Background Renal cell carcinoma (RCC) is a prevalent malignancy with highly variable outcomes. MicroRNA-15a
(miR-15a) has emerged as a promising prognostic biomarker in RCC, linked to angiogenesis, apoptosis, and proliferation.
Radiogenomics integrates radiological features with molecular data to non-invasively predict biomarkers, offering
valuable insights for precision medicine. This study aimed to develop a machine learning-assisted radiogenomic
model to predict miR-15a expression in RCC.
Methods A retrospective analysis was conducted on 64 RCC patients who underwent preoperative multiphase
contrast-enhanced CT or MRI. Radiological features, including tumor size, necrosis, and nodular enhancement, were
evaluated. MiR-15a expression was quantified using real-time qPCR from archived tissue samples. Polynomial regression
and Random Forest models were employed for prediction, and hierarchical clustering with K-means analysis
was used for phenotypic stratification. Statistical significance was assessed using non-parametric tests and machine
learning performance metrics.
Results Tumor size was the strongest radiological predictor of miR-15a expression (adjusted R2 = 0.8281, p < 0.001).
High miR-15a levels correlated with aggressive features, including necrosis and nodular enhancement (p < 0.05),
while lower levels were associated with cystic components and macroscopic fat. The Random Forest regression
model explained 65.8% of the variance in miR-15a expression ( R2 = 0.658). For classification, the Random Forest classifier
demonstrated exceptional performance, achieving an AUC of 1.0, a precision of 1.0, a recall of 0.9, and an F1-score
of 0.95. Hierarchical clustering effectively segregated tumors into aggressive and indolent phenotypes, consistent
with clinical expectations.
Conclusions Radiogenomic analysis using machine learning provides a robust, non-invasive approach to predicting
miR-15a expression, enabling enhanced tumor stratification and personalized RCC management. These findings
underscore the clinical utility of integrating radiological and molecular data, paving the way for broader adoption
of precision medicine in oncology.

Purpose: Inferior vena cava (IVC) involvement by renal cell carcinoma (RCC) is associated with a higher disease stage and is considered a risk factor for poor prognosis. This study aimed to investigate the role of the apparent diffusion coefficient (ADC) of MRI 3D texture analysis in the differentiation of solid and friable tumour thrombus in patients with RCC.

Materials and methods: The study involved 27 patients with RCC with tumour thrombus in the renal vein or IVC, surgically treated with nephrectomy and thrombectomy and in whom preoperatively abdominal MRI including the DWI sequence was conducted. For 3D texture analysis, the ADC map was used, and the first-order radiomic features were calculated from the whole volume of the thrombus. All tumour thrombi were histologically clas sified as solid or friable.

Results: The solid and friable thrombus was detected in 51.9 % and 48.1 % of patients, respectively. No differences in mean values of range, 90th percentile, interquartile range, kurtosis, uniformity and variance were found between groups. Equal sensitivity and specificity (93 % and 69 %, respectively) of ADC mean, median and entropy in differentiation between solid and friable tumour thrombus, with the highest AUC for entropy (0.808), were observed. Applying the skewness threshold value of 0.09 allowed us to achieve a sensitivity of 86 % and a specificity of 92 %.

Conclusions: In patients with RCC and tumour thrombus in the renal vein or IVC, the 3D texture analysis based on ADC-map allows for precise differentiation of a solid from a friable thrombus.