Share Email Print

Proceedings Paper

Neural network based segmentation system
Author(s): Kelby K. Chan; Alek S. Hayrapetian; Christina C. Lau; Robert B. Lufkin
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A neural network is used to segment double echo MR images. Images are acquired using an interleaved acquisition protocol that results in registered proton density and T2 weighted images. For each tissue class, a user selects approximately 15 - 20 points representative of the double echo signature of that tissue. This set of intensities and tissue classes are used as a pattern-target set for training a feed forward neural network using back propagation. The trained network is then used to classify all of the points in the dataset. Statistical testing of the network using pattern-target pairs distinct from those used in training showed roughly 90% correct classification for the selected tissues. The bulk of the error was due to ambiguities in classifying based solely on MR intensities. The resultant classified images can be further processed using special software that allows manual correction and interactive 2D or 3D connectivity analysis based on selection of seed points.

Paper Details

Date Published: 14 September 1993
PDF: 5 pages
Proc. SPIE 1898, Medical Imaging 1993: Image Processing, (14 September 1993); doi: 10.1117/12.154548
Show Author Affiliations
Kelby K. Chan, UCLA School of Medicine (United States)
Alek S. Hayrapetian, UCLA School of Medicine (United States)
Christina C. Lau, UCLA School of Medicine (United States)
Robert B. Lufkin, UCLA School of Medicine (United States)

Published in SPIE Proceedings Vol. 1898:
Medical Imaging 1993: Image Processing
Murray H. Loew, Editor(s)

© SPIE. Terms of Use
Back to Top