Background: Malignant pleural effusion is defined as the presence of malignant cells in pleural effusion (PE) or biopsy specimens and occurs in 15% of all cancer patients. The most common cause is lung cancer in men and breast cancer in women. The reason for hospital admission is usually shortness of breath. The main goal of treatment is to relieve symptoms and prevent recurrence. PET/CT is an imaging system that combines the metabolic properties of PET with the morphologic properties of computed tomography. The patient can be managed more rapidly if malignant effusion can be detected on PET/CT. In this study, we aimed to predict the diagnostic impact of metabolic uptake of fluid in patients with malignant pleural effusion. Methods: In our study, we aimed to find the contribution of PET/CT to the diagnosis of malignant pleural effusion by examining patients between 18 and 90 years of age who had malignancy as a result of pleural cytology and who underwent PET/CT with a primary diagnosis of malignancy. 26 patients were evaluated. The values analyzed were; the presence of PE FDG uptake, the presence of single or double uptake in PE, the presence of multiple pulmonary nodules, the presence of pleural thickness (PT) increase, PK diameter, the presence of FDG uptake in PK, primary pathology being lung or other organ, PE Standardized Uptake Value (SUV) max, PE SUVmax/ Med SUVmax, PE SUVmax/ Liver SUVmax, PE SUVmax/ primary tumor SUVmax, primary tumor SUV values. Results: 6 of 26 patients had bilateral effusions and 12 patients had FDG uptake. 5 patients had pleural thickening and 4 of them had pleural uptake. In the ROC analysis, PE SUVmax, PE SUV / Med SUV, PE SUV / Liver SUV, and PE SUV / Primary tm SUV values were found to be significant in terms of predicting PE FDG uptake, while PT diameter was not significant. Conclusions: Patients with malignant pleural effusion have a short life expectancy. Diagnosis and treatment management of patients should be performed effectively and rapidly. PET/CT can be used as a noninvasive diagnostic method for this purpose. Therefore, if further studies are performed, PET/CT in the diagnosis of MPE will contribute to patient management.

Purpose: Accurate preoperative risk stratification in endometrial cancer (EC) is essential for guiding surgical and therapeutic decisions. This study aimed to evaluate the discriminative performance of [18F]-FDG PET/CT-derived radiomic features combined with machine learning models for differentiating low-risk (LRH-EC) and high-risk histology (HRH-EC) subtypes. Methods: A total of 159 patients with histopathologically confirmed EC who underwent preoperative [18F]-FDG PET/CT were retrospectively analyzed. Radiomic features were extracted using LIFEx version 7.4.0 software following IBSI guidelines. After FDR correction and Pearson correlation–based redundancy reduction (|r| > 0.80), 16 radiomic features were retained for modeling. Three feature configurations (Conventional PET parameters, Radiomics16, and Combined) were evaluated. Machine learning models were developed using stratified 5-fold cross-validation. Model performance was assessed using AUC, accuracy, sensitivity, specificity, F1-score, Wilson confidence intervals, DeLong’s test, and McNemar’s test. Results: Artificial Neural Network (ANN) (AUC = 0.709) and Random Forest (RF) (AUC = 0.686) achieved the highest discriminative performance within the Radiomics16 feature set. No statistically significant superiority between algorithms or feature configurations was observed by DeLong analysis. However, McNemar’s test demonstrated significant patient-level classification differences for the Combined ANN model (p < 0.001). NGTDM_Coarseness and SUVmin emerged as the most influential features, reflecting tumor heterogeneity and metabolic activity. Conclusions: [18F]-FDG PET/CT-based radiomics combined with machine learning provides moderate yet consistent discrimination between LRH-EC and HRH-EC. While external validation is required, this approach may support noninvasive preoperative risk stratification in endometrial cancer.