Yao Shieh, Mengkai Shieh, Chien-Hung Chang, and Scott Goodwin
Acute Stroke, ASPECTS, Computer-assisted Decision Support System, Integrated Biomedical Image Analysis, Neuroimaging, Pattern Recognition
Non-contrast CT (NCCT) imaging plays an important role in the diagnosis and prognosis of acute stroke. Tissue plasminogen activator (tPA) is the only FDA approved treatment for ischemic strokes. . Determining whether or not to administer tPA based on NCCT within a short time frame is a challenging task.
We have developed a computer-assisted ASPECTS scoring system, built upon our previous stand-alone, automated scoring system, with added components that allow a synergistic physician-computer interpretation. Our system centers on two innovative ideas: (1) allowing doctors to make necessary interventions at critical points to achieve physicisn-computer joint decision making, and (2) visually oriented interaction that adapts to a physician’s intuitive way of information processing when reading medical images. The preliminary results are very promising.
The next step of our research is to evaluate the effect based on a large data set on scoring accuracy as well as productivity in a stroke center.