The optimal use of computer aided detection to find low prevalence cancers

Abstract

Abstract People miss a high proportion of targets that only appear rarely. This low prevalence (LP) effect has implications for applied search tasks such as the clinical reading of mammograms. Computer aided detection (CAD) has been used to help radiologists search mammograms by highlighting areas likely to contain a cancer. Previous research has found a benefit in search when CAD cues were correct but a cost to search when CAD cues were incorrect. The current research investigated whether there is an optimal way to present CAD to ensure low error rates when CAD is both correct and incorrect. Experiment 1 compared an automatic condition, where CAD appeared simultaneously with the display to an interactive condition, where participants could choose to use CAD. Experiment 2 compared the automatic condition to a confirm condition, where participants searched the display first before being shown the CAD cues. The results showed that miss errors were reduced overall in the confirm condition, with no cost to false alarms. Furthermore, having CAD be interactive, resulted in a low uptake where it was only used in 34% of trials. The results showed that the presentation mode of CAD can affect decision-making in LP search.

Keywords

• Low prevalence
• Mammogram
• Visual search
• Computer aided detection (CAD)
• Decision-making