Machine Learning Integrating 99mTc Sestamibi SPECT/CT and Radiomics Data Achieves Optimal Characterization of Renal Oncocytic Tumors

The increasing evidence of oncocytic renal tumors positive in 99mTc Sestamibi Single Photon Emission Tomography/Computed Tomography (SPECT/CT) examination calls for the development diagnostic tools to differentiate these from more aggressive forms. This study combined radiomics analysis with uptake on SPECT/CT benign neoplasms cell carcinoma. A total 57 were prospectively collected. Histopathological and data extraction performed. XGBoost classifiers trained using features alone results visual evaluation examination. SPECT/radiomics model achieved higher accuracy (95%) an area under curve (AUC) 98.3% (95% CI 93.7–100%) than radiomics-only (71.67%) AUC 75% 49.7–100%) (90.8%) 90.8% (95%CI 82.5–99.1%). predictive values SPECT/radiomics, radiomics-only, SPECT/CT-only models 100%, 85.71%, 85%, respectively, whereas negative 55.56%, 94.6%, respectively. Feature importance revealed that was most influential attribute model. highlights potential combining improve preoperative characterization neoplasms. proposed classifier outperformed Sestamibii model, demonstrating integration provides improved performance, minimal false results.