Potential contribution of computer-aided detection to the sensitivity of screening mammography.

PURPOSE: To determine the false-negative rate in screening mammography, the capability of computer-aided detection (CAD) to identify these missed lesions, and whether or not CAD increases the radiologists' recall rate. MATERIALS AND METHODS: All available screening mammograms that led to the detection of biopsy-proved cancer (n = 1,083) and the most recent corresponding prior mammograms (n = 427) were collected from 13 facilities. Panels of radiologists evaluated the retrospectively visible prior mammograms by means of blinded review. All mammograms were analyzed by a CAD system that marks features associated with cancer. The recall rates of 14 radiologists were prospectively measured before and after installation of the CAD system. RESULTS: At retrospective review, 67% (286 of 427) of screening mammography-detected breast cancers were visible on the prior mammograms. At independent, blinded review by panels of radiologists, 27% (115 of 427) were interpreted as warranting recall on the basis of a statistical evaluation index; and the CAD system correctly marked 77% (89 of 115) of these cases. The original attending radiologists' sensitivity was 79% (427 of [427 + 115]). There was no statistically significant increase in the radiologists' recall rate when comparing the values before (8.3%) with those after (7.6%) installation of the CAD system. CONCLUSION: The original attending radiologists had a false-negative rate of 21% (115 of [427 + 115]). CAD prompting could have potentially helped reduce this false-negative rate by 77% (89 of 115) without an increase in the recall rate.

Standardized abnormal interpretation and cancer detection ratios to assess reading volume and reader performance in a breast screening program.

PURPOSE: To determine the relationship between annual screening volume and radiologist performance in the Screening Mammography Program of British Columbia, Canada. MATERIALS AND METHODS: Standardized abnormal interpretation ratios and standardized cancer detection ratios were constructed for 35 readers with at least 3 years of experience with the Screening Mammography Program of British Columbia. The ratios were used to compare individual reader performance with the mean program performance after adjustment for the age and screening history (first versus subsequent screening examinations) of the women who underwent screening. RESULTS: The mean standardized abnormal interpretation ratio was better for readers of 2,000-2,999 (n = 8) and 3,000-3,999 (n = 9) screening mammograms per year than for those of less than 2,000 (n = 9) and 4, 000-5,199 (n = 9) screening mammograms per year. Differences in the mean standardized abnormal interpretation ratios were significant (P <.05) between the readers of less than 2,000 and of 2,000-2,999 screening mammograms per year, between readers of less than 2,000 and of 3,000-3,999 screening mammograms per year and between readers of 3,000-3,999 and of 4,000-5,199 screening mammograms per year. The mean standardized cancer detection ratio improved gradually with increasing annual volume, but the differences between groups were not statistically significant. Five of the eight readers of 2,000-2, 999 mammograms were reading 2,475 or more screening mammograms per year. CONCLUSION: Standardized abnormal interpretation ratios and standardized cancer detection ratios provide a method of comparing two important performance measures in a screening program. A minimum of 2,500 interpretations per year is associated with lower abnormal interpretation rates and average or better cancer detection rates.