BIT DEPTH REDUCTION: ASSESSING THE IMPACT ON PULSE COUPLED NEURAL NETWORK MAMMOGRAM PREPROCESSING

Abstract

Breast cancer is the second leading cause of cancer deathamong women. In the United States alone more than fortythousand women die annually. Mammography is a frontlinescreening tool for the early detection of malignantmasses. This work describes the effect of reducing the bitdepth, or bits per pixel, on the output of Pulse CoupledNeural Network when preprocessing mammogram images.Index Terms  -  Computer Vision, Artificial Intelligence, Medicine, Visualization,Health, Mammography, Neural Networks, ImageProcessing.