Constance D. Lehman

New evidence on breast Magnetic Resonance Imaging (MRI) screening has become available since the American Cancer Society (ACS) last issued guidelines for the early detection of breast cancer in 2003. A guideline panel has reviewed this evidence and developed new recommendations for women at different defined levels of risk. Screening MRI is recommended for women with an approximately 20-25% or greater lifetime risk of breast cancer, including women with a strong family history of breast or ovarian cancer and women who were treated for Hodgkin disease. There are several risk subgroups for which the available data are insufficient to recommend for or against screening, including women with a personal history of breast cancer, carcinoma in situ, atypical hyperplasia, and extremely dense breasts on mammography. Diagnostic uses of MRI were not considered to be within the scope of this review.

BACKGROUND: Even after careful clinical and mammographic evaluation, cancer is found in the contralateral breast in up to 10% of women who have received treatment for unilateral breast cancer. We conducted a study to determine whether magnetic resonance imaging (MRI) could improve on clinical breast examination and mammography in detecting contralateral breast cancer soon after the initial diagnosis of unilateral breast cancer. METHODS: A total of 969 women with a recent diagnosis of unilateral breast cancer and no abnormalities on mammographic and clinical examination of the contralateral breast underwent breast MRI. The diagnosis of MRI-detected cancer was confirmed by means of biopsy within 12 months after study entry. The absence of breast cancer was determined by means of biopsy, the absence of positive findings on repeat imaging and clinical examination, or both at 1 year of follow-up. RESULTS: MRI detected clinically and mammographically occult breast cancer in the contralateral breast in 30 of 969 women who were enrolled in the study (3.1%). The sensitivity of MRI in the contralateral breast was 91%, and the specificity was 88%. The negative predictive value of MRI was 99%. A biopsy was performed on the basis of a positive MRI finding in 121 of the 969 women (12.5%), 30 of whom had specimens that were positive for cancer (24.8%); 18 of the 30 specimens were positive for invasive cancer. The mean diameter of the invasive tumors detected was 10.9 mm. The additional number of cancers detected was not influenced by breast density, menopausal status, or the histologic features of the primary tumor. CONCLUSIONS: MRI can detect cancer in the contralateral breast that is missed by mammography and clinical examination at the time of the initial breast-cancer diagnosis. (ClinicalTrials.gov number, NCT00058058 [ClinicalTrials.gov].).

Background Mammographic density improves the accuracy of breast cancer risk models. However, the use of breast density is limited by subjective assessment, variation across radiologists, and restricted data. A mammography-based deep learning (DL) model may provide more accurate risk prediction. Purpose To develop a mammography-based DL breast cancer risk model that is more accurate than established clinical breast cancer risk models. Materials and Methods This retrospective study included 88 994 consecutive screening mammograms in 39 571 women between January 1, 2009, and December 31, 2012. For each patient, all examinations were assigned to either training, validation, or test sets, resulting in 71 689, 8554, and 8751 examinations, respectively. Cancer outcomes were obtained through linkage to a regional tumor registry. By using risk factor information from patient questionnaires and electronic medical records review, three models were developed to assess breast cancer risk within 5 years: a risk-factor-based logistic regression model (RF-LR) that used traditional risk factors, a DL model (image-only DL) that used mammograms alone, and a hybrid DL model that used both traditional risk factors and mammograms. Comparisons were made to an established breast cancer risk model that included breast density (Tyrer-Cuzick model, version 8 [TC]). Model performance was compared by using areas under the receiver operating characteristic curve (AUCs) with DeLong test (P < .05). Results The test set included 3937 women, aged 56.20 years ± 10.04. Hybrid DL and image-only DL showed AUCs of 0.70 (95% confidence interval [CI]: 0.66, 0.75) and 0.68 (95% CI: 0.64, 0.73), respectively. RF-LR and TC showed AUCs of 0.67 (95% CI: 0.62, 0.72) and 0.62 (95% CI: 0.57, 0.66), respectively. Hybrid DL showed a significantly higher AUC (0.70) than TC (0.62; P < .001) and RF-LR (0.67; P = .01). Conclusion Deep learning models that use full-field mammograms yield substantially improved risk discrimination compared with the Tyrer-Cuzick (version 8) model. © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Sitek and Wolfe in this issue.

IMPORTANCE: After the US Food and Drug Administration (FDA) approved computer-aided detection (CAD) for mammography in 1998, and the Centers for Medicare and Medicaid Services (CMS) provided increased payment in 2002, CAD technology disseminated rapidly. Despite sparse evidence that CAD improves accuracy of mammographic interpretations and costs over $400 million a year, CAD is currently used for most screening mammograms in the United States. OBJECTIVE: To measure performance of digital screening mammography with and without CAD in US community practice. DESIGN, SETTING, AND PARTICIPANTS: We compared the accuracy of digital screening mammography interpreted with (n = 495 818) vs without (n = 129 807) CAD from 2003 through 2009 in 323 973 women. Mammograms were interpreted by 271 radiologists from 66 facilities in the Breast Cancer Surveillance Consortium. Linkage with tumor registries identified 3159 breast cancers in 323 973 women within 1 year of the screening. MAIN OUTCOMES AND MEASURES: Mammography performance (sensitivity, specificity, and screen-detected and interval cancers per 1000 women) was modeled using logistic regression with radiologist-specific random effects to account for correlation among examinations interpreted by the same radiologist, adjusting for patient age, race/ethnicity, time since prior mammogram, examination year, and registry. Conditional logistic regression was used to compare performance among 107 radiologists who interpreted mammograms both with and without CAD. RESULTS: Screening performance was not improved with CAD on any metric assessed. Mammography sensitivity was 85.3% (95% CI, 83.6%-86.9%) with and 87.3% (95% CI, 84.5%-89.7%) without CAD. Specificity was 91.6% (95% CI, 91.0%-92.2%) with and 91.4% (95% CI, 90.6%-92.0%) without CAD. There was no difference in cancer detection rate (4.1 in 1000 women screened with and without CAD). Computer-aided detection did not improve intraradiologist performance. Sensitivity was significantly decreased for mammograms interpreted with vs without CAD in the subset of radiologists who interpreted both with and without CAD (odds ratio, 0.53; 95% CI, 0.29-0.97). CONCLUSIONS AND RELEVANCE: Computer-aided detection does not improve diagnostic accuracy of mammography. These results suggest that insurers pay more for CAD with no established benefit to women.

RSNA, 2016 Online supplemental material is available for this article.