Magnetic resonance imaging (MRI) is used to diagnose prostate cancer non-invasively. It is used for detecting and staging the cancer as well as guiding biopsies and planning treatments. Advanced MRI methods like T2-weighted imaging, diffusion-weighted imaging (DWI), dynamic contrast-enhanced MRI (DCE-MRI) and magnetic resonance spectroscopic imaging (MRSI) are used to assess prostate cancer. The aim of the study is to analyse and compare parameter values obtained from imaging techniques such as DWI, DCE and MRSI at 1.5 and 3 T magnetic field strengths, as well as to evaluate how well the parameters benefit in differentiating between benign and cancerous prostate tissues. This study included 85 patients (35, 1.5 T MRI and 50, 3 T MRI). For the purpose of characterization, machine learning methods like linear discriminant analysis and support vector machines (both linear and Gaussian kernels) were employed alongside a fivefold cross-validation method to ensure robust validation. By using a combination of parameters from DWI, DCE-MRI and MRS imaging, a Gaussian support vector machine classifier was able to achieve an accuracy rate of around 92.50% when analysing data from 1.5 T data and 3 T data achieved an accuracy rate of 95%. The findings revealed that the use of field strength with the 3 T MRI led to higher diagnostic performance compared to those obtained from the 1.5 T MRI, thereby emphasizing the advantages associated with higher field strengths in accurately characterizing prostate cancer.