Text Links
  • NMMI
Actions
Cited
CITED
export Copy
Close
Share
  • Twitter
  • Facebook
Similar articles
Copyright © 2024 by Korean Association of Medical Journal Editors. All rights reserved.     E-mail: koreamed@kamje.or.kr