Information Sciences in Imaging 2012 Seminar Series: June


Next Generation CAD in Mammography: Human-­-Centered Design


Existing computer-­-assisted decision (CAD) support systems in mammography are optimized to detect as many cancers as possible. Even though there has been marked improvement in the performance of the technology, the clinical effectiveness of the commerical CAD products remains one of the most heavily debated issues in breast imaging. 

I believe that a serious limitation of the existing technology is that it follows a "one-size-fits-all" approach, ignoring the radiologist's evolving reading needs and case-specific behavior. 

In this seminar I will present my group's work towards gaining better understanding of the radiologist's visual search and error-making patterns and using that knowledge to develop more effective decision support systems in mammography. Specifically, I will discuss a personalized model for a CAD system that provides decision support tailored to each radiologist's perceptual and cognitive patterns for the specific case under review.