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.
Highlights
Visual search is an important part of our everyday life, whether it is searching for a mobile phone in a living room, a child in a playground, or car in a car park
The experiment investigated whether cancer detection was improved when participants could choose to interact with Computer aided detection (CAD) compared to when CAD was presented automatically alongside the mammogram
They were affected by CAD cue
Summary
Visual search is an important part of our everyday life, whether it is searching for a mobile phone in a living room, a child in a playground, or car in a car park. A baggage screener searching through x-rays for a prohibited item or radiologists searching through mammograms for a cancer. These latter searches are made all the more difficult given that the targets only appear rarely (e.g. cancers typically appear in fewer than 1% of cases, Gur et al, 2003) and that search for a low prevalence item leads to a large proportion of miss errors (Wolfe et al, 2005). Given the importance of finding a rare mass in radiology and the serious implications of missing a cancer, it is critical to find ways to help detection of a low prevalence target. One method to help with this is computer aided detection
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have