How Does the Perception of a Lesion Influence Visual Search Strategy in Mammogram Reading?

Abstract

Radiologists do not decide whether to report or to dismiss a perceived finding based solely on the conspicuity of the finding itself, but rather, they compare the finding with selected areas of the background. In this article, we examined how the perception of a malignant mass changed the background sampling strategy of experienced mammographers when searching mammograms for breast cancer. We determined whether these changes were different for correctly reported masses and for both visually inspected but unreported masses (ie, misses) and for lesion-free areas that were interpreted as containing a malignant mass (ie, false-positive decisions). Four experienced mammographers read a case set of 20 two-view mammograms on two trials. Fifteen cases contained one biopsy-proven malignant mass, and five cases were lesion-free. Each cancer case had two sets of images: 1) the ones in which the lesion was reported at mammography screening, and 2) the first prior mammogram. On each trial, for each cancer case, only one set of images was shown to the observer in a balanced mix of current and prior cases per trial. The complementary set was shown in the next trial. The lesion-free cases were shown in both trials. The observers' eye positions were recorded. Spatial frequency analysis was used to represent the observers' background sampling strategy, and analysis of variance and correlation analysis were used to evaluate whether there were significant differences in the background areas sampled before and after the observers' eyes hit for the first time the location of the lesion. We found statistically significant differences (analysis of variance F(1,19) = 12.812, P = .0003) in the spatial frequency representation of the background areas sampled before and after the observers' eyes first hit the location of a true malignant mass. There were no statistically significant differences in the spatial frequency representation of background areas sampled before and after the observers' eyes first hit the location of a correctly reported malignant mass, but there were significant differences when either the observer did not report the mass (a miss) or the observer reported a lesion-free area as containing a mass (a false positive). A true malignant mass that the observers correctly report may be perceived immediately after image onset, thus biasing background sampling from the start, whereas areas that yield both false-negative and false-positive decisions may only be perceived during visual examination of the parenchyma. For the false negatives, our data suggest that after fixating the location of the lesion, the observers actively tried to reconcile the perception of the lesion with its background, whereas for the false positives, which represent a "true" lesion for the observers, background sampling was clearly different before and after the location was fixated for the first time. Hence, the perception of a finding effectively biases any further analysis of the case.