Faculty Bibliography

Implementation of artificial intelligence (AI) applications into clinical practice requires AI-savvy radiologists to ensure the safe, ethical, and effective use of these systems for patient care. Increasing demand for AI education reflects recognition of the translation of AI applications from research to clinical practice, with positive trainee attitudes regarding the influence of AI on radiology. However, barriers to AI education, such as limited access to resources, predispose to insufficient preparation for the effective use of AI in practice. In response, national organizations have sponsored formal and self-directed learning courses to provide introductory content on imaging informatics and AI. Foundational courses, such as the National Imaging Informatics Course "“ Radiology and the Radiological Society of North America Imaging AI Certificate, lay a framework for trainees to explore the creation, deployment, and critical evaluation of AI applications. This report includes additional resources for formal programming courses, video series from leading organizations, and blogs from AI and informatics communities. Furthermore, the scope of "AI and radiology education" includes AI-augmented radiology education, with emphasis on the potential for "precision education" that cre-ates personalized experiences for trainees by accounting for varying learning styles and inconsistent, possibly deficient, clinical case volume.

Purpose: There are insufficient large-scale studies comparing the performance of screening mammography in women of different races. This study aims to compare the screening performance metrics across racial and age groups in the National Mammography Database (NMD). Methods: All screening mammograms performed between January 1, 2008, and December 31, 2021, in women aged 30"“100 years from 746 mammography facilities in 46 U.S. states in the NMD were included. Patients were stratified by 10-year age intervals and 5 racial groups (African American, American Indian, Asian, White, unknown). Incidence of risk factors (breast density, personal history, family history of breast cancer, age), and time since prior exams were compared. Five screening mammography metrics were calculated: recall rate (RR), cancer detection rate (CDR), positive predictive values for recalls (PPV1), biopsy recommended (PPV2) and biopsy performed (PPV3). Results: 29,479,655 screening mammograms performed in 13,181,241 women between January 1, 2008, and December 31, 2021, from the NMD were analyzed. The overall mean performance metrics were RR 10.00% (95% CI 9.99"“10.02), CDR 4.18/1000 (4.16"“4.21), PPV1 4.18% (4.16"“4.20), PPV2 25.84% (25.72"“25.97), PPV3 25.78% (25.66"“25.91). With advancing age, RR significantly decreases, while CDR, PPV1, PPV2, and PPV3 significantly increase. Incidence of personal/family history of breast cancer, breast density, age, prior mammogram availability, and time since prior mammogram were mostly similar across all races. Compared to White women, African American women had significantly higher RR, but lower CDR, PPV1, PPV2 and PPV3. Conclusions: Benefits of screening mammography increase with age, including for women age > 70 and across all races. Screening mammography is effective; with lower RR and higher CDR, PPV2, and PPV3 with advancing age. African American women have poorer outcomes from screening mammography (higher RR and lower CDR), compared to White and all women in the NMD. Racial disparity can be partly explained by higher rate of African American women lost to follow up.

The use of digital breast tomosynthesis (DBT) in breast cancer screening has become widely accepted, facilitating increased cancer detection and lower recall rates compared with those achieved by using full-field digital mammography (DM). However, the use of DBT, as compared with DM, raises new challenges, including a larger number of acquired images and thus longer interpretation times. While most current artificial intelligence (AI) applications are developed for DM, there are multiple potential opportunities for AI to augment the benefits of DBT. During the diagnostic steps of lesion detection, characterization, and classification, AI algorithms may not only assist in the detection of indeterminate or suspicious findings but also aid in predicting the likelihood of malignancy for a particular lesion. During image acquisition and processing, AI algorithms may help reduce radiation dose and improve lesion conspicuity on synthetic two-dimensional DM images. The use of AI algorithms may also improve workflow efficiency and decrease the radiologist's interpretation time. There has been significant growth in research that applies AI to DBT, with several algorithms approved by the U.S. Food and Drug Administration for clinical implementation. Further development of AI models for DBT has the potential to lead to improved practice efficiency and ultimately improved patient health outcomes of breast cancer screening and diagnostic evaluation. See the invited commentary by Bahl in this issue. ^©RSNA, 2022.

Given that 20% to 40% of women who have percutaneous breast biopsy subsequently undergo breast surgery, knowledge of imaging women with a history of benign (including high-risk) disease or breast cancer is important. For women who had surgery for nonmalignant pathology, the surveillance recommendations are determined by their overall risk. Higher-than-average risk women with a history of benign surgery may require screening mammography starting at an earlier age before 40 and may benefit from screening MRI. For women with breast cancer who have undergone initial excision and have positive margins, imaging with diagnostic mammography or MRI can sometimes guide additional surgical planning. Women who have completed breast conservation therapy for cancer should get annual mammography and may benefit from the addition of MRI or ultrasound to their surveillance regimen. The ACR Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances in which peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.

The type of nipple discharge dictates the appropriate imaging study. Physiologic nipple discharge is common and does not require diagnostic imaging. Pathologic nipple discharge in women, men, and transgender patients necessitates breast imaging. Evidence-based guidelines were used to evaluate breast imaging modalities for appropriateness based on patient age and gender. For an adult female or male 40 years of age or greater, mammography or digital breast tomosynthesis (DBT) is performed initially. Breast ultrasound is usually performed at the same time with rare exception. For males or females 30 to 39 years of age, mammography/DBT or breast ultrasound is performed based on institutional preference and individual patient considerations. For young women less than 30 years of age, ultrasound is performed first with mammography/DBT added if there are suspicious findings or if the patient is at elevated lifetime risk for developing breast cancer. There is a high incidence of breast cancer in males with pathologic discharge. Men 25 years and older should be evaluated using mammography/DBT and ultrasound added when indicted. In transfeminine (male-to-female) patients, mammography/DBT and ultrasound are useful due to the increased incidence of breast cancer. The ACR Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer-reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances in which peer-reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) has a high sensitivity in detecting breast cancer but often leads to unnecessary biopsies and patient workup. We used a deep learning (DL) system to improve the overall accuracy of breast cancer diagnosis and personalize management of patients undergoing DCE-MRI. On the internal test set (n = 3936 exams), our system achieved an area under the receiver operating characteristic curve (AUROC) of 0.92 (95% CI: 0.92 to 0.93). In a retrospective reader study, there was no statistically significant difference (P = 0.19) between five board-certified breast radiologists and the DL system (mean ΔAUROC, +0.04 in favor of the DL system). Radiologists' performance improved when their predictions were averaged with DL's predictions [mean ΔAUPRC (area under the precision-recall curve), +0.07]. We demonstrated the generalizability of the DL system using multiple datasets from Poland and the United States. An additional reader study on a Polish dataset showed that the DL system was as robust to distribution shift as radiologists. In subgroup analysis, we observed consistent results across different cancer subtypes and patient demographics. Using decision curve analysis, we showed that the DL system can reduce unnecessary biopsies in the range of clinically relevant risk thresholds. This would lead to avoiding biopsies yielding benign results in up to 20% of all patients with BI-RADS category 4 lesions. Last, we performed an error analysis, investigating situations where DL predictions were mostly incorrect. This exploratory work creates a foundation for deployment and prospective analysis of DL-based models for breast MRI.