The Thallium Diagnostic Workstation: Learning to Diagnose Heart Imagery from Examples

Rin Saunders

The thallium diagnostic workstation (tdw) is an integrated workstation for the learning and application of diagnostic rules for thallium heart imagery. tdw learns diagnostic rules from training sets of images, using a symbolic induction algorithm developed specifically for this application. tdw uses machine vision to identify image features of diagnostic significance (findings), which are described to the physician in a write-up. The physician can perform automated diagnosis by applying a rule set to the findings, selected from tdw’s catalog of learned rules. The physician can also view imagery, record his(her) own findings, and enter a diagnosis. tdw informs the physician of its concurrence or nonconcurrence with the physician’s diagnosis.


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.