Search

PURPOSE To assess diagnostic performance of digital breast tomosynthesis (DBT) alone or combined with technologist-performed handheld screening ultrasound (US) in women with dense breasts. METHODS In an institutional review board–approved, Health Insurance Portability and Accountability Act–compliant multicenter protocol in western Pennsylvania, 6,179 women consented to three rounds of annual screening, interpreted by two radiologist observers, and had appropriate follow-up. Primary analysis was based on first observer results. RESULTS Mean participant age was 54.8 years (range, 40-75 years). Across 17,552 screens, there were 126 cancer events in 125 women (7.2/1,000; 95% CI, 5.9 to 8.4). In year 1, DBT-alone cancer yield was 5.0/1,000, and of DBT+US, 6.3/1,000, difference 1.3/1,000 (95% CI, 0.3 to 2.1; P = .005). In years 2 + 3, DBT cancer yield was 4.9/1,000, and of DBT+US, 5.9/1,000, difference 1.0/1,000 (95% CI, 0.4 to 1.5; P < .001). False-positive rate increased from 7.0% for DBT in year 1 to 11.5% for DBT+US and from 5.9% for DBT in year 2 + 3 to 9.7% for DBT+US ( P < .001 for both). Nine cancers were seen only by double reading DBT and one by double reading US. Ten interval cancers (0.6/1,000 [95% CI, 0.2 to 0.9]) were identified. Despite reduction in specificity, addition of US improved receiver operating characteristic curves, with area under receiver operating characteristic curve increasing from 0.83 for DBT alone to 0.92 for DBT+US in year 1 ( P = .01), with smaller improvements in subsequent years. Of 6,179 women, across all 3 years, 172/6,179 (2.8%) unique women had a false-positive biopsy because of DBT as did another 230/6,179 (3.7%) women because of US ( P < .001). CONCLUSION Overall added cancer detection rate of US screening after DBT was modest at 19/17,552 (1.1/1,000; CI, 0.5- to 1.6) screens but potentially overcomes substantial increases in false-positive recalls and benign biopsies.

ObjectiveEvaluate lesion visibility and radiologist confidence during contrast-enhanced mammography (CEM)-guided biopsy.MethodsWomen with BI-RADS ≥4A enhancing breast lesions were prospectively recruited for 9-g vacuum-assisted CEM-guided biopsy. Breast density, background parenchymal enhancement (BPE), lesion characteristics (enhancement and conspicuity), radiologist confidence (scale 1–5), and acquisition times were collected. Signal intensities in specimens were analyzed. Patient surveys were collected.ResultsA cohort of 28 women aged 40–81 years (average 57) had 28 enhancing lesions (7/28, 25% malignant). Breast tissue was scattered (10/28, 36%) or heterogeneously dense (18/28, 64%) with minimal (12/28, 43%), mild (7/28, 25%), or moderate (9/28, 32%) BPE on CEM. Twelve non-mass enhancements, 11 masses, 3 architectural distortions, and 2 calcification groups demonstrated weak (12/28, 43%), moderate (14/28, 50%), or strong (2/28, 7%) enhancement. Specimen radiography demonstrated lesion enhancement in 27/28 (96%). Radiologists reported complete lesion removal on specimen radiography in 8/28 (29%). Average time from contrast injection to specimen radiography was 18 minutes (SD = 5) and, to post-procedure mammogram (PPM), 34 minutes (SD = 10). Contrast-enhanced mammography PPM was performed in 27/28 cases; 13/19 (68%) of incompletely removed lesions on specimen radiography showed residual enhancement; 6/19 (32%) did not. Across all time points, average confidence was 2.2 (SD = 1.2). Signal intensities of enhancing lesions were similar to iodine. Patients had an overall positive assessment.ConclusionLesion enhancement persisted through PPM and was visible on low energy specimen radiography, with an average “confident” score. Contrast-enhanced mammography-guided breast biopsy is easily implemented clinically. Its availability will encourage adoption of CEM.

Objective To assess effectiveness of a web-based educational intervention on women’s health care provider knowledge of breast cancer risk models and high-risk screening recommendations. Methods A web-based pre- and post-test study including 177 U.S.-based women’s health care providers was conducted in 2019. Knowledge gaps were defined as fewer than 75% of respondents answering correctly. Pre- and post-test knowledge differences (McNemar test) and associations of baseline characteristics with pre-test knowledge gaps (logistic regression) were evaluated. Results Respondents included 131/177 (74.0%) physicians; 127/177 (71.8%) practiced obstetrics/gynecology. Pre-test, 118/177 (66.7%) knew the Gail model predicts lifetime invasive breast cancer risk; this knowledge gap persisted post-test [(121/177, 68.4%); P = 0.77]. Just 39.0% (69/177) knew the Gail model identifies women eligible for risk-reducing medications; this knowledge gap resolved. Only 48.6% (86/177) knew the Gail model should not be used to identify women meeting high-risk MRI screening guidelines; this deficiency decreased to 66.1% (117/177) post-test (P = 0.001). Pre-test, 47.5% (84/177) knew the Tyrer-Cuzick model is used to identify women meeting high-risk screening MRI criteria, 42.9% (76/177) to predict BRCA1/2 pathogenic mutation risk, and 26.0% (46/177) to predict lifetime invasive breast cancer risk. These knowledge gaps persisted but improved. For a high-risk 30-year-old, 67.8% (120/177) and 54.2% (96/177) pre-test knew screening MRI and mammography/tomosynthesis are recommended, respectively; 19.2% (34/177) knew both are recommended; and 53% (94/177) knew US is not recommended. These knowledge gaps resolved or reduced. Conclusion Web-based education can reduce important provider knowledge gaps about breast cancer risk models and high-risk screening recommendations.

Pseudoangiomatous stromal hyperplasia (PASH) is a benign mesenchymal proliferative lesion of the breast. PASH is postulated to be hormonally induced and predominantly occurs in premenopausal women and postmenopausal women on menopausal hormone therapy. Clinical presentation varies from screen-detected lesions to palpable masses. Imaging findings of PASH are nonspecific. The most common mammographic findings are an oval or round circumscribed non-calcified mass or developing asymmetry. On US, PASH is often seen as an oval hypoechoic mass that may be circumscribed and can have an echogenic rim, or, when manifest as mammographic asymmetry, US may show a corresponding non-mass focal area of echogenic tissue. Limited studies have investigated the MRI appearance, with PASH most often manifesting as non-mass enhancement, or, less often, as an oval or irregular mass with persistent kinetics. Histopathologically, PASH can be mistaken for a fibroadenoma or phyllodes tumor and has features overlapping low-grade angiosarcoma. Assessment of radiologic-pathologic concordance is particularly important as PASH is often an incidental finding, adjacent to the targeted lesion at histopathology. Surgical excision or repeat core-needle biopsy is necessary for discordant suspicious cases. After a benign, concordant diagnosis of PASH, the patient may resume routine screening.

The continually increasing demands placed on physicians have led to high levels of burnout, and breast radiologists are no exception. Professional coaching is a means to guide and support the radiologist through a process of positive thinking, stress reduction, goal setting, mental growth, work-life balance, and behavioral change. Professional coaching may be effective in preparation for leadership roles or in response to workplace issues or conflict. The radiologist, with the help of a coach, establishes goals, expands perception and mindset, and collaboratively may find ways to resolve issues by taking new and different approaches. This article discusses why radiologists should seek out a certified coach and what a coach can offer radiologists during these trying times, as well as outlining the coaching process. Coaching has proven useful in addressing professional growth, workplace issues, and physician burnout. At the conclusion of the article, the readers will be able to discern whether coaching can support a better quality of life for them.

Diabetic fibrous mastopathy (DFM) is a rare benign fibrotic disease of the breast that develops in patients with longstanding and often uncontrolled diabetes mellitus. Clinically, patients may present with an irregular, firm, palpable mass, which may be solitary or multiple, occurring in one or both breasts. Diabetic fibrous mastopathy occurs most often in premenopausal women with heterogeneously or extremely dense breasts; mammography may show focal asymmetry or, less often, a noncalcified mass with indistinct or obscured margins, but there are usually no discrete findings. On US, DFM may have marked hypoechogenicity and posterior shadowing secondary to extensive fibrosis. Diabetic fibrous mastopathy features on contrast-enhanced MRI are also nonspecific, with gradual persistent nonmass enhancement reported. Because the clinical presentation and US features of DFM overlap with those of breast cancer, histopathologic correlation is needed to confirm diagnosis and exclude malignancy. These findings include collagenous stroma often with keloidal features and chronic perilobular and perivascular inflammation. Histopathologic findings of lymphocytic lobulitis and perivascular inflammation are common to other autoimmune conditions.

Thirty-eight states and the District of Columbia (DC) have dense breast notification (DBN) laws that mandate varying levels of patient notification about breast density after a mammogram, and these cover over 90% of American women. On March 10, 2023, the Food and Drug Administration issued a final rule amending regulations under the Mammography Quality Standards Act for a national dense breast reporting standard for both patient results letters and mammogram reports. Effective September 10, 2024, letters will be required to tell a woman her breasts are “dense” or “not dense,” that dense tissue makes it harder to find cancers on a mammogram and also increases the risk of developing cancer. Women with dense breasts will also be told that other imaging tests in addition to a mammogram may help find cancers. The specific density category can be maintained (e.g. if mandated by state “inform” law) or added. Reports to providers must include the BI-RADS density category. Implementing appropriate supplemental screening should be based on patient risk for missed breast cancer on mammography; such an assessment should include consideration of breast density and other risk factors. This article discusses strategies for implementation. Currently 15 states plus DC have varying individual state insurance laws for supplemental breast imaging; in addition, Oklahoma requires coverage for diagnostic breast imaging. A federal insurance bill, the Find It Early Act, has been introduced which would ensure no-cost screening and diagnostic imaging for women with dense breasts or at increased risk and close loopholes in state laws.

Nipple adenomas (NAs) are benign neoplasms composed of papillary hyperplasia of the epithelium of the major lactiferous ducts. Patients with NA may report bloody nipple discharge and clinically may resemble Paget disease, raising concern for malignancy. Mammographically, NAs are often occult. US can show a hypervascular circumscribed mass centered within the nipple with varying echogenicity. Diagnosis is usually made on punch biopsy or excision, but breast radiologists should be aware of this entity. Malignancy can be found elsewhere in the ipsilateral or contralateral breast, or very rarely may directly extend to involve an NA, but published experience with concurrent malignancies is small. We describe the radiologic-pathologic correlation of NAs.

US is widely used in breast imaging for diagnostic purposes and is also used increasingly for supplemental screening in women with dense breasts. US frequently depicts masses that are occult on mammography, even after tomosynthesis, and the vast majority of such masses are benign. Many masses seen only on screening US are easily recognized as benign simple cysts. Probably benign, BI-RADS 3, or low suspicion, BI-RADS 4A masses are also common and often prompt short-interval follow-up or biopsy, respectively, yet the vast majority of these are benign. This review details appropriate characterization, classification, and new approaches to the management of probably benign masses seen on screening US that can reduce false positives and, thereby, reduce costs and patient anxiety.

Granular cell tumor (GCT) is an uncommon neoplasm arising from perineural Schwann cells that can arise anywhere in the body and is particularly rare in the breast. Imaging typically shows an irregular, noncalcified mass with high density on mammography and intense posterior shadowing on US that mimics malignancy. Benign GCTs can be locally aggressive and invade the skin or chest wall. Core biopsy is necessary for diagnosis. Polygonal- to spindle-shaped cells with prominent cytoplasmic eosinophilic granules show S-100 and CD68 staining on immunohistochemistry and lack cytokeratin, estrogen, or progesterone expression. The vast majority of GCTs are benign, albeit locally infiltrative, tumors cured by wide local excision.

Background Breast Imaging Reporting and Data System (BI-RADS) category 3 (BR3) (probably benign) mammographic assessments are reserved for imaging findings known to have likelihood of malignancy of 2% or less. Purpose To determine the effect of age, finding type, and prior mammography on cancer yield for BR3 findings in the National Mammography Database (NMD). Materials and Methods This HIPAA-compliant retrospective cohort institutional review board-exempt study evaluated women recalled from screening mammography followed by BR3 assessment at diagnostic evaluation from January 2009 to March 2018 and from 471 NMD facilities. Only the first BR3 occurrence was included for women with biopsy or imaging follow-up of at least 2 years. Women with a history of breast cancer or who underwent biopsy at time of initial BR3 assessment were excluded. Women were stratified by age in 10-year intervals. Cancer yield was calculated for each age group, with (for presumed new findings) and without prior mammographic comparison, and by lesion type, where available. Linear regression with weighted-age binning was performed to assess for differences between groups

Objective For breast US interpretation, to assess impact of computer-aided diagnosis (CADx) in original mode or with improved sensitivity or specificity. Methods In this IRB approved protocol, orthogonal-paired US images of 319 lesions identified on screening, including 88 (27.6%) cancers (median 7 mm, range 1–34 mm), were reviewed by 9 breast imaging radiologists. Each observer provided BI-RADS assessments (2, 3, 4A, 4B, 4C, 5) before and after CADx in a mode-balanced design: mode 1, original CADx (outputs benign, probably benign, suspicious, or malignant); mode 2, artificially-high-sensitivity CADx (benign or malignant); and mode 3, artificially-high-specificity CADx (benign or malignant). Area under the receiver operating characteristic curve (AUC) was estimated under each modality and for standalone CADx outputs. Multi-reader analysis accounted for inter-reader variability and correlation between same-lesion assessments. Results AUC of standalone CADx was 0.77 (95% CI: 0.72–0.83). For mode 1, average reader AUC was 0.82 (range 0.76–0.84) without CADx and not significantly changed with CADx. In high-sensitivity mode, all observers’ AUCs increased: average AUC 0.83 (range 0.78–0.86) before CADx increased to 0.88 (range 0.84–0.90), P < 0.001. In high-specificity mode, all observers’ AUCs increased: average AUC 0.82 (range 0.76–0.84) before CADx increased to 0.89 (range 0.87–0.92), P < 0.0001. Radiologists responded more frequently to malignant CADx cues in high-specificity mode (42.7% vs 23.2% mode 1, and 27.0% mode 2, P = 0.008). Conclusion Original CADx did not substantially impact radiologists’ interpretations. Radiologists showed improved performance and were more responsive when CADx produced fewer false-positive malignant cues.

Objective Using terms adapted from the BI-RADS Mammography and MRI lexicons, we trained radiologists to interpret contrast-enhanced mammography (CEM) and assessed reliability of their description and assessment. Methods A 60-minute presentation on CEM and terminology was reviewed independently by 21 breast imaging radiologist observers. For 21 CEM exams with 31 marked findings, observers recorded background parenchymal enhancement (BPE) (minimal, mild, moderate, marked), lesion type (oval/round or irregular mass, or non-mass enhancement), intensity of enhancement (none, weak, medium, strong), enhancement quality (none, homogeneous, heterogeneous, rim), and BI-RADS assessment category (2, 3, 4A, 4B, 4C, 5). “Expert” consensus of 3 other radiologists experienced in CEM was developed. Kappa statistic was used to assess agreement between radiologists and expert consensus, and between radiologists themselves, on imaging feature categories and final assessments. Reproducibility of specific feature descriptors was assessed as fraction of consensus-concordant responses. Results Radiologists demonstrated moderate agreement for BPE, (mean kappa, 0.43; range, 0.05–0.69), and lowest reproducibility for “minimal.” Agreement was substantial for lesion type (mean kappa, 0.70; range, 0.47–0.93), moderate for intensity of enhancement (mean kappa, 0.57; range, 0.44–0.76), and moderate for enhancement quality (mean kappa, 0.59; range, 0.20–0.78). Agreement on final assessment was fair (mean kappa, 0.26; range, 0.09–0.44), with BI-RADS category 3 the least reproducible. Decision to biopsy (BI-RADS 2–3 vs 4–5) showed moderate agreement with consensus (mean kappa, 0.54; range, −0.06–0.87). Conclusion With minimal training, agreement for description of CEM findings by breast imaging radiologists was comparable to other BI-RADS lexicons.

Screening mammography reduces breast cancer mortality; however, when used to examine women with dense breasts, its performance and resulting benefits are reduced. Increased breast density is an independent risk factor for breast cancer. Digital breast tomosynthesis (DBT), ultrasound (US), molecular breast imaging (MBI), MRI, and contrast-enhanced mammography (CEM) each have shown improved cancer detection in dense breasts when compared with 2D digital mammography (DM). DBT is the preferred mammographic technique for producing a simultaneous reduction in recalls (i.e., additional imaging). US further increases cancer detection after DM or DBT and reduces interval cancers (cancers detected in the interval between recommended screening examinations), but it also produces substantial additional false-positive findings. MBI improves cancer detection with an effective radiation dose that is approximately fourfold that of DM or DBT but is still within accepted limits. MRI provides the greatest increase in cancer detection and reduces interval cancers and late-stage disease; abbreviated techniques will reduce cost and improve availability. CEM appears to offer performance similar to that of MRI, but further validation is needed. Dense breast notification will soon be a national standard; therefore, understanding the performance of mammography and supplemental modalities is necessary to optimize screening for women with dense breasts.

Screening mammography reduces breast cancer mortality; however, when used to examine women with dense breasts, its performance and resulting benefits are reduced. Increased breast density is an independent risk factor for breast cancer. Digital breast tomosynthesis (DBT), ultrasound (US), molecular breast imaging (MBI), MRI, and contrast-enhanced mammography (CEM) each have shown improved cancer detection in dense breasts when compared with 2D digital mammography (DM). DBT is the preferred mammographic technique for producing a simultaneous reduction in recalls (i.e., additional imaging). US further increases cancer detection after DM or DBT and reduces interval cancers (cancers detected in the interval between recommended screening examinations), but it also produces substantial additional false-positive findings. MBI improves cancer detection with an effective radiation dose that is approximately fourfold that of DM or DBT but is still within accepted limits. MRI provides the greatest increase in cancer detection and reduces interval cancers and late-stage disease; abbreviated techniques will reduce cost and improve availability. CEM appears to offer performance similar to that of MRI, but further validation is needed. Dense breast notification will soon be a national standard; therefore, understanding the performance of mammography and supplemental modalities is necessary to optimize screening for women with dense breasts.

Encapsulated papillary carcinoma (EPC) is a rare, clinically indolent breast malignancy most common in postmenopausal women. Absence of myoepithelial cells at the periphery is a characteristic feature. Mammographically, EPC typically presents as a mostly circumscribed, noncalcified, dense mass that can have focally indistinct margins when there is associated frank invasive carcinoma. Ultrasound shows a circumscribed solid or complex cystic and solid mass, and occasional hemorrhage in the cystic component may produce a fluid-debris level; the solid components typically show intense washout enhancement on MRI. Color Doppler may demonstrate a prominent vascular pedicle and blood flow within solid papillary fronds. Encapsulated papillary carcinoma can exist in pure form; however, EPC is often associated with conventional ductal carcinoma in-situ and/or invasive ductal carcinoma, no special type. Adjacent in-situ and invasive disease may be only focally present at the periphery of EPC and potentially unsampled at core-needle biopsy. In order to facilitate diagnosis, the mass wall should be included on core-needle biopsy, which will show absence of myoepithelial markers. Staging and prognosis are determined by any associated frankly invasive component, with usually excellent long-term survival and rare distant metastases.

Objective We sought to identify provider knowledge gaps and their predictors, as revealed by a breast density continuing education course marketed to the radiology community. Methods The course, continually available online during the study period of November 2, 2016 and December 31, 2018, includes demographics collection; a monograph on breast density, breast cancer risk, and screening; and a post-test. Four post-test questions were modified during the study period, resulting in different sample sizes pre- and postmodification. Multiple logistic regression was used to identify predictors of knowledge gaps (defined as > 25% of responses incorrect). Results Of 1649 analyzable registrants, 1363 (82.7%) were radiologic technologists, 226 (13.7%) were physicians, and 60 (3.6%) were other nonphysicians; over 90% of physicians and over 90% of technologists/nonphysicians specialized in radiology. Sixteen of 49 physicians (32.7%) and 80/233 (34.3%) technologists/nonphysicians mistakenly thought the Gail model should be used to determine “high-risk” status for recommending MRI or genetic testing. Ninety-nine of 226 (43.8%) physicians and 682/1423 (47.9%) technologists/nonphysicians misunderstood the inverse relationship between increasing age and lifetime breast cancer risk. Fifty-two of 166 (31.3%) physicians and 549/1151 (47.7%) technologists/nonphysicians were unaware that MRI should be recommended for women with a family history of BRCA1/BRCA2 mutations. Tomosynthesis effectiveness was overestimated, with 18/60 (30.0%) physicians and 95/272 (34.9%) technologists/nonphysicians believing sensitivity nearly equaled MRI. Knowledge gaps were more common in technologists/nonphysicians. Conclusions Important knowledge gaps about breast density, breast cancer risk assessment, and screening exist among radiologic technologists and radiologists. Continued education efforts may improve appropriate breast cancer screening recommendations.

Objective To assess prospectively the interpretative performance of automated breast ultrasound (ABUS) as a supplemental screening after digital breast tomosynthesis (DBT) or as a standalone screening of women with dense breast tissue. Methods Under an IRB-approved protocol (written consent required), women with dense breasts prospectively underwent concurrent baseline DBT and ABUS screening. Examinations were independently evaluated, in opposite order, by two of seven Mammography Quality Standards Act–qualified radiologists, with the primary radiologist arbitrating disagreements and making clinical management recommendations. We report results for 1111 screening examinations (598 first year and 513 second year) for which all diagnostic workups are complete. Imaging was also retrospectively reviewed for all cancers. Statistical assessments used a 0.05 significance level and accounted for correlation between participants’ examinations. Results Of 1111 women screened, primary radiologists initially “recalled” based on DBT alone (6.6%, 73/1111, CI: 5.2%–8.2%), of which 20 were biopsied, yielding 6/8 total cancers. Automated breast ultrasound increased recalls overall to 14.4% (160/1111, CI: 12.4%–16.6%), with 27 total biopsies, yielding 1 additional cancer. Double reading of DBT alone increased the recall rate to 10.7% (119/1111), with 21 biopsies, with no improvement in cancer detection. Double reading ABUS increased the recall rate to 15.2% (169/1111, CI: 13.2%–17.5%) of women, of whom 22 were biopsied, yielding the detection of 7 cancers, including one seen only on double reading ABUS. Inter-radiologist agreement was similar for recall recommendations from DBT (κ = 0.24, CI: 0.14–0.34) and ABUS (κ = 0.23, CI: 0.15–0.32). Integrated assessments from both readers resulted in a recall rate of 15.1% (168/1111, CI: 13.1%–17.4%). Conclusion Supplemental or standalone ABUS screening detected cancers not seen on DBT, but substantially increased noncancer recall rates.

Background Staging newly diagnosed breast cancer by using dynamic contrast material-enhanced MRI is limited by access, high cost, and false-positive findings. The utility of contrast-enhanced mammography (CEM) and 99mTc sestamibi-based molecular breast imaging (MBI) in this setting is largely unknown. Purpose To compare extent-of-disease assessments by using MRI, CEM, and MBI versus pathology in women with breast cancer. Materials and Methods In this HIPAA-compliant prospective study, women with biopsy-proven breast cancer underwent MRI, CEM, and MBI between October 2014 and April 2018. Eight radiologists independently interpreted each examination result prospectively and were blinded to interpretations of findings with the other modalities. Visibility of index malignancies, lesion size, and additional suspicious lesions (malignant or benign) were compared during pathology review. Accuracy of index lesion sizing and detection of additional lesions in women without neoadjuvant chemotherapy were compared. Results A total of 102 women were enrolled and 99 completed the study protocol (mean age, 51 years ± 11 [standard deviation]; range, 32-77 years). Lumpectomy or mastectomy was performed in 71 women (79 index malignancies) without neoadjuvant chemotherapy and in 28 women (31 index malignancies) with neoadjuvant chemotherapy. Of the 110 index malignancies, MRI, CEM, and MBI depicted 102 (93%; 95% confidence interval [CI]: 86%, 97%), 100 (91%; 95% CI: 84%, 96%), and 101 (92%; 95% CI: 85%, 96%) malignancies, respectively. In patients without neoadjuvant chemotherapy, pathologic size of index malignancies was overestimated with all modalities (P = .02). MRI led to overestimation of 24% (17 of 72) of malignancies by more than 1.5 cm compared with 11% (eight of 70) with CEM and 15% (11 of 72) with MBI. MRI depicted more (P = .007) nonindex lesions, with sensitivity similar to that of CEM or MBI, resulting in lower positive predictive value of additional biopsies (13 of 46 [28%; 95% CI: 17%, 44%] for MRI; 14 of 27 [52%; 95% CI: 32%, 71%] for CEM; and 11 of 25 [44%; 95% CI: 24%, 65%] for MBI (overall P = .01). Conclusion Contrast-enhanced mammography, molecular breast imaging, and MRI showed similar detection of all malignancies. MRI depicted more nonindex suspicious benign lesions than did contrast-enhanced mammography or molecular breast imaging, leading to lower positive predictive value of additional biopsies. All three modalities led to overestimation of index tumor size, particularly MRI. © RSNA, 2019 Online supplemental material is available for this article.

PURPOSE: To investigate two deep learning-based modeling schemes for predicting short-term risk of developing breast cancer using prior normal screening digital mammograms in a case-control setting. METHODS: We conducted a retrospective Institutional Review Board-approved study on a case-control cohort of 226 patients (including 113 women diagnosed with breast cancer and 113 controls) who underwent general population breast cancer screening. For each patient, a prior normal (i.e., with negative or benign findings) digital mammogram examination (including mediolateral oblique [MLO] view and craniocaudal [CC] view two images) was collected. Thus, a total of 452 normal images (226 MLO view images and 226 CC view images) of this case-control cohort were analyzed to predict the outcome, i.e., developing breast cancer (cancer cases) or remaining breast cancer-free (controls) within the follow-up period. We implemented an end-to-end deep learning model and a GoogLeNet-LDA model and compared their effects in several experimental settings using two mammographic view images and inputting two different sub-regions of the images to the models. The proposed models were also compared to logistic regression modeling of mammographic breast density. Area under the receiver operating characteristic curve (AUC) was used as the model performance metric. RESULTS: The highest AUC was 0.73 (95% Confidence Interval [CI]: 0.68 – 0.78; GoogLeNet-LDA model on CC view) when using the whole-breast and was 0.72 (95% CI: 0.67– 0.76; GoogLeNet-LDA model on MLO+CC view) when using the dense tissue, respectively, as the model input. The GoogleNet-LDA model significantly (all p

In women with dense breasts (heterogeneously or extremely dense), adding screening ultrasound to mammography increases detection of node-negative invasive breast cancer. Similar incremental cancer detection rates averaging 2.1–2.7 per 1000 have been observed for physician- and technologist-performed handheld ultrasound (HHUS) and automated ultrasound (AUS). Adding screening ultrasound (US) for women with dense breasts significantly reduces interval cancer rates. Training is critical before interpreting examinations for both modalities, and a learning curve to achieve optimal performance has been observed. On average, about 3% of women will be recommended for biopsy on the prevalence round because of screening US, with a wide range of 2%–30% malignancy rates for suspicious findings seen only on US. Breast Imaging Reporting and Data System 3 lesions identified only on screening HHUS can be safely followed at 1 year rather than 6 months. Computer-aided detection and diagnosis software can augment performance of AUS and HHUS; ongoing research on machine learning and deep learning algorithms will likely improve outcomes and workflow with screening US.

Data on utilization rate and cancer yield of BI-RADS® category 3 in routine clinical practice in diagnostic mammography are sparse. The aim of this study was to determine utilization rate and cancer yield of BI-RADS 3 in diagnostic mammography in the ACR National Mammography Database (NMD).Retrospective analysis of NMD mammograms from January 1, 2009, to June 30, 2018, was performed. BI-RADS 3 utilization rate in diagnostic setting was calculated and stratified by patient, facility, and examination-level variables. Patient-level cancer yield was calculated among women with BI-RADS 3 assessment and adequate follow-up (imaging follow-up ≥24 months or biopsy). Logistic regression was performed to assess the odds of utilization of BI-RADS 3, with respect to facility, examination, and patient variables, and the odds of malignancy among patients with probably benign findings. Chi-square and t tests were used to determine significance (P.05).Data from 19,443,866 mammograms from 500 NMD facilities across 31 states were analyzed, of which 3,039,952 were diagnostic mammograms. Utilization rate of BI-RADS 3 was 15.5% (470,155 of 3,039,952) in the diagnostic setting. There was a statistically significant difference in BI-RADS 3 utilization rate across all collected variables (P.001). Patient-level cancer yield at 2-year follow-up was 0.91% (2,009 of 220,672; 95% confidence interval [CI], 0.87%-0.95%) in the diagnostic setting. Patient and examination variables associated with significantly higher likelihood of malignancy included calcifications (odds ratio, 4.27; 95% CI, 2.43-7.51), patient age70 years (odds ratio, 3.77; 95% CI, 2.49-5.7), and presence of prior comparisons (odds ratio, 1.23; 95% CI, 1.07-1.42).In the NMD, BI-RADS 3 assessment was common in diagnostic mammography (15.5%), with an overall cancer yield of 0.91%, less than the benchmark of 2%. Utilization trends in diagnostic mammography warrant further research for optimization of use.

OBJECTIVES We sought to assess the effect of an educational intervention, based on DenseBreast-info.org website content, on women's healthcare provider knowledge of breast density, its risk and screening implications, and comfort level discussing these topics with patients. METHODS US-based women's healthcare providers participated in a web-based pretest/posttest study from May 14, 2019 to September 30, 2019. Pretest included demographics; comfort/knowledge discussing breast density impact on risk and screening; and educational material. Posttest contained the same knowledge and comfort questions. We assessed mean pretest/posttest score and comfort level differences (paired t tests) and pretest/posttest knowledge gap differences (McNemar test). We evaluated associations of baseline characteristics with pretest score and score improvement using multiple linear regression, and associations with knowledge gaps using logistic regression. RESULTS Of 177 providers analyzed, 74.0% (131/177) were physicians and 71.8% (127/177) practiced obstetrics/gynecology. Average test score increased from 40.9% (5.7/14) responses correct pretest to 72.1% (10.1/14) posttest (P

Purpose: False positives in digital mammography screening lead to high recall rates, resulting in unnecessary medical procedures to patients and health care costs. This study aimed to investigate the revolutionary deep learning methods to distinguish recalled but benign mammography images from negative exams and those with malignancy. Experimental Design: Deep learning convolutional neural network (CNN) models were constructed to classify mammography images into malignant (breast cancer), negative (breast cancer free), and recalled-benign categories. A total of 14,860 images of 3,715 patients from two independent mammography datasets: Full-Field Digital Mammography Dataset (FFDM) and a digitized film dataset, Digital Dataset of Screening Mammography (DDSM), were used in various settings for training and testing the CNN models. The ROC curve was generated and the AUC was calculated as a metric of the classification accuracy. Results: Training and testing using only the FFDM dataset resulted in AUC ranging from 0.70 to 0.81. When the DDSM dataset was used, AUC ranged from 0.77 to 0.96. When datasets were combined for training and testing, AUC ranged from 0.76 to 0.91. When pretrained on a large nonmedical dataset and DDSM, the models showed consistent improvements in AUC ranging from 0.02 to 0.05 (all P > 0.05), compared with pretraining only on the nonmedical dataset. Conclusions: This study demonstrates that automatic deep learning CNN methods can identify nuanced mammographic imaging features to distinguish recalled-benign images from malignant and negative cases, which may lead to a computerized clinical toolkit to help reduce false recalls.

Screening mammography reduces breast cancer mortality; however, when used to examine women with dense breasts, its performance and resulting benefits are reduced. Increased breast density is an independent risk factor for breast cancer. Digital breast tomosynthesis (DBT), ultrasound (US), molecular breast imaging (MBI), MRI, and contrast-enhanced mammography (CEM) each have shown improved cancer detection in dense breasts when compared with 2D digital mammography (DM). DBT is the preferred mammographic technique for producing a simultaneous reduction in recalls (i.e., additional imaging). US further increases cancer detection after DM or DBT and reduces interval cancers (cancers detected in the interval between recommended screening examinations), but it also produces substantial additional false-positive findings. MBI improves cancer detection with an effective radiation dose that is approximately fourfold that of DM or DBT but is still within accepted limits. MRI provides the greatest increase in cancer detection and reduces interval cancers and late-stage disease; abbreviated techniques will reduce cost and improve availability. CEM appears to offer performance similar to that of MRI, but further validation is needed. Dense breast notification will soon be a national standard; therefore, understanding the performance of mammography and supplemental modalities is necessary to optimize screening for women with dense breasts.

Background The literature supports the use of short-interval follow-up as an alternative to biopsy for lesions assessed as probably benign, Breast Imaging Reporting and Data System (BI-RADS) category 3, with an expected malignancy rate of less than 2%. Purpose To assess outcomes from 6-, 12-, and 24-month follow-up of probably benign findings first identified at recall from screening mammography in the National Mammography Database (NMD). Materials and Methods This retrospective study included women recalled from screening mammography with BI-RADS category 3 assessment at additional evaluation from January 2009 through March 2018 from 471 NMD facilities. Only the first BI-RADS category 3 occurrence for women aged 25 years or older with no personal history of breast cancer was analyzed, with biopsy or 2-year imaging follow-up. Cancer yield and positive predictive value of biopsies performed (PPV3) were determined at each follow-up. Results Among 45 202 women (median age, 55 years; range, 25-90 years) with a BI-RADS category 3 lesion, 1574 (3.5%) underwent biopsy at the time of lesion detection, yielding 72 cancers (cancer yield, 4.6%; 72 of 1574 women). For the remaining 43 628 women who accepted surveillance, 922 were seen within 90 days (with 78 lesions biopsied and 12 [15%] classified as malignant). The women still in surveillance (31 465 of 43 381 women [72.5%]) underwent follow-up mammography at 6 months. Of 3001 (9.5%) lesions biopsied, 456 (15.2%) were malignant (cancer yield, 1.5%; 456 of 31 465 women; 95% confidence interval [CI]: 1.3%, 1.6%). Among 18 748 of 25 997 women (72.1%) in surveillance who underwent follow-up at 12 months, 1219 (6.5%) underwent biopsy with 230 (18.9%) malignant lesions found (cancer yield, 1.2%; 230 of 18 748 women; 95% CI: 1.1%, 1.4%). Through 2-year follow-up, the biopsy rate was 11.2% (4894 of 43 628 women) with a cancer yield of 1.86% (810 malignancies found among 43 628 women; 95% CI: 1.73%, 1.98%) and a PPV3 of 16.6% (810 malignancies found among 4894 women). Conclusion In the National Mammography Database, Breast Imaging Reporting and Data System (BI-RADS) category 3 use is appropriate, with 1.86% cumulative cancer yield through 2-year follow-up. Of 810 malignancies, 468 (57.8%) were diagnosed at or before 6 months, validating necessity of short-interval follow-up of mammographic BI-RADS category 3 findings. © RSNA, 2020

Artificial intelligence (AI) algorithms, especially deep learning methods have proven to be successful in many medical imaging applications. Computerized breast cancer image analysis can improve diagnosis accuracy. Digital Breast Tomosynthesis (DBT) imaging is a new modality and more advantageous compared to classical digital mammography (DM). Therefore, development of new deep learning algorithms compatible with DBT modality are potent to improve DBT imaging reading time efficiency and increase accuracy for breast cancer diagnosis when used as additional tool for radiologists. In this work, we aimed to build a 3D deep learning model to distinguish malignancy and benign breasts using DBT images. We also investigated effects of different loss functions in our deep learning models. We implemented and evaluated our method on a large data set of 546 patients (205 malignancy and 341 benign). Our results showed that different loss functions lead to an influence on the models performance in our classification tasks, and specific loss function may be selected or customized to adjust a specific performance metric for concrete applications.

Background Clustered microcysts are common, especially in perimenopausal women, and are seen in up to 6% of US examinations. However, there are limited published data on appropriate assessment and management recommendations for clustered microcysts on breast US images. Purpose To determine outcomes of lesions identified as clustered microcysts on breast US images to help guide appropriate management recommendations. Materials and Methods Lesions classified as clustered microcysts at breast US were retrospectively identified in women at two hospitals (a large tertiary care academic hospital and a National Comprehensive Cancer Network-designated comprehensive cancer center) within one metropolitan health system from 2005 through 2015. If US-guided tissue sampling was performed, results were obtained from the pathology or cytology reports. If sampling was not performed, only lesions with at least 24 months of imaging follow-up or any imaging follow-up with interval resolution or decrease in size were included in the study. Data were evaluated using standard statistics, Fisher exact tests, and Wilcoxon rank sum tests. Results A total of 189 women (median age, 52 years [interquartile range, 46-59 years]) with 196 lesions classified as clustered microcysts on US images were included in this study. During the surveillance period of at least 24 months and at tissue diagnosis, malignancy was not found in any of the 196 lesions (0%) (95% confidence interval: 0.0%, 1.9%). A total of 158 of 196 (80%) lesions were followed with imaging, and 38 of 196 (20%) lesions underwent percutaneous sampling. During the follow-up period, 28 of 158 (18%) lesions spontaneously resolved, 13 of 158 (8%) decreased in size, and one of 158 lesions (0.6%) increased at 18-month follow-up but then became stable. One hundred sixteen of 158 lesions (73%) demonstrated no change at follow-up imaging, 38 of 196 (19%) lesions underwent percutaneous sampling, and 38 of 38 (100%) revealed benign results. Conclusion No malignancies were identified in this series. These results further support the existing literature that lesions characterized as clustered microcysts demonstrate a very low risk of malignancy and can be classified as benign. Biopsy may be safely avoided. © RSNA, 2020 See also the editorial by Berg in this issue.

Purpose To determine rate of malignancy at stereotactic biopsy of amorphous calcifications with different distributions using current imaging, clinical, and histopathologic criteria. Materials and Methods From January 2009 to September 2013, this retrospective study reviewed a large set of stereotactic biopsies to identify amorphous calcifications and their clinical, imaging, and histopathologic characteristics. Calcification distribution was correlated with malignancy rate after adjusting for known risk factors using logistic regression. Results Of 1903 sequential biopsies, 546 (28.7%) were for amorphous calcifications. After excluding atypical lesions not excised and patients with more than one biopsy in the same year, 497 lesions from 494 women (median age, 52 years; age range, 30-81 years) remained. Fifty-two (10.5%; 95% confidence interval [CI]: 7.9, 13.5) lesions proved malignant, with 17 of 52 (42.7%) being invasive cancers (median, 0.3 cm; range, 0.1-1.3 cm) and all 17 of them being estrogen and progesterone receptor positive and node negative. Malignancy rates in a segmental (six of 21 [28.6%]), linear (eight of 32 [25.0%]), or multiple group same quadrant (nine of 36 [25.0%]) distribution were significantly higher than malignancy rate in a solitary group of amorphous calcifications (25 of 356 [7.0%]) (P = .004, P = .003, and P = .002, respectively). Of 356 grouped amorphous calcifications, 102 (28.7%) yielded atypical results prompting excision, with three of 102 (2.9%) upgraded to ductal carcinoma in situ at excision. In women younger than 50 years without a personal history of cancer, grouped amorphous calcifications showed four of 127 (3.1%) (95% CI: 0.9, 7.9) were malignant and 39 of 127 (30.7%) were atypical at final histopathology. Conclusion Biopsy of amorphous calcifications remains necessary, with an overall malignancy rate of 10.5%; only 17 of 497 (3.4%) biopsies showed invasive cancer, and all of these were estrogen and progesterone receptor positive. Grouped amorphous calcifications in women younger than 50 years without history of breast or ovarian cancer showed a low malignancy rate of 3.1% (four of 127).

Purpose In low- to middle-income countries (LMICs), most breast cancers present as palpable lumps; however, most palpable lumps are benign. We have developed artificial intelligence–based computer-assisted diagnosis (CADx) for an existing low-cost portable ultrasound system to triage which lumps need further evaluation and which are clearly benign. This pilot study was conducted to demonstrate that this approach can be successfully used by minimally trained health care workers in an LMIC country. Patients and Methods We recruited and trained three nonradiologist health care workers to participate in an institutional review board–approved, Health Insurance Portability and Accountability Act–compliant pilot study in Jalisco, Mexico, to determine whether they could use portable ultrasound (GE Vscan Dual Probe) to acquire images of palpable breast lumps of adequate quality for accurate computer analysis. Images from 32 women with 32 breast masses were then analyzed with a triage-CADx system, generating an output of benign or suspicious (biopsy recommended). Triage-CADx outputs were compared with radiologist readings. Results The nonradiologists were able to acquire adequate images. Triage by the CADx software was as accurate as assessment by specialist radiologists, with two (100%) of two cancers considered suspicious and 30 (100%) of 30 benign lesions classified as benign. Conclusion A portable ultrasound system with CADx software can be successfully used by first-level health care workers to triage palpable breast lumps. These results open up the possibility of implementing practical, cost-effective triage of palpable breast lumps, ensuring that scarce resources can be dedicated to suspicious lesions requiring further workup.