Thomas H. Helbich

BACKGROUND: Artificial intelligence (AI) systems performing at radiologist-like levels in the evaluation of digital mammography (DM) would improve breast cancer screening accuracy and efficiency. We aimed to compare the stand-alone performance of an AI system to that of radiologists in detecting breast cancer in DM. METHODS: Nine multi-reader, multi-case study datasets previously used for different research purposes in seven countries were collected. Each dataset consisted of DM exams acquired with systems from four different vendors, multiple radiologists' assessments per exam, and ground truth verified by histopathological analysis or follow-up, yielding a total of 2652 exams (653 malignant) and interpretations by 101 radiologists (28 296 independent interpretations). An AI system analyzed these exams yielding a level of suspicion of cancer present between 1 and 10. The detection performance between the radiologists and the AI system was compared using a noninferiority null hypothesis at a margin of 0.05. RESULTS: The performance of the AI system was statistically noninferior to that of the average of the 101 radiologists. The AI system had a 0.840 (95% confidence interval [CI] = 0.820 to 0.860) area under the ROC curve and the average of the radiologists was 0.814 (95% CI = 0.787 to 0.841) (difference 95% CI = -0.003 to 0.055). The AI system had an AUC higher than 61.4% of the radiologists. CONCLUSIONS: The evaluated AI system achieved a cancer detection accuracy comparable to an average breast radiologist in this retrospective setting. Although promising, the performance and impact of such a system in a screening setting needs further investigation.

UNLABELLED: This paper summarizes information about breast MRI to be provided to women and referring physicians. After listing contraindications, procedure details are described, stressing the need for correct scheduling and not moving during the examination. The structured report including BI-RADS® categories and further actions after a breast MRI examination are discussed. Breast MRI is a very sensitive modality, significantly improving screening in high-risk women. It also has a role in clinical diagnosis, problem solving, and staging, impacting on patient management. However, it is not a perfect test, and occasionally breast cancers can be missed. Therefore, clinical and other imaging findings (from mammography/ultrasound) should also be considered. Conversely, MRI may detect lesions not visible on other imaging modalities turning out to be benign (false positives). These risks should be discussed with women before a breast MRI is requested/performed. Because breast MRI drawbacks depend upon the indication for the examination, basic information for the most important breast MRI indications is presented. Seventeen notes and five frequently asked questions formulated for use as direct communication to women are provided. The text was reviewed by Europa Donna-The European Breast Cancer Coalition to ensure that it can be easily understood by women undergoing MRI. KEY POINTS: • Information on breast MRI concerns advantages/disadvantages and preparation to the examination • Claustrophobia, implantable devices, allergic predisposition, and renal function should be checked • Before menopause, scheduling on day 7-14 of the cycle is preferred • During the examination, it is highly important that the patient keeps still • Availability of prior examinations improves accuracy of breast MRI interpretation.

Breast density is an independent risk factor for the development of breast cancer and also decreases the sensitivity of mammography for screening. Consequently, women with extremely dense breasts face an increased risk of late diagnosis of breast cancer. These women are, therefore, underserved with current mammographic screening programs. The results of recent studies reporting on contrast-enhanced breast MRI as a screening method in women with extremely dense breasts provide compelling evidence that this approach can enable an important reduction in breast cancer mortality for these women and is cost-effective. Because there is now a valid option to improve breast cancer screening, the European Society of Breast Imaging (EUSOBI) recommends that women should be informed about their breast density. EUSOBI thus calls on all providers of mammography screening to share density information with the women being screened. In light of the available evidence, in women aged 50 to 70 years with extremely dense breasts, the EUSOBI now recommends offering screening breast MRI every 2 to 4 years. The EUSOBI acknowledges that it may currently not be possible to offer breast MRI immediately and everywhere and underscores that quality assurance procedures need to be established, but urges radiological societies and policymakers to act on this now. Since the wishes and values of individual women differ, in screening the principles of shared decision-making should be embraced. In particular, women should be counselled on the benefits and risks of mammography and MRI-based screening, so that they are capable of making an informed choice about their preferred screening method. KEY POINTS: • The recommendations in Figure 1 summarize the key points of the manuscript.

PURPOSE: To measure the effect of biopsy device, probe size, mammographic lesion type, lesion size, and number of samples obtained per lesion on the ductal carcinoma in situ (DCIS) underestimation rate. MATERIALS AND METHODS: Nonpalpable breast lesions at 16 institutions received a histologic diagnosis of DCIS after 14-gauge automated large-core biopsy in 373 lesions and after 14- or 11-gauge directional vacuum-assisted biopsy in 953 lesions. The presence of histopathologic invasive carcinoma was noted at subsequent surgical biopsy. RESULTS: By performing the chi(2) test, independent significant DCIS underestimation rates by biopsy device were 20.4% (76 of 373) of lesions diagnosed at large-core biopsy and 11.2% (107 of 953) of lesions diagnosed at vacuum-assisted biopsy (P <.001); by lesion type, 24.3% (35 of 144) of masses and 12.5% (148 of 1,182) of microcalcifications (P <.001); and by number of specimens per lesion, 17.5% (88 of 502) with 10 or fewer specimens and 11.5% (92 of 799) with greater than 10 (P <.02). DCIS underestimations increased with lesion size. CONCLUSION: DCIS underestimations were 1.9 times more frequent with masses than with calcifications, 1.8 times more frequent with large-core biopsy than with vacuum-assisted biopsy, and 1.5 times more frequent with 10 or fewer specimens per lesion than with more than 10 specimens per lesion.