Fostering Organizational Excellence through Inclusive Leadership: Practical Guide for Radiology Leaders.

Inclusive leadership styles value team members, invite diverse perspectives, and recognize and support the contributions of employees. The authors provide guidance to radiology leaders interested in developing inclusive leadership skills and competencies to improve workforce recruitment and retention and unlock the potential of a rapidly diversifying health care workforce. As health care organizations look to attract the best and brightest talent, they will be increasingly recruiting millennial and Generation Z employees, who belong to the most diverse generations in American history. Additionally, radiology departments currently face critical workforce shortages in radiologists, radiology technicians, staff, and advanced practice providers. In the context of these shortages, the costs of employee turnover have emphasized the need for radiology leaders to develop leadership behaviors that promote recruitment and retention. Radiology department leaders who perceive and treat valued employees as replaceable commodities will be forced to deal with the extremely high costs associated with recruitment and training, decreased morale, and increased burnout. The authors review inclusive versus exclusive leadership styles, describe key attributes and skills of inclusive leaders, provide radiology leaders with concrete methods to make their organizations more inclusive, and outline key steps in change management. By adopting and implementing inclusive leadership strategies, radiology groups can position themselves to succeed in rapidly diversifying health care environments. ©RSNA, 2024 See the invited commentary by Siewert in this issue.

High-Temporal/High-Spatial Resolution Breast Magnetic Resonance Imaging Improves Diagnostic Accuracy Compared With Standard Breast Magnetic Resonance Imaging in Patients With High Background Parenchymal Enhancement.

PURPOSE: To compare breast magnetic resonance imaging (MRI) diagnostic performance using a standard high-spatial resolution protocol versus a simultaneous high-temporal/high-spatial resolution (HTHS) protocol in women with high levels of background parenchymal enhancement (BPE). MATERIALS AND METHODS: We conducted a retrospective study of contrast-enhanced breast MRIs performed at our institution before and after the introduction of the HTHS protocol. We compared diagnostic performance of the HTHS and standard protocol by comparing cancer detection rate (CDR) and positive predictive value of biopsy (PPV3) among women with high BPE (ie, marked or moderate). RESULTS: Among women with high BPE, the HTHS protocol demonstrated increased CDR (23.6 per 1,000 patients v 7.9 per 1,000 patients; P = 0. 013) and increased PPV3 (16.0% v 6.3%; P = .021) compared with the standard protocol. This corresponded to a 9.8% (95% CI, 1.29 to 18.3) decrease in the proportion of unnecessary biopsies among high-BPE patients and an additional cancer yield of 15.7 per 1,000 patients (95% CI, 1.3 to 18.3). CONCLUSION: Among women with high BPE, HTHS MRI improved diagnostic performance, leading to an additional cancer yield of 15.7 cancers per 1,000 women and concomitantly decreasing unnecessary biopsies by 9.8%. A multisite prospective trial is warranted to confirm these findings and to pave the way for more widespread clinical implementation.

Artificial Intelligence Applications in Breast Imaging: Current Status and Future Directions.

Attempts to use computers to aid in the detection of breast malignancies date back more than 20 years. Despite significant interest and investment, this has historically led to minimal or no significant improvement in performance and outcomes with traditional computer-aided detection. However, recent advances in artificial intelligence and machine learning are now starting to deliver on the promise of improved performance. There are at present more than 20 FDA-approved AI applications for breast imaging, but adoption and utilization are widely variable and low overall. Breast imaging is unique and has aspects that create both opportunities and challenges for AI development and implementation. Breast cancer screening programs worldwide rely on screening mammography to reduce the morbidity and mortality of breast cancer, and many of the most exciting research projects and available AI applications focus on cancer detection for mammography. There are, however, multiple additional potential applications for AI in breast imaging, including decision support, risk assessment, breast density quantitation, workflow and triage, quality evaluation, response to neoadjuvant chemotherapy assessment, and image enhancement. In this review the current status, availability, and future directions of investigation of these applications are discussed, as well as the opportunities and barriers to more widespread utilization.

Automated Triage of Screening Breast MRI Examinations in High-Risk Women Using an Ensemble Deep Learning Model.

OBJECTIVES: The aim of the study is to develop and evaluate the performance of a deep learning (DL) model to triage breast magnetic resonance imaging (MRI) findings in high-risk patients without missing any cancers. MATERIALS AND METHODS: In this retrospective study, 16,535 consecutive contrast-enhanced MRIs performed in 8354 women from January 2013 to January 2019 were collected. From 3 New York imaging sites, 14,768 MRIs were used for the training and validation data set, and 80 randomly selected MRIs were used for a reader study test data set. From 3 New Jersey imaging sites, 1687 MRIs (1441 screening MRIs and 246 MRIs performed in recently diagnosed breast cancer patients) were used for an external validation data set. The DL model was trained to classify maximum intensity projection images as "extremely low suspicion" or "possibly suspicious." Deep learning model evaluation (workload reduction, sensitivity, specificity) was performed on the external validation data set, using a histopathology reference standard. A reader study was performed to compare DL model performance to fellowship-trained breast imaging radiologists. RESULTS: In the external validation data set, the DL model triaged 159/1441 of screening MRIs as "extremely low suspicion" without missing a single cancer, yielding a workload reduction of 11%, a specificity of 11.5%, and a sensitivity of 100%. The model correctly triaged 246/246 (100% sensitivity) of MRIs in recently diagnosed patients as "possibly suspicious." In the reader study, 2 readers classified MRIs with a specificity of 93.62% and 91.49%, respectively, and missed 0 and 1 cancer, respectively. On the other hand, the DL model classified MRIs with a specificity of 19.15% and missed 0 cancers, highlighting its potential use not as an independent reader but as a triage tool. CONCLUSIONS: Our automated DL model triages a subset of screening breast MRIs as "extremely low suspicion" without misclassifying any cancer cases. This tool may be used to reduce workload in standalone mode, to shunt low suspicion cases to designated radiologists or to the end of the workday, or to serve as base model for other downstream AI tools.

Strategies to Improve Racial and Ethnic Diversity in Breast Imaging Training and Beyond.

Diversity and inclusion in breast imaging can improve creativity and innovation, enrich the workplace environment, and enhance culturally appropriate care for an increasingly diverse patient population. Current estimates predict the racial and ethnic demographics of the United States population will change markedly by the year 2060, with increases in representation of the Black demographic projected to comprise 15% of the population (currently 13.3%) and the Hispanic/Latinx demographic projected to comprise 27.5% of the population (currently 17.8%). However, matriculation rates for those who are underrepresented in medicine (URM), defined as "racial and ethnic populations that are underrepresented in the medical profession relative to their numbers in the general population," have remained largely stagnant. Black students comprise only 7.1% of medical student matriculants, and Hispanic/Latinx students comprise only 6.2% of medical school matriculants compared to the general population. The matriculation rate of URM students into diagnostic radiology is even lower, with Black trainees comprising 3.1% of radiology residents and Hispanic/Latinx trainees comprising 4.8% of radiology residents. This lack of URM radiology resident representation leads to a lack of URM potential applicants to breast imaging fellowships due to the pipeline effect. Strategies to improve diversity and inclusion in breast imaging include recruiting a diverse breast imaging workforce, establishing robust mentorship and sponsorship programs, fostering an inclusive training and workplace environment, and retaining and promoting a diverse workforce.

Image-guided Localization Techniques for Nonpalpable Breast Lesions: An Opportunity for Multidisciplinary Patient-centered Care.

Selection of a localization method for nonpalpable breast lesions offers an opportunity for institutions to seek multidisciplinary input to promote value-based, patient-centered care. The diverse range of nonpalpable breast and axillary pathologies identified through increased utilization of screening mammography often necessitates image-guided preoperative localization for accurate lesion identification and excision. Preoperative localization techniques for breast and axillary lesions have evolved to include both wire and nonwire methods, the latter of which include radioactive seeds, radar reflectors, magnetic seeds, and radiofrequency identification tag localizers. There are no statistically significant differences in surgical outcomes when comparing wire and nonwire localization devices. Factors to consider during selection and adoption of image-guided localization systems include physician preference and ease of use, workflow efficiency, and patient satisfaction.

Educational Strategies to Achieve Equitable Breast Imaging Care.

As the population of the United States becomes increasingly diverse, radiologists must learn to both understand and mitigate the impact of health disparities. Significant health disparities persist in radiologic care, including breast imaging. Racial and ethnic minorities, women from lower socioeconomic status, those living in rural areas, and the uninsured bear a disproportionate burden of breast cancer morbidity and mortality. Currently, there is no centralized radiology curriculum focusing on breast health disparities available to residents, breast imaging fellows, or practicing breast radiologists. While patient-, provider-, and system-level initiatives are necessary to overcome disparities, our purpose is to describe educational strategies targeted to breast imaging radiologists at all levels to provide equitable care to a diverse population. These strategies may include, but are not limited to, diversifying the breast imaging workforce, understanding the needs of a diverse population, cultural sensitivity and bias training, and fostering awareness of the existing issues in screening mammography access, follow-up imaging, and clinical care.

Development of Nonbacterial Thrombotic Endocarditis While on Systemic Anticoagulation in Pancreatic Cancer: A Case Report.

Nonbacterial thromboembolic endocarditis (NBTE), or marantic endocarditis, is a rare complication associated with advanced cancer. Enoxaparin or unfractionated heparin is considered the standard treatment for NBTE. In this case report, we describe a 59-year-old female with metastatic pancreatic cancer who presented with embolic stroke and was found to have new NBTE of the mitral valve while she was receiving the therapeutic dose of enoxaparin. Of note, her recent echocardiogram one week ago was negative for mitral valve vegetations. Our case emphasized that for patients with advanced cancer presenting with stroke, the diagnosis of NBTE should be entertained even for those on systemic anticoagulation.