Abstract
Objective: This study evaluates the accuracy of a Machine Learning model of Random Forest (RF) type, using MRI data and radiomic features to predict lymph node involvement in prostate cancer (PCa). Methods: Ninety-five patients who underwent mp-MRI, prostatectomy, and lymphadenectomy at the Fondazione Policlinico Campus Bio-medico Radiological Department from 2016 to 2022 were analyzed. Radiomic features were extracted from T2-weighted, DWI, and ADC sequences and processed using a Random Forest (RF) model. Clinical data such as PSA levels and Gleason scores were also considered. Results: The RF model demonstrated significant accuracy in predicting lymph node involvement, achieving 84% accuracy for nodules in the peripheral zone (80% for predicting positive lymph node involvement and 85% for negative lymph node involvement) and 87% for those in the transitional zone (86% for predicting positive lymph node involvement and 88% for negative lymph node involvement). In the peripheral zone, key features included ADC shape maximum 2D diameter row and T2 noduloglcm difference variance, while in the transitional zone, DWI glcm difference average and DWI glcm Idm were important. DWI and ADC sequences were particularly crucial for accurate lymph node assessment. First-order features emerged as the most significant in whole-gland analysis, indicating fundamental differences in tumor composition and density critical for identifying malignancies with higher metastatic potential. Conclusions: AI-driven radiomic analysis, especially using DWI- and ADC-derived features, effectively predicts lymph node involvement in PCa patients, in particular in negative linfonode status patients, offering a promising tool for preoperative linfonode sparing patient selection. Further validation with larger cohorts is needed. Some limitations of this study are a relatively small sample size and it being a retrospective study.