This project implements a 2D UNet CNN architecture for segmenting prostates from MRI scans using a 2D U-Net architecture. The workflow is designed to handle pre-processed 2D slices of prostate MRIs, enabling efficient training and evaluation of segmentation models. Preprocessing was already handled by the 2d segments taken as inputs to this CNN, but some augmentation (flipping and rotation) and normalisation was still done.

The goal is to accurately delineate the prostate from surrounding tissues, which is critical for clinical applications such as radiotherapy planning, disease diagnosis, and progression monitoring.