The Thallium Diagnostic Workstation is an AIM application deployed at the USAF School of Aerospace Medicine. TDW learns to diagnose thallium myocardial scintigraphy from a training set of examples. Digitized images are acquired by a gamma camera and send to TDW via ethernet. TDW performs considerable low-level vision processing, then extracts features of diagnostic significance using template-based techniques. The physician can view the images and TDW's findings simultaneously on-screen.
TDW uses induction to learn diagnostic rules. A rule learned from 150 cases diagnosed by cardiac catheter outperforms the best human diagnostician at the school by a few percentage points. Users can view imagery, enter their own findings and diagnosis, select a rule from a catalogue of rule sets (each rule is accompanied by performance statistics), and perform automated diagnosis.