SEGMENTATION OF ULTRASONIC IMAGES WITH NEURAL NETWORKS
This work was supported in part by NIH grant EY03183, the Dyson Foundation, the St. Giles Foundation, the Rudin Foundation and Research to Prevent Blindness. Computations for this project were performed in part at the Cornell National Supercomputer Facility, which is supported by the National Science Foundation, New York State, the IBM Corporation, and members of the Corporate Research Institute.
Neural networks differ from traditional approaches to image processing in terms of their ability to adapt to regularities in image structure and to self-organize so as to implement directed transformations. Biomedical ultrasonic images are often degraded in quality by noise and other factors, making enhancement techniques particularly important. This paper describes use of back propagation and competitive learning for enhancement and segmentation of ultrasonic images of the eye. Of particular interest is the extension of these techniques to segmentation of three-dimensional data sets, where simple thresholding and gradient operations are not entirely successful.
