A blackboard architecture for automating cephalometric analysis

Abstract

This paper describes a principled attempt to use artificial intelligence methodologies for interpretation of lateral skull X-ray images. Lateral skull X-ray images are routinely used in cephalometric analysis to provide quantitative measurements useful to clinical orthodontists. Manual and interactive methods of analysis are known to be error-prone, and time-consuming. Previous attempts have been made to automate this analysis, using conventional algorithmic approaches. Unfortunately such systems typically fail to capture the expertise and adaptability required to cope with the variability in biological structure and X-ray image quality found in cephalograms. The present system makes use of a blackboard architecture and multiple knowledge sources within an integrated model-based system. A data-gathering system allows models of feature appearance and location to be built from examples. Blackboard and task control modules allow specific knowledge-based modules to act on information available to the blackboard. Knowledge-based modules include location hypothesis, intelligent segmentation, and constraint propagation systems. Results from a working experimental system are given, and compare favourably with previous algorithmic solutions.