RESUMO
The aim of our study was to predict the occurrence of distant metastases in non-small-cell lung cancer (NSCLC) patients using machine learning methods and texture analysis of 18F-labeled 2-deoxy-d-glucose Positron Emission Tomography/Computed Tomography {[18F]FDG PET/CT} images. In this retrospective and single-center study, we evaluated 79 patients with advanced NSCLC who had undergone [18F]FDG PET/CT scan at diagnosis before any therapy. Patients were divided into two independent training (n = 44) and final testing (n = 35) cohorts. Texture features of primary tumors and lymph node metastases were extracted from [18F]FDG PET/CT images using the LIFEx program. Six machine learning methods were applied to the training dataset using the entire panel of features. Dedicated selection methods were used to generate different combinations of five features. The performance of selected machine learning methods applied to the different combinations of features was determined using accuracy, the confusion matrix, receiver operating characteristic (ROC) curves, and area under the curve (AUC). A total of 104 and 78 lesions were analyzed in the training and final testing cohorts, respectively. The support vector machine (SVM) and decision tree methods showed the highest accuracy in the training cohort. Seven combinations of five features were obtained and introduced in the models and subsequently applied to the training and final testing cohorts using the SVM and decision tree. The accuracy and the AUC of the decision tree method were higher than those obtained with the SVM in the final testing cohort. The best combination of features included shape sphericity, gray level run length matrix_run length non-uniformity (GLRLM_RLNU), Total Lesion Glycolysis (TLG), Metabolic Tumor Volume (MTV), and shape compacity. The combination of these features with the decision tree method could predict the occurrence of distant metastases with an accuracy of 74.4% and an AUC of 0.63 in NSCLC patients.
RESUMO
We investigated the role of Coefficient of Variation (CoV), a first-order texture parameter derived from 18F-FDG PET/CT, in the prognosis of Non-Small Cell Lung Cancer (NSCLC) patients. Eighty-four patients with advanced NSCLC who underwent 18F-FDG PET/CT before therapy were retrospectively studied. SUVmax, SUVmean, CoV, total Metabolic Tumor Volume (MTVTOT) and whole-body Total Lesion Glycolysis (TLGWB) were determined by an automated contouring program (SUV threshold at 2.5). We analyzed 194 lesions: primary tumors (n = 84), regional (n = 48) and non-regional (n = 17) lymph nodes and metastases in liver (n = 9), bone (n = 23) and other sites (n = 13); average CoVs were 0.36 ± 0.13, 0.36 ± 0.14, 0.42 ± 0.18, 0.30 ± 0.14, 0.37 ± 0.17, 0.34 ± 0.13, respectively. No significant differences were found between the CoV values among the different lesion categories. Survival analysis included age, gender, histology, stage, MTVTOT, TLGWB and imaging parameters derived from primary tumors. At univariate analysis, CoV (p = 0.0184), MTVTOT (p = 0.0050), TLGWB (p = 0.0108) and stage (p = 0.0041) predicted Overall Survival (OS). At multivariate analysis, age, CoV, MTVTOT and stage were retained in the model (p = 0.0001). Patients with CoV > 0.38 had significantly better OS than those with CoV ≤ 0.38 (p = 0.0143). Patients with MTVTOT ≤ 89.5 mL had higher OS than those with MTVTOT > 89.5 mL (p = 0.0063). Combining CoV and MTVTOT, patients with CoV ≤ 0.38 and MTVTOT > 89.5 mL had the worst prognosis. CoV, by reflecting the heterogeneity of glycolytic phenotype, can predict clinical outcomes in NSCLC patients.
