Bayesian optimization of Random Forest hyperparameters for radiomics-based detection of clinically significant prostate cancer

This thesis presents a case study in enhancing a medical imaging machine learning (ML) system for prostate cancer detection. Prostate cancer affects approximately one in eight men in the United States, making early and accurate detection critical for patient outcomes. While ML systems show promise for improving diagnostic accuracy, their effectiveness depends fundamentally on the quality and integrity of the data.