Prostate cancer is the most common type of cancer in males, affecting 1 in every 8 males some point in their lifetime and methods for early diagnosis is currently ineffective.
The project aims to use Deep Learning and Computer Vision to classify images of hydrodynamically stretched prostate cells as either cancerous or healthy.
These goals are aimed to be achieved with the use of a convolutional neural network (CNN) built in Python using Keras. Images of cancerous and healthy prostate cells undergoing hydrodynamic stretching are extracted and processed from videos. These processed images are then used to train and evaluate a CNN to determine if a difference between the the two populations of cells can be accurately learned.