Poster Presentation: Prostate MRI Segmentation at ICIAP 2025, Rome

Prostate cancer is one of the most frequently diagnosed malignancies in men worldwide, requiring early and accurate diagnosis for effective treatment and improved survival. Multiparametric MRI (mpMRI) provides detailed anatomical imaging, but accurate segmentation of the prostate and cancerous regions is critical for diagnostic precision. Manual segmentation is labor-intensive and prone to variability, motivating the use of deep learning-based automated approaches. Convolutional neural network models, including U-Net and E-Net, have shown excellent performance in capturing complex anatomy and enhancing segmentation accuracy. This study evaluates the effectiveness and clinical applicability of these architectures for automated prostate MRI segmentation, aiming to support precise diagnosis and personalized treatment planning.