Speaker: Anke Meyer-Baese.
Title: Lossy Neural Compression Methods for Medical Images.
Affiliation: FAMU-FSU College of Engineering.
Date: Friday, January 25, 2002.
Place and Time: Room 101 - Love Building, 3:35-4:35 pm.
Refreshments: Room 204 - Love Building, 3:00 pm.

Abstract. The research and development of teleradiology and telemedicine systems has progressed through many technical and clinical endeavors. When dealing with large volume image transmission and storage, lossy data compression is an outstanding issue in medical applications to which current technologies were not designed to address. The goal of this talk is to present and evaluate lossy neural-based compression algorithms for digitized mammograms in the context of computer-aided diagnosis systems. The methods combine different types of neural networks based on Hebbian and/or anti-Hebbian learning with a "neural-gas" network for vector quantization.