Date of Award

12-1996

Document Type

Thesis

Degree Name

Master of Science

Department

Department of Electrical and Computer Engineering

First Advisor

Steven K. Rogers, PhD

Abstract

This research develops an automated method for segmenting Magnetic Resonance (MR) brain images based on Pulse Coupled Neural Networks (PCNN). MR brain image segmentation has proven difficult, primarily due to scanning artifacts such as interscan and intrascan intensity inhomogeneities. The method developed and presented here uses a PCNN to both filter and segment MR brain images. The technique begins by preprocessing images with a PCNN filter to reduce scanning artifacts. Images are then contrast enhanced via histogram equalization. Finally, a PCNN is used to segment the images to arrive at the final result. Modifications to the original PCNN model are made that drastically improve performance while greatly reducing memory requirements. These modifications make it possible to extend the method to filter and segment three dimensionally. Volumes represented as series of images are segmented using this new method. This new three dimensional segmentation technique can be used to obtain a better segmentation of a single image or of an entire volume. Results indicate that the PCNN shows promise as an image analysis tool.

AFIT Designator

AFIT-GCS-ENG-96D-01

DTIC Accession Number

ADA323643

Download

Share

COinS