Responsive Web-based Breast Imaging Core Curriculum for International Radiology Residents with Self-Assessment: A Pilot Study.

RATIONALE AND OBJECTIVES: Lack of uniformity in radiology resident education is partially attributable to variable access to subspecialty education. Web-based courses improve standardization, but with growing emphasis on competency based education, more evaluation of their effectiveness is needed. We created a responsive web-based breast imaging curriculum for radiology residents including self-assessment and a satisfaction survey. MATERIALS AND METHODS: Two global academic institutions collaboratively developed a breast imaging curriculum to address radiology residents' educational needs. This virtual course comprised 11 video lectures, nine didactic (with attached pre-test and post-test assessments) and two case review sessions. In April 2020, this optional curriculum was made available to all 56 radiology residents in one residency program cluster in Singapore, to be accessed alongside the breast imaging rotation as a supplement. A voluntary anonymous satisfaction survey was provided upon completion. RESULTS: A total of 39 of the 56 radiology residents (70%) completed the course. For the average score of nine lectures (maximum score 5), there was a significant increase in mean pre and post - test scores (mean = 2.2, SD = 0.7), p < 0.001. The proportion of residents with improvement between the pre-test score and the post-test score ranged from 74% to 100% (mean, 84%). Thirty three of the 39 participants (85%) completed the satisfaction survey, and all agreed or strongly agreed that the curriculum increased their knowledge of breast imaging. CONCLUSION: This web based breast imaging curriculum supplement was viewed positively by participating residents and improved their self-assessed knowledge. Curriculum access could be expanded to improve global radiology education.

Bleeding Complications After Breast Core-needle Biopsy-An Approach to Managing Patients on Antithrombotic Therapy.

Image-guided core-needle breast and axillary biopsy (CNB) is the standard-of-care procedure for the diagnosis of breast cancer. Although the risks of CNB are low, the most common complications include bleeding and hematoma formation. Post-procedural bleeding is of particular concern in patients taking antithrombotic therapy, but there is currently no widely established standard protocol in the United States to guide antithrombotic therapy management. In the face of an increasing number of patients taking antithrombotic therapy and with the advent of novel classes of anticoagulants, the American College of Radiology guidelines recommend that radiologists consider cessation of antithrombotic therapy prior to CNB on a case-by-case basis. Lack of consensus results in disparate approaches to patients on antithrombotic therapy undergoing CNB. There is further heterogeneity in recommendations for cessation of antithrombotic therapy based on the modality used for image-guided biopsy, target location, number of simultaneous biopsies, and type of antithrombotic agent. A review of the available data demonstrates the safety of continuing antithrombotic therapy during CNB while highlighting additional procedural and target lesion factors that may increase the risk of bleeding. Risk stratification of patients undergoing breast interventional procedures is proposed to guide both pre-procedural decision-making and post-procedural management. Radiologists should be aware of antithrombotic agent pharmacokinetics and strategies to minimize post-procedural bleeding to safely manage patients.

Does lateral arm technique decrease the rate of clip migration in stereotactic and tomosynthesis-guided biopsies?

BACKGROUND: Mammography-guided vacuum-assisted biopsies (MGVAB) can be done with stereotaxis or digital breast tomosynthesis guidance. Both methods can be performed with a conventional (CBA) or a lateral arm biopsy approach (LABA). Marker clip migration is relatively frequent in MGVAB (up to 44%), which in cases requiring surgery carries a risk of positive margins and re-excision. We aimed to compare the rates of clip migration and hematoma formation between the CBA and LABA techniques of prone MGVAB. Our HIPAA compliant retrospective study included all consecutive prone MGVAB performed in a single institution over a 20-month period. The LABA approach was used with DBT guidance; CBA utilized DBT or stereotactic guidance. The tissue sampling techniques were otherwise identical. RESULTS: After exclusion, 389 biopsies on 356 patients were analyzed. LABA was done in 97 (25%), and CBA in 292 (75%) cases. There was no statistical difference in clip migration rate with either 1 cm or 2 cm distance cut-off [15% for CBA and 10% for LABA for 1 cm threshold (p = 0.31); 5.8% or CBA and 3.1% or LABA for 2 cm threshold (p = 0.43)]. There was no difference in the rate of hematoma formation (57.5% in CDB and 50.5% in LABA, p = 0.24). The rates of technical failure were similar for both techniques (1.7% for CBA and 3% for LABA) with a combined failure rate of 1%. CONCLUSIONS: LABA and CBA had no statistical difference in clip migration or hematoma formation rates. Both techniques had similar success rates and may be helpful in different clinical situations.

A Deep Learning Approach to Re-create Raw Full-Field Digital Mammograms for Breast Density and Texture Analysis.

PURPOSE: To develop a computational approach to re-create rarely stored for-processing (raw) digital mammograms from routinely stored for-presentation (processed) mammograms. MATERIALS AND METHODS: In this retrospective study, pairs of raw and processed mammograms collected in 884 women (mean age, 57 years ± 10 [standard deviation]; 3713 mammograms) from October 5, 2017, to August 1, 2018, were examined. Mammograms were split 3088 for training and 625 for testing. A deep learning approach based on a U-Net convolutional network and kernel regression was developed to estimate the raw images. The estimated raw images were compared with the originals by four image error and similarity metrics, breast density calculations, and 29 widely used texture features. RESULTS: In the testing dataset, the estimated raw images had small normalized mean absolute error (0.022 ± 0.015), scaled mean absolute error (0.134 ± 0.078) and mean absolute percentage error (0.115 ± 0.059), and a high structural similarity index (0.986 ± 0.007) for the breast portion compared with the original raw images. The estimated and original raw images had a strong correlation in breast density percentage (Pearson r = 0.946) and a strong agreement in breast density grade (Cohen κ = 0.875). The estimated images had satisfactory correlations with the originals in 23 texture features (Pearson r ≥ 0.503 or Spearman ρ ≥ 0.705) and were well complemented by processed images for the other six features. CONCLUSION: This deep learning approach performed well in re-creating raw mammograms with strong agreement in four image evaluation metrics, breast density, and the majority of 29 widely used texture features.Keywords: Mammography, Breast, Supervised Learning, Convolutional Neural Network (CNN), Deep learning algorithms, Machine Learning AlgorithmsSee also the commentary by Chan in this issue.Supplemental material is available for this article.©RSNA, 2021.

Breast cancer screening in women with and without implants: retrospective study comparing digital mammography to digital mammography combined with digital breast tomosynthesis.

OBJECTIVES: Compare four groups being screened: women without breast implants undergoing digital mammography (DM), women without breast implants undergoing DM with digital breast tomosynthesis (DM/DBT), women with implants undergoing DM, and women with implants undergoing DM/DBT. METHODS: Mammograms from February 2011 to March 2017 were retrospectively reviewed after 13,201 were excluded for a unilateral implant or prior breast cancer. Patients had been allowed to choose between DM and DM/DBT screening. Mammography performance metrics were compared using chi-square tests. RESULTS: Six thousand forty-one women with implants and 91,550 women without implants were included. In mammograms without implants, DM (n = 113,973) and DM/DBT (n = 61,896) yielded recall rates (RRs) of 8.53% and 6.79% (9726/113,973 and 4204/61,896, respectively, p < .001), cancer detection rates per 1000 exams (CDRs) of 3.96 and 5.12 (451/113,973 and 317/61,896, respectively, p = .003), and positive predictive values for recall (PPV1s) of 4.64% and 7.54% (451/9726 and 317/4204, respectively, p < .001), respectively. In mammograms with implants, DM (n = 6815) and DM/DBT (n = 5138) yielded RRs of 5.81% and 4.87% (396/6815 and 250/5138, respectively, p = .158), CDRs of 2.49 and 2.92 (17/6815 and 15/5138, respectively, p > 0.999), and PPV1s of 4.29% and 6.0% (17/396 and 15/250, respectively, p > 0.999), respectively. CONCLUSIONS: DM/DBT significantly improved recall rates, cancer detection rates, and positive predictive values for recall compared to DM alone in women without implants. DM/DBT performance in women with implants trended towards similar improvements, though no metric was statistically significant. KEY POINTS: • Digital mammography with tomosynthesis improved recall rates, cancer detection rates, and positive predictive values for recall compared to digital mammography alone for women without implants. • Digital mammography with tomosynthesis trended towards improving recall rates, cancer detection rates, and positive predictive values for recall compared to digital mammography alone for women with implants, but these trends were not statistically significant - likely related to sample size.

Retrospective statistical analysis on the diagnostic value of ductography based on lesion pathology in patients presenting with nipple discharge.

PURPOSE: To compare sensitivities and specificities of ductography to noninvasive imaging studies in determining the cause of nipple discharge and assess the value of ductography on the basis of pathologic results. METHODS: In this retrospective review of women with nipple discharge who underwent ductography between January 1, 2005 and October 30, 2015, at our institution, we compared ductography with noninvasive imaging results (mammography, ultrasound, MRI) to determine its relative diagnostic sensitivity, specificity, and relative accuracy. Diagnosis was defined from pathology results, clinical notes, and minimum of 1-year follow-up monitoring. The primary endpoints include accuracy, sensitivity, specificity, positive predictive value, and negative predictive value. The analyses were carried out in different configurations to compare results by the following pathologic categories: cancer, high-risk lesion, intraductal papilloma (IP) without atypia, and benign pathology and/or normal imaging results. RESULTS: In patients with breast cancer, ductography and noninvasive breast imaging had similar sensitivities. In patients with a high-risk lesion, ductography was significantly more sensitive than noninvasive imaging modalities. In patients with intraductal papilloma without atypia, ductography was more sensitive than noninvasive imaging, but the difference was of only borderline significance. For women with benign pathology and/or normal imaging, noninvasive imaging showed a significantly higher specificity than ductography. CONCLUSION: In the absence of standard diagnostic algorithm for patients presenting with nipple discharge, the clinician has numerous options to choose a diagnostic approach that will yield the most accurate information with the least disruption to the patient. Our results indicate the value of ductography compared to value of noninvasive imaging modalities when cancer is suspected and when high risk lesion is suspected. While we show the sensitivity of ductography is similar to noninvasive imaging modalities in the setting of cancer, the sensitivity of ductography is statistically valuable for diagnosing high-risk lesions. Our hope is that this study will emphasize more research and more understanding in clinical utility and management of high-risk lesions, leading to patient-focused algorithm for diagnosing the etiology of abnormal nipple discharge.