Association of Fluorodeoxyglucose Positron Emission Tomography Radiomics Features with Clinicopathological Factors and Prognosis in Lung Squamous Cell Cancer
Nuclear Medicine and Molecular Imaging, cilt.56, sa.6, ss.306-312, 2022 (ESCI, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 56 Sayı: 6
- Basım Tarihi: 2022
- Doi Numarası: 10.1007/s13139-022-00774-2
- Dergi Adı: Nuclear Medicine and Molecular Imaging
- Derginin Tarandığı İndeksler: Emerging Sources Citation Index (ESCI), Scopus, EMBASE
- Sayfa Sayıları: ss.306-312
- Anahtar Kelimeler: Squamous cell lung cancer, Radiomics, Fluorodeoxyglucose, Positron emission tomography
- Sağlık Bilimleri Üniversitesi Adresli: Evet
Özet
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.