If you don't find it often, you often don't find it: why some cancers are missed in breast cancer screening

Abstract

Mammography is an important tool in the early detection of breast cancer. However, the perceptual task is difficult and a significant proportion of cancers are missed. Visual search experiments show that miss (false negative) errors are elevated when targets are rare (low prevalence) but it is unknown if low prevalence is a significant factor under real world, clinical conditions. Here we show that expert mammographers in a real, low-prevalence, clinical setting, miss a much higher percentage of cancers than are missed when the mammographers search for the same cancers under high prevalence conditions. We inserted 50 positive and 50 negative cases into the normal workflow of the breast cancer screening service of an urban hospital over the course of nine months. This rate was slow enough not to markedly raise disease prevalence in the radiologists' daily practice. Six radiologists subsequently reviewed all 100 cases in a session where the prevalence of disease was 50%. In the clinical setting, participants missed 30% of the cancers. In the high prevalence setting, participants missed just 12% of the same cancers. Under most circumstances, this low prevalence effect is probably adaptive. It is usually wise to be conservative about reporting events with very low base rates (Was that a flying saucer? Probably not.). However, while this response to low prevalence appears to be strongly engrained in human visual search mechanisms, it may not be as adaptive in socially important, low prevalence tasks like medical screening. While the results of any one study must be interpreted cautiously, these data are consistent with the conclusion that this behavioral response to low prevalence could be a substantial contributor to miss errors in breast cancer screening.

Figure 1. Error rates for rare targets (red bars, ∼1% prevalence) and common targets (green bars, 50% prevalence) for two types of errors, false negatives and false positives.

The dark colored bars represent data average over all 14 observers. The light red bars represent low prevalence average errors (false negatives and false positives) for the six observers who participated in both arms of the study (low and high prevalence). The light green bars represent high prevalence average errors (false negatives and false positives) restricted to the cases that the six high prevalence observers did not also see during the low prevalence arm of the study. Regardless of these filtering of the data, low prevalence, false negative errors are markedly higher than high prevalence false negative errors.

Figure 2. One of the seven cases not seen at low prevalence but seen by all 6 readers at high prevalence.

This is a case of a 56-year-old woman whose test screening mammogram was presented with a prior mammogram taken two years earlier. The case was rated level 5 of difficulty, the cancer was detected on the original screening and the lesion type is calcifications measuring 10 mm in size with the pathology of DCIS with microinvasion. The parenchymal density is less dense. a) MLO (top 2 images) and CC (bottom two images). b) Lesion in right upper quadrant. Magnification view shows pleomorphic calcifications in a segmental distribution.