In this study, we aimed to compare the diagnostic accuracy of 18 F−fluorodeoxyglucose ( 18 F-FDG) and Gallium-68 labeled fibroblast activator protein inhibitor ( 68 Ga-FAPI)-04 PET/CT in the tumor-node-metastasis (TNM) staging of patients with nonsmall cell lung cancer (NSCLC) and investigate whether adenocarcinoma (ADC) and squamous cell cancer (SCC) exhibit different uptake patterns on 68 Ga-FAPI-04 PET/CT. Materials and methodTwenty-nine patients with a histopathologically-confirmed diagnosis of NSCLC, who had no history of previous radiation therapy or chemotherapy and underwent 18 F-FDG PET/CT and 68 Ga-FAPI-04 PET/CT imaging between January 2021 and December 2021 were included in this retrospective study. Staging was performed using the 8th edition of the TNM staging system on both 18 F-FDG PET/CT and 68 Ga-FAPI-04 PET/CT images. Standardized uptake value (SUV) max and tumor-to-background ratios (TBR) were calculated on primary lesions and metastases. ResultsThere was no statistically significant difference in primary lesions in terms of SUV max and TBR values. However, 68 Ga-FAPI-04 PET/CT was significantly superior to 18 F-FDG PET/CT in terms of the number of lymph nodes and bone metastases revealed. The SUV max and TBR values of lymph nodes, hepatic lesions and bone lesions were significantly higher on 68 Ga-FAPI-04 PET/ CT than on 18 F-FDG PET/CT. 68 Ga-FAPI-04 PET/CT changed the disease stage of three patients (10.9%). The diagnostic accuracy of 68 Ga-FAPI-04 PET/CT was 100%, whereas the diagnostic accuracy of 18 F-FDG PET/CT was 89.6% (P = 0.250). ConclusionAlthough 68 Ga-FAPI-04 PET/CT detected more lesions and higher diagnostic accuracy than 18 F-FDG PET/CT in NSCLC, neither method was statistically superior to each other in terms of diagnostic accuracy in TNM staging.

Objective Identification of anaplastic lymphoma kinase (ALK) and epidermal growth factor receptor (EGFR) mutation types is of great importance before treatment with tyrosine kinase inhibitors (TKIs). Radiomics is a new strategy for noninvasively predicting the genetic status of cancer. We aimed to evaluate the predictive power of 18F-FDG PET/CT-based radiomic features for mutational status before treatment in non-small cell lung cancer (NSCLC) and to develop a predictive model based on radiomic features. Methods Images of patients who underwent 18F-FDG PET/CT for initial staging with the diagnosis of NSCLC between January 2015 and July 2020 were evaluated using LIFEx software. The region of interest (ROI) of the primary tumor was established and volumetric and textural features were obtained. Clinical data and radiomic data were evaluated with machine learning (ML) algorithms to create a model. Results For EGFR mutation prediction, the most successful machine learning algorithm obtained with GLZLM_GLNU and clinical data was Naive Bayes (AUC: 0.751, MCC: 0.347, acc: 71.4%). For ALK rearrangement prediction, the most successful machine learning algorithm obtained with GLCM_correlation, GLZLM_LZHGE and clinical data was evaluated as Naive Bayes (AUC: 0.682, MCC: 0.221, acc: 77.4%). Conclusions In our study, we created prediction models based on radiomic analysis of 18F-FDG PET/CT images. Tissue analysis with ML algorithms are non-invasive methods for predicting ALK rearrangement and EGFR mutation status in NSCLC, which may be useful for targeted therapy selection in a clinical setting.

No abstract

Objective In this study, we aimed to evaluate the role of 18F-fluorodeoxyglucose PET/computerized tomography (18F-FDG PET/CT)-based radiomic features in the differentiation of infection and malignancy in consolidating pulmonary lesions and to develop a prediction model based on radiomic features. Material and methods The images of 106 patients who underwent 18F-FDG PET/CT of consolidated lesions observed in the lung between January 2015 and July 2020 were evaluated using LIFEx software. The region of interest of the lung lesions was determined and volumetric and textural features were obtained. Clinical and radiomic data were evaluated with machine learning algorithms to build a model. Results There was a significant difference in all standardized uptake value (SUV) parameters and 26 texture features between the infection and cancer groups. The features with a correlation coefficient of less than 0.7 among the significant features were determined as SUVmean, GLZLM_SZE, GLZLM_LZE, GLZLM_SZLGE and GLZLM_ZLNU. These five features were analyzed in the Waikato Environment for Knowledge Analysis program to create a model that could distinguish infection and cancer groups, and the model performance was found to be the highest with logistic regression (area under curve, 0.813; accuracy, 75.7%). The sensitivity and specificity values of the model in distinguishing cancer patients were calculated as 80.6 and 70.6%, respectively. Conclusions In our study, we created prediction models based on radiomic analysis of 18F-FDG PET/CT images. Texture analysis with machine learning algorithms is a noninvasive method that can be useful in the differentiation of infection and malignancy in consolidating lung lesions in the clinical setting.