A TECHNIQUE FOR ANATOMIC FEATURE EXTRACTION AND
TRACKING ON SEQUENTIAL DIGITAL X-RAY IMAGES
Sean Curry
Vexcel Corporation
Boulder, Colorado USA
J.M. Anderson
University of California
Berkeley, California USA
ABSTRACT
The Craniofacial Research Instrumentation Laboratory at the
University of California, San Francisco, has for a number of
years been developing instrumentation and software packages
for the acquisition and display of biostereometric data.
Stereo photographs and x-rays of the head are used to
analyse growth and treatment effects during orthodontic
treatment and orthognathic surgery. Recent efforts have been
directed towards automating anatomic feature location and
tracking on series of time-separated cranial x-rays.
Two tests were performed to evaluate the potential
accuracies that could be achieved in feature tracking. In
both tests, a series of cranial x-rays was converted to
digital images using a CID camera connected to a frame
grabber and a small computer. The first test series
consisted of a single x-ray image which was translated and
rotated three times. The second series of images consisted
of three actual cranial x-rays of a single subject, acquired
over a period of approximately two years.
A number of anatomic features, such as incisor edges and
apexes of teeth, were manually selected on the first image
of each series. The features were then automatically tracked
on subsequent digital images, and their locations compared
to those derived from direct manual digitizing of the
original film images.
1. INTRODUCTION
There are many potential applications of image processing in
photogrammetry. However, because of the complex nature of
the problems involved in pattern recognition, image
understanding, and scene analysis, progress towards
completely automated vision systems in photogrammetry has
been slow.
There are applications where the problems can be well
defined, and specific image analysis solutions applied.
Rosenfeld states that, from a practical standpoint,
successful applications of image analysis are likely to be
of a focussed nature, where a 'specialist' system has been
tailored to a specific domain, making use of methods
designed especially for that domain /5/
"0163 -