Faculty Bibliography

The degree of normal fibroglandular tissue that enhances on breast MRI, known as background parenchymal enhancement (BPE), was initially described as an incidental finding that could affect interpretation performance. While BPE is now established to be a physiologic phenomenon that is affected by both endogenous and exogenous hormone levels, evidence supporting the notion that BPE frequently masks breast cancers is limited. However, compelling data have emerged to suggest BPE is an independent marker of breast cancer risk and breast cancer treatment outcomes. Specifically, multiple studies have shown that elevated BPE levels, measured qualitatively or quantitatively, are associated with a greater risk of developing breast cancer. Evidence also suggests that BPE could be a predictor of neoadjuvant breast cancer treatment response and overall breast cancer treatment outcomes. These discoveries come at a time when breast cancer screening and treatment have moved toward an increased emphasis on targeted and individualized approaches, of which the identification of imaging features that can predict cancer diagnosis and treatment response is an increasingly recognized component. Historically, researchers have primarily studied quantitative tumor imaging features in pursuit of clinically useful biomarkers. However, the need to segment less well-defined areas of normal tissue for quantitative BPE measurements presents its own unique challenges. Furthermore, there is no consensus on the optimal timing on dynamic contrast-enhanced MRI for BPE quantitation. This article comprehensively reviews BPE with a particular focus on its potential to increase precision approaches to breast cancer risk assessment, diagnosis, and treatment. It also describes areas of needed future research, such as the applicability of BPE to women at average risk, the biological underpinnings of BPE, and the standardization of BPE characterization. Level of Evidence: 3 Technical Efficacy Stage: 5.

Architectural distortion on digital breast tomosynthesis (

OBJECTIVE. The purpose of this study is to describe screening updates for women with average and high risk for breast cancer, compare different screening strategies, and describe new approaches in risk prediction, including radiomics. CONCLUSION. All women are at substantial risk for breast cancer. For women with average risk, annual mammography beginning at 40 years old maximizes the life-extending benefits and provides improved treatment options. Women at higher risk need earlier and more intense screening. Delaying initiation or decreasing frequency of mammographic screening adversely affects breast cancer detection.

As the proportion of women diagnosed with early stage breast cancer increases, the role of imaging for staging and surveillance purposes is considered. National and international guidelines discourage the use of staging imaging for asymptomatic patients newly diagnosed with stage 0 to II breast cancer, even if there is nodal involvement, as unnecessary imaging can delay care and affect outcomes. In asymptomatic patients with a history of stage I breast cancer that received treatment for curative intent, there is no role for imaging to screen for distant recurrences. However, routine surveillance with an annual mammogram is the only imaging test that should be performed to detect an in-breast recurrence or a new primary breast cancer in women with a history of stage I breast cancer. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision include an extensive analysis of current medical literature from peer reviewed journals and the application of well-established methodologies (RAND/UCLA Appropriateness Method and Grading of Recommendations Assessment, Development, and Evaluation or GRADE) to rate the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where evidence is lacking or equivocal, expert opinion may supplement the available evidence to recommend imaging or treatment.

Deep learning models designed for visual classification tasks on natural images have become prevalent in medical image analysis. However, medical images differ from typical natural images in many ways, such as significantly higher resolutions and smaller regions of interest. Moreover, both the global structure and local details play important roles in medical image analysis tasks. To address these unique properties of medical images, we propose a neural network that is able to classify breast cancer lesions utilizing information from both a global saliency map and multiple local patches. The proposed model outperforms the ResNet-based baseline and achieves radiologist-level performance in the interpretation of screening mammography. Although our model is trained only with image-level labels, it is able to generate pixel-level saliency maps that provide localization of possible malignant findings.

PURPOSE/OBJECTIVE:Sodium MRI has shown promise for monitoring neoadjuvant chemotherapy response in breast cancer. The purpose of this work was to build a dual-tuned bilateral proton/sodium breast coil for 7T MRI that provides sufficient SNR to enable sodium breast imaging in less than 10 minutes. METHODS:The proton/sodium coil consists of 2 shielded unilateral units: 1 for each breast. Each unit consists of 3 nested layers: (1) a 3-loop solenoid for sodium excitation, (2) a 3-loop solenoid for proton excitation and signal reception, and (3) a 4-channel receive array for sodium signal reception. Benchmark measurements were performed in phantoms with and without the sodium receive array insert. In vivo images were acquired on a healthy volunteer. RESULTS:The sodium receive array boosted 1.5 to 3 times the SNR compared with the solenoid. Proton SNR loss due to residual interaction with the sodium array was less than 10%. The coil enabled sodium imaging in vivo with 2.8-mm isotropic nominal resolution (~5-mm real resolution) in 9:36 minutes. CONCLUSION/CONCLUSIONS:The coil design that we propose addresses challenges associated with sodium's low SNR from a hardware perspective and offers the opportunity to investigate noninvasively breast tumor metabolism as a function of sodium concentration in patients undergoing neoadjuvant chemotherapy.

Although computer-aided diagnosis (CAD) is widely used in mammography, conventional CAD programs that use prompts to indicate potential cancers on the mammograms have not led to an improvement in diagnostic accuracy. Because of the advances in machine learning, especially with use of deep (multilayered) convolutional neural networks, artificial intelligence has undergone a transformation that has improved the quality of the predictions of the models. Recently, such deep learning algorithms have been applied to mammography and digital breast tomosynthesis (DBT). In this review, the authors explain how deep learning works in the context of mammography and DBT and define the important technical challenges. Subsequently, they discuss the current status and future perspectives of artificial intelligence-based clinical applications for mammography, DBT, and radiomics. Available algorithms are advanced and approach the performance of radiologists-especially for cancer detection and risk prediction at mammography. However, clinical validation is largely lacking, and it is not clear how the power of deep learning should be used to optimize practice. Further development of deep learning models is necessary for DBT, and this requires collection of larger databases. It is expected that deep learning will eventually have an important role in DBT, including the generation of synthetic images.

Background Male breast cancer incidence is rising. There may be a potential role in selective screening in men at elevated risk for breast cancer, but the effectiveness of such screening remains unexplored. Purpose To evaluate patterns of male breast imaging utilization, to determine high-risk screening outcomes, and to delineate risk factors associated with cancer diagnosis. Materials and Methods This retrospective study reviewed consecutive male breast imaging examinations over a 12-year period (between 2005-2017). Examination indications, biopsy recommendations, and pathologic results were correlated with patient characteristics. Fisher exact test, Mann-Whitney test, Spearman correlation, and logistic regression were used for statistical analysis. Results A total of 1869 men (median age, 55 years; range, 18-96 years) underwent 2052 examinations yielding 2304 breast lesions and resulting in 149 (6.5%) biopsies in 133 men; 41 (27.5%) were malignant and 108 (72.5%) were benign. There were 1781 (86.8%) diagnostic and 271 (13.2%) screening examinations. All men undergoing screening had personal or family history of breast cancer and/or genetic mutations. There was a significant increase in the number of examinations in men relative to the number of examinations in women over time (Spearman correlation, r = 0.85; P < .001). Five node-negative cancers resulted from screening mammography, yielding a cancer detection rate of 18 per 1000 examinations (95% confidence interval [CI]: 7, 41), with cancers diagnosed on average after 4 person-years of screening (range, 1-10 person-years). Mammographic screening sensitivity, specificity, and positive predictive value of biopsy were 100% (95% CI: 50%, 100%), 95.0% (95% CI: 93.1%, 98%), and 50% (95% CI: 22.2%, 77.8%). Older age (P < .001), Ashkenazi descent (P < .001), genetic mutations (P = .006), personal history (P < .001), and first-degree family history (P = .03) were associated with breast cancer. Non-first-degree family history was not associated with cancer (P = .09). Conclusion There is potential benefit in screening men at high risk for developing breast cancer. Such screening may have increased over time. © RSNA, 2019.