A rare case of giant cell tumor of the anterior rib presenting as a breast mass.

Initial diagnostic ultrasound of a 22-year-old female patient presenting with a palpable breast mass revealed a suspicious mass initially thought to arise from the breast. However, follow-up diagnostic mammography was normal without evidence of the 5 cm mass seen on ultrasound, and pathology results from ultrasound-guided core needle biopsy raised suspicion for giant cell tumor, making chest wall origin of the mass more likely. Further CT and MRI imaging indeed revealed a locally invasive mass arising from the anterior fifth rib. The patient was treated with denosumab to decrease tumor burden before surgery, and subsequently underwent successful surgical resection of the tumor with mesh overlay and flap reconstruction of the chest wall defect. This case highlights the importance of keeping chest wall lesions in the differential for lesions presenting clinically as breast lesions. Despite the rarity of giant cell tumor of the anterior rib and its unusual presentation as a breast mass, appropriate diagnostic imaging work-up allowed for successful diagnosis and treatment in this case.

Ultrasound-based comparative analysis and nomogram development for predicting triple-negative and non-triple-negative breast cancer: a 4-year institutional study in Quanzhou First Hospital.

OBJECTIVE: The objective of this study was to compare ultrasound features and establish a predictive nomogram for distinguishing between triple-negative breast cancer (TNBC) and non-TNBC. DESIGN: A retrospective cohort study. SETTING: This study was conducted at Quanzhou First Hospital, a grade A tertiary hospital in Quanzhou, China, with the research data set covering the period from September 2019 to August 2023. PARTICIPANTS: The study included a total of 205 female patients with confirmed TNBC and 574 female patients with non-TNBC, who were randomly divided into a training set and a validation set at a ratio of 7:3. MAIN OUTCOME MEASURES: All patients underwent ultrasound examination and received a confirmatory pathological diagnosis. Nodules were classified according to the Breast Imaging-Reporting and Data System standard. Subsequently, the study conducted a comparative analysis of clinical characteristics and ultrasonic features. RESULTS: A statistically significant difference was observed in multiple clinical and ultrasonic features between TNBC and non-TNBC. Specifically, in the logistic regression analysis conducted on the training set, indicators such as posterior echo, lesion size, presence of clinical symptoms, margin characteristics, internal blood flow signals, halo and microcalcification were found to be statistically significant (p<0.05). These significant indicators were then effectively incorporated into a static and dynamic nomogram model, demonstrating high predictive performance in distinguishing TNBC from non-TNBC. CONCLUSION: The results of our study demonstrated that ultrasound features can be valuable in distinguishing between TNBC and non-TNBC. The presence of posterior echo, size, clinical symptoms, margin, internal flow, halo and microcalcification was identified as predictive factors for this differentiation. Microcalcification, hyperechoic halo, internal flow and clinical symptoms emerged as the strongest predictive factors, indicating their potential as reliable indicators for identifying TNBC and non-TNBC.

Molecular Breast Imaging Biopsy with a Dual-Detector System.

Purpose To develop a molecular breast imaging (MBI)-guided biopsy system using dual-detector MBI and to perform initial testing in participants. Materials and Methods The Stereo Navigator MBI Accessory biopsy system comprises a lower detector, upper fenestrated compression paddle, and upper detector. The upper detector retracts, allowing craniocaudal, oblique, or medial or lateral biopsy approaches. The compression paddle allows insertion of a needle guide and needle. Lesion depth is calculated by triangulation of lesion location on the upper detector at 0° and 15° and relative lesion activity on upper and lower detectors. In a prospective study (July 2022-June 2023), participants with Breast Imaging Reporting and Data System category 2, 3, 4, or 5 breast lesions underwent MBI-guided biopsy. After injection of 740 MBq technetium 99m sestamibi, craniocaudal and mediolateral oblique MBI (2-minute acquisition per view) confirmed lesion visualization. A region of interest over the lesion permitted depth calculation in the system software. Upper detector retraction allowed biopsy device placement. Specimen images were obtained on the retracted upper detector, confirming sampling of the target. Results Of 21 participants enrolled (mean age, 50.6 years ± 10.1 [SD]; 21 [100%] women), 17 underwent MBI-guided biopsy with concordant pathology. No lesion was observed at the time of biopsy in four participants. Average lesion size was 17 mm (range, 6-38 mm). Average procedure time, including preprocedure imaging, was 55 minutes ± 13 (range, 38-90 minutes). Pathology results included invasive ductal carcinoma (n = 1), fibroadenoma (n = 4), pseudoangiomatous stromal hyperplasia (n = 6), and fibrocystic changes (n = 6). Conclusion MBI-guided biopsy using a dual-head system with retractable upper detector head was feasible, well tolerated, and efficient. Keywords: Breast Biopsy, Molecular Breast Imaging, Image-guided Biopsy, Molecular Breast Imaging-guided Biopsy, Breast Cancer Clinical trial registration no. NCT06058650 © RSNA, 2024.

A Survey of Patient Experience During Molecular Breast Imaging.

Molecular breast imaging (MBI) is one of several options available to patients seeking supplemental screening due to mammographically dense breasts. Patient experience during MBI may influence willingness to undergo the test but has yet to be formally assessed. We aimed to assess patient comfort level during MBI, to compare MBI comfort with mammography comfort, to identify factors associated with MBI discomfort, and to evaluate patients' willingness to return for future MBI. Methods: A 10-question survey was sent by e-mail to patients undergoing MBI between August and December 2022 to obtain quantitative assessments and qualitative opinions about MBI. Results: Of 561 invited patients, 209 (37%) completed the survey and provided study consent. Their average age was 60.1 y (range, 40-81 y). Of the 209 responders, 202 (97%) were presenting for screening MBI, 195 (94%) had dense breasts, and 46 (22%) had a personal history of breast cancer. The average rating of MBI comfort was 2.9 (SD, 1.5; median, 3.0) on a 7-point scale (1 indicating extremely comfortable and 7 indicating extremely uncomfortable). The rating distribution was as follows: 140 (67%) comfortable (rating, 1-3); 24 (12%) neither comfortable nor uncomfortable (rating, 4); and 45 (22%) uncomfortable (rating, 5 or 6). No responders gave a 7 rating. The most frequently mentioned sources of discomfort included breast compression (n = 16), back or neck discomfort (n = 14), and maintaining position during the examination (n = 14). MBI comfort was associated with responder age (74% ≥55 y old were comfortable, versus 53% <55 y old [P = 0.003]) and history of MBI (71% with prior MBI were comfortable, versus 61% having a first MBI [P = 0.006]). Of 208 responders with a prior mammogram, 148 (71%) said MBI is more comfortable than mammography (a significant majority [P < 0.001]). Of 202 responders to the question of whether they were willing to return for a future MBI, 196 (97%) were willing. A notable factor in positive patient experience was interaction with the MBI nuclear medicine technologist. Conclusion: Most responders thought MBI to be a comfortable examination and more comfortable than mammography. Patient experience during MBI may be improved by ensuring back support and soliciting patient feedback at the time of positioning and throughout the examination. Methods under study to reduce imaging time may be most important for improving patient experience.

Auditing Abbreviated Breast MR Imaging: Clinical Considerations and Implications.

Abbreviated breast MR (AB-MR) imaging is a relatively new breast imaging tool, which maintains diagnostic accuracy while reducing image times compared with full-protocol breast MR (FP-MR) imaging. Breast imaging audits involve calculating individual and organizational metrics, which can be compared with established benchmarks, providing a standard against which performance can be measured. Unlike FP-MR imaging, there are no established benchmarks for AB-MR imaging but studies demonstrate comparable performance for cancer detection rate, positive predictive value 3, sensitivity, and specificity with T2. We review the basics of performing an audit, including strategies to implement if benchmarks are not being met.

A Prospective Multicenter Study on the Additive Value of Contrast-Enhanced Ultrasound for Biopsy Decision of Ultrasound BI-RADS 4 Breast Lesions.

OBJECTIVE: The main aim of this study was to determine whether the use of contrast-enhanced ultrasound (CEUS) could improve the categorization of suspicious breast lesions based on the Breast Imaging Reporting and Data System (BI-RADS), thereby reducing the number of benign breast lesions referred for biopsy. METHODS: This prospective study, conducted between January 2017 and December 2018, enrolled consenting patients from eight teaching hospitals in China, who had been diagnosed with solid breast lesions classified as BI-RADS 4 using conventional ultrasound. CEUS was performed within 1 wk of diagnosis for reclassification of breast lesions. Histopathological results obtained from core needle biopsies or surgical excision samples served as the reference standard. The simulated biopsy rate and cancer-to-biopsy yield were used to compare the accuracy of CEUS and conventional ultrasound (US). RESULTS: Among the 1490 lesions diagnosed as BI-RADS 4 with conventional ultrasound, 486 malignant and 1004 benign lesions were confirmed based on histology. Following CEUS, 2, 395, and 211 lesions were reclassified as CEUS-based BI-RADS 2, 3, and 5, respectively, while 882 (59%) remained as BI-RADS 4. The actual cancer-to-biopsy yield based on US was 32.6%, which increased to 43.4% when CEUS-based BI-RADS 4A was used as the cut-off point to recommend biopsy. The simulated biopsy rate decreased to 73.4%. Overall, in this preselected BI-RADS 4 population, only 2.5% (12/486) of malignant lesions would have been miscategorized as BI-RADS 3 using CEUS-based reclassification. The diagnostic accuracy, sensitivity, and specificity of contrast-enhanced ultrasound reclassification were 57.65%, 97.53%, and 38.35%, respectively. CONCLUSION: Our collective findings indicate that CEUS is a valuable tool in further triage of BI-RADS category 4 lesions and facilitates a reduction in the number of biopsies while increasing the cancer-to-biopsy yield.

Breast imaging in focus: A bibliometric overview of visual quality, modality innovations, and diagnostic performance.

INTRODUCTION: Breast imaging plays a crucial role in the early detection and management of breast cancer, with visual quality, modality innovation and diagnostic performance being key factors in achieving accurate diagnoses and optimal patient outcomes. This paper presents a comprehensive bibliometric analysis of the literature on the three above elements focusing on breast imaging, aiming to uncover publication trends, identify influential works and authors, and highlight future research directions. METHODS: We employed a methodical bibliometric approach, making use of Scopus and Web of Science (WoS) databases for gathering literatures. We planned our search strategy, concentrating on terms linked to "breast imaging," "image quality," and "diagnostic accuracy" to ensure a systematic examination of the subject. The enhanced search functions in these databases enabled us to narrow down and improve our findings, choosing only the articles, conference papers, and book sections that are most relevant. After conducting a thorough screening process to remove duplicates and evaluate significance, we utilized ScientoPy and VOSviewer software for an in-depth bibliometric analysis. This helped to explore trends in publications, patterns of citations, and thematic groups, giving us a better understanding of how the field has changed and where it currently stands. Our approach prioritized assessing methodological quality and bias in the studies we included, guaranteeing the reliability of our findings. RESULTS: We reviewed 2984 relevant publications, revealing a consistent annual growth rate of 2.8% in breast imaging research, with the United States and Europe leading in contributions. The study found that advancements in radiological technologies and international collaboration are driving forces behind the field's expansion. Key subject areas such as 'Radiology, Nuclear Medicine, and Medical Imaging' dominated, underscoring their impact on diagnostic quality. Notable authors and institutions have been identified for their influential research, characterized by high citation metrics and significant scholarly impact. CONCLUSION: The study shows a continuous increase in research on breast imaging, considered by new technologies and teamwork defining the present time. The assessment highlights a key move towards utilizing digital imaging methods and computational analysis, affecting the improvement of future diagnostic procedures and patients' results. The study highlights the importance of continued international collaborations to tackle the new barriers in breast imaging and make the most of technological progress. IMPLICATIONS FOR PRACTICE: This study shows a focus on using interdisciplinary methods and cutting-edge technology in breast imaging to help healthcare professionals improve their performance and accuracy in diagnosis. Recognizing vital research and emerging trends should guide clinical guidelines, radiology training, and patient care plans to encourage the use of effective techniques and stimulate innovation in diagnostic approaches.

The application of computer-aided diagnosis in Breast Imaging Reporting and Data System ultrasound training for residents-a randomized controlled study.

Background: The consistency of Breast Imaging Reporting and Data System (BI-RADS) classification among experienced radiologists is different, which is difficult for inexperienced radiologists to master. This study aims to explore the value of computer-aided diagnosis (CAD) (AI-SONIC breast automatic detection system) in the BI-RADS training for residents. Methods: A total of 12 residents who participated in the first year and the second year of standardized resident training in Ningbo No. 2 Hospital from May 2020 to May 2021 were randomly divided into 3 groups (Group 1, Group 2, Group 3) for BI-RADS training. They were asked to complete 2 tests and questionnaires at the beginning and end of the training. After the first test, the educational materials were given to the residents and reviewed during the breast imaging training month. Group 1 studied independently, Group 2 studied with CAD, and Group 3 was taught face-to-face by experts. The test scores and ultrasonographic descriptors of the residents were evaluated and compared with those of the radiology specialists. The trainees' confidence and recognition degree of CAD were investigated by questionnaire. Results: There was no statistical significance in the scores of residents in the first test among the 3 groups (P=0.637). After training and learning, the scores of all 3 groups of residents were improved in the second test (P=0.006). Group 2 (52±7.30) and Group 3 (54±5.16) scored significantly higher than Group 1 (38±3.65). The consistency of ultrasonographic descriptors and final assessments between the residents and senior radiologists were improved (κ3 > κ2 > κ1), with κ2 and κ3 >0.4 (moderately consistent with experts), and κ1 =0.225 (fairly agreed with experts). The results of the questionnaire showed that the trainees had increased confidence in BI-RADS classification, especially Group 2 (1.5 to 3.5) and Group 3 (1.25 to 3.75). All trainees agreed that CAD was helpful for BI-RADS learning (Likert scale score: 4.75 out of 5) and were willing to use CAD as an aid (4.5, max. 5). Conclusions: The AI-SONIC breast automatic detection system can help residents to quickly master BI-RADS, improve the consistency between residents and experts, and help to improve the confidence of residents in the classification of BI-RADS, which may have potential value in the BI-RADS training for radiology residents. Trial Registration: Chinese Clinical Trial Registry (ChiCTR2400081672).

Assessing the Responses of Large Language Models (ChatGPT-4, Gemini, and Microsoft Copilot) to Frequently Asked Questions in Breast Imaging: A Study on Readability and Accuracy.

Background Large language models (LLMs), such as ChatGPT-4, Gemini, and Microsoft Copilot, have been instrumental in various domains, including healthcare, where they enhance health literacy and aid in patient decision-making. Given the complexities involved in breast imaging procedures, accurate and comprehensible information is vital for patient engagement and compliance. This study aims to evaluate the readability and accuracy of the information provided by three prominent LLMs, ChatGPT-4, Gemini, and Microsoft Copilot, in response to frequently asked questions in breast imaging, assessing their potential to improve patient understanding and facilitate healthcare communication. Methodology We collected the most common questions on breast imaging from clinical practice and posed them to LLMs. We then evaluated the responses in terms of readability and accuracy. Responses from LLMs were analyzed for readability using the Flesch Reading Ease and Flesch-Kincaid Grade Level tests and for accuracy through a radiologist-developed Likert-type scale. Results The study found significant variations among LLMs. Gemini and Microsoft Copilot scored higher on readability scales (p < 0.001), indicating their responses were easier to understand. In contrast, ChatGPT-4 demonstrated greater accuracy in its responses (p < 0.001). Conclusions While LLMs such as ChatGPT-4 show promise in providing accurate responses, readability issues may limit their utility in patient education. Conversely, Gemini and Microsoft Copilot, despite being less accurate, are more accessible to a broader patient audience. Ongoing adjustments and evaluations of these models are essential to ensure they meet the diverse needs of patients, emphasizing the need for continuous improvement and oversight in the deployment of artificial intelligence technologies in healthcare.

Facilitating Culturally Competent Breast Imaging Care in South Asian Patients.

South Asians are a rapidly growing subset of the Asian population in the United States. They comprise people from multiple countries with diverse beliefs, languages, and cultural identities and values. The incidence of breast cancer is rising in South Asian women in the United States, with earlier onset and predilection for HER2-enriched tumors. Despite the rising incidence of breast cancer, participation in screening remains lower than other populations. Health care inequities in South Asian women are multifactorial and may be due to traditional health beliefs and practices, language barriers, cultural differences, and lack of overall awareness. Developing a culturally sensitive environment in breast imaging clinic practice can lead to improved patient care and adherence. Given the scarcity of data specific to the South Asian population in United States, there is a need for health service researchers and practice leaders to obtain more high-quality data to understand the needs of South Asian patient populations.

Digital Breast Tomosynthesis for Upgraded BIRADS Scoring towards the True Pathology of Lesions Detected by Contrast-Enhanced Mammography.

OBJECTIVE: To determine the added value of digital breast tomosynthesis (DBT) in the assessment of lesions detected by contrast-enhanced mammography (CEM). MATERIAL AND METHODS: A retrospective study was conducted in a tertiary university medical center. All CEM studies including DBT performed between January 2016 and December 2020 were included. Lesions were categorized and scored by four dedicated breast radiologists according to the recent CEM and DBT supplements to the Breast Imaging Reporting and Data System (BIRADS) lexicon. Changes in the BIRADS score of CEM-detected lesions with the addition of DBT were evaluated according to the pathology results and 1-year follow-up imaging study. RESULTS: BIRADS scores of CEM-detected lesions were upgraded toward the lesion's pathology with the addition of DBT (p > 0.0001), overall and for each reader. The difference in BIRADS scores before and after the addition of DBT was more significant for readers who were less experienced. The reason for changes in the BIRADS score was better lesion margin visibility. The main BIRADS descriptors applied in the malignant lesions were spiculations, calcifications, architectural distortion, and sharp or obscured margins. CONCLUSIONS: The addition of DBT to CEM provides valuable information on the enhancing lesion, leading to a more accurate BIRADS score.

Detection and diagnosis of automated breast ultrasound in patients with BI-RADS category 4 microcalcifications: a retrospective study.

BACKGROUND: Automated Breast Ultrasound (AB US) has shown good application value and prospects in breast disease screening and diagnosis. The aim of the study was to explore the ability of AB US to detect and diagnose mammographically Breast Imaging Reporting and Data System (BI-RADS) category 4 microcalcifications. METHODS: 575 pathologically confirmed mammographically BI-RADS category 4 microcalcifications from January 2017 to June 2021 were included. All patients also completed AB US examinations. Based on the final pathological results, analyzed and summarized the AB US image features, and compared the evaluation results with mammography, to explore the detection and diagnostic ability of AB US for these suspicious microcalcifications. RESULTS: 250 were finally confirmed as malignant and 325 were benign. Mammographic findings including microcalcifications morphology (61/80 with amorphous, coarse heterogeneous and fine pleomorphic, 13/14 with fine-linear or branching), calcification distribution (189/346 with grouped, 40/67 with linear and segmental), associated features (70/96 with asymmetric shadow), higher BI-RADS category with 4B (88/120) and 4 C (73/38) showed higher incidence in malignant lesions, and were the independent factors associated with malignant microcalcifications. 477 (477/575, 83.0%) microcalcifications were detected by AB US, including 223 malignant and 254 benign, with a significantly higher detection rate for malignant lesions (x2 = 12.20, P < 0.001). Logistic regression analysis showed microcalcifications with architectural distortion (odds ratio [OR] = 0.30, P = 0.014), with amorphous, coarse heterogeneous and fine pleomorphic morphology (OR = 3.15, P = 0.037), grouped (OR = 1.90, P = 0.017), liner and segmental distribution (OR = 8.93, P = 0.004) were the independent factors which could affect the detectability of AB US for microcalcifications. In AB US, malignant calcification was more frequent in a mass (104/154) or intraductal (20/32), and with ductal changes (30/41) or architectural distortion (58/68), especially with the both (12/12). BI-RADS category results also showed that AB US had higher sensitivity to malignant calcification than mammography (64.8% vs. 46.8%). CONCLUSIONS: AB US has good detectability for mammographically BI-RADS category 4 microcalcifications, especially for malignant lesions. Malignant calcification is more common in a mass and intraductal in AB US, and tend to associated with architectural distortion or duct changes. Also, AB US has higher sensitivity than mammography to malignant microcalcification, which is expected to become an effective supplementary examination method for breast microcalcifications, especially in dense breasts.

Protocol for evaluating the fitness for purpose of an artificial intelligence product for radiology reporting in the BreastScreen New South Wales breast cancer screening programme.

INTRODUCTION: Radiologist shortages threaten the sustainability of breast cancer screening programmes. Artificial intelligence (AI) products that can interpret mammograms could mitigate this risk. While previous studies have suggested this technology has accuracy comparable to radiologists most have been limited by using 'enriched' datasets and/or not considering the interaction between the algorithm and human readers. This study will address these limitations by comparing the accuracy of a workflow using AI alongside radiologists on a large consecutive cohort of examinations from a breast cancer screening programme. The study will combine the strengths of a large retrospective design with the benefit of prospective data collection. It will test this technology without risk to screening programme participants nor the need to wait for follow-up data. With a sample of 2 years of consecutive screening examinations, it is likely the largest test of this technology to date. The study will help determine whether this technology can safely be introduced into the BreastScreen New South Wales (NSW) population-based screening programme to address radiology workforce risks without compromising cancer detection rates or increasing false-positive recalls. METHODS AND ANALYSIS: A retrospective, consecutive cohort of digital mammography screens from 658 207 examinations from BreastScreen NSW will be reinterpreted by the Lunit Insight MMG AI product. The cohort includes 4383 screen-detected and 1171 interval cancers. The results will be compared with radiologist single reading and the AI results will also be used to replace the second reader in a double-reading model. New adjudication reading will be performed where the AI disagrees with the first reader. Recall rates and cancer detection rates of combined AI-radiologist reading will be compared with the rates obtained at the time of screening. ETHICS AND DISSEMINATION: This study has ethical approval from the NSW Health Population Health Services Research Ethics Committee (2022/ETH02397). Findings will be published in peer-reviewed journals and presented at conferences. The findings of this evaluation will be provided to programme managers, governance bodies and other stakeholders in Australian breast cancer screening programmes.

Review of Breast Imaging in Transgender and Gender-Diverse Patients: Gender-Affirming Care, Histopathologic Findings, Breast Cancer Risk, and Screening Recommendations.

Gender diversity, especially pertaining to transgender and gender-diverse (TGD) populations, is often stigmatized. A small but not insignificant number of adults in the United States identify as TGD, including transgender, nonbinary, and other gender identities than cisgender. Accessing health care remains a significant challenge for TGD individuals because many health care systems adhere to a gender binary model and many TGD individuals experience negative interactions when interfacing with health care. There is also a scarcity of literature addressing their unique health care needs, limiting our current understanding of breast cancer risks and screening recommendations for TGD patients. This article reviews important considerations when providing care to TGD patients. It covers background information on gender identity and sexuality, explores gender-affirming care, discusses histopathologic findings of breast biopsy specimens, examines breast cancer risks, and presents current breast cancer screening recommendations for TGD patients. Education on TGD breast cancer risks and screening and creating a standardized screening protocol for TGD patients who may receive gender-affirming care through hormonal and surgical therapies could help improve their health care equity and access.

Use of artificial intelligence in breast surgery: a narrative review.

Background and Objective: We have witnessed tremendous advances in artificial intelligence (AI) technologies. Breast surgery, a subspecialty of general surgery, has notably benefited from AI technologies. This review aims to evaluate how AI has been integrated into breast surgery practices, to assess its effectiveness in improving surgical outcomes and operational efficiency, and to identify potential areas for future research and application. Methods: Two authors independently conducted a comprehensive search of PubMed, Google Scholar, EMBASE, and Cochrane CENTRAL databases from January 1, 1950, to September 4, 2023, employing keywords pertinent to AI in conjunction with breast surgery or cancer. The search focused on English language publications, where relevance was determined through meticulous screening of titles, abstracts, and full-texts, followed by an additional review of references within these articles. The review covered a range of studies illustrating the applications of AI in breast surgery encompassing lesion diagnosis to postoperative follow-up. Publications focusing specifically on breast reconstruction were excluded. Key Content and Findings: AI models have preoperative, intraoperative, and postoperative applications in the field of breast surgery. Using breast imaging scans and patient data, AI models have been designed to predict the risk of breast cancer and determine the need for breast cancer surgery. In addition, using breast imaging scans and histopathological slides, models were used for detecting, classifying, segmenting, grading, and staging breast tumors. Preoperative applications included patient education and the display of expected aesthetic outcomes. Models were also designed to provide intraoperative assistance for precise tumor resection and margin status assessment. As well, AI was used to predict postoperative complications, survival, and cancer recurrence. Conclusions: Extra research is required to move AI models from the experimental stage to actual implementation in healthcare. With the rapid evolution of AI, further applications are expected in the coming years including direct performance of breast surgery. Breast surgeons should be updated with the advances in AI applications in breast surgery to provide the best care for their patients.

Artificial Intelligence for breast cancer detection: Technology, challenges, and prospects.

PURPOSE: This review provides an overview of the current state of artificial intelligence (AI) technology for automated detection of breast cancer in digital mammography (DM) and digital breast tomosynthesis (DBT). It aims to discuss the technology, available AI systems, and the challenges faced by AI in breast cancer screening. METHODS: The review examines the development of AI technology in breast cancer detection, focusing on deep learning (DL) techniques and their differences from traditional computer-aided detection (CAD) systems. It discusses data pre-processing, learning paradigms, and the need for independent validation approaches. RESULTS: DL-based AI systems have shown significant improvements in breast cancer detection. They have the potential to enhance screening outcomes, reduce false negatives and positives, and detect subtle abnormalities missed by human observers. However, challenges like the lack of standardised datasets, potential bias in training data, and regulatory approval hinder their widespread adoption. CONCLUSIONS: AI technology has the potential to improve breast cancer screening by increasing accuracy and reducing radiologist workload. DL-based AI systems show promise in enhancing detection performance and eliminating variability among observers. Standardised guidelines and trustworthy AI practices are necessary to ensure fairness, traceability, and robustness. Further research and validation are needed to establish clinical trust in AI. Collaboration between researchers, clinicians, and regulatory bodies is crucial to address challenges and promote AI implementation in breast cancer screening.

Disparities in Study Inclusion and Screening Rates in Breast Cancer Screening Rates Among Transgender People: A Systematic Review.

BACKGROUND: Breast cancer screening trends of transgender and gender diverse (TGD) people remain largely unknown. This is concerning, as data are necessary to inform recommendations made by clinicians to their patients and by national guidelines to clinicians. The aim of this review is to explore the state of existing research literature and provide a summary report of current breast cancer screening rates in TGD adults. METHODS: All articles were identified using Medical Subject Headings terms. Inclusion criteria were all the following: (1) documents inclusion of at least one participant who identifies as a TGD person; (2) at least one TGD participant with top surgery or currently receiving estrogen-based gender-affirming hormone therapy; (3) results that report rates of breast cancer screening or mammogram referral. RESULTS: Twelve articles met inclusion criteria, six cross-sectional studies and six retrospective chart reviews. Three studies conducted secondary analysis of the Behavioral Risk Factor Surveillance System national dataset, and nine articles recruited their own sample with number of TGD participants ranging from 30 to 1,822 and number of cisgender women ranging from 242 to 18,275. Three studies found lower rates of screening in transfeminine persons receiving gender-affirming care compared with cisgender women; two studies found lower rates among TGD people compared with cisgender women; and three studies found no differences between the breast cancer screening rates of TGD and cisgender participants. CONCLUSION: Limited studies recruit and report trends in breast cancer screening of TGD people. Those that do include TGD participants have mixed results, but overall TGD people had lower rates of breast cancer screening. More research is needed regarding breast cancer screening of TGD people to inform the development of protocols that ensure equitable access to preventative care.

Breast Implant Imaging Surveillance Practice: Survey of Breast Imaging Radiologists in the Society of Breast Imaging.

OBJECTIVE: The objectives of this Society of Breast Imaging (SBI)-member survey study were to assess the current imaging patterns for evaluation of symptomatic and asymptomatic breast implant integrity, including modalities used and imaging intervals. METHODS: A 12-question survey assessing the frequency of imaging modalities used to evaluate implant integrity, approximate number of breast implant integrity studies requested per month, intervals of integrity studies, and referring provider and radiology practice characteristics was distributed to members of the SBI. RESULTS: The survey response rate was 7.6% (143/1890). Of responding radiologists, 54.2% (77/142) were in private, 29.6% (42/142) in academic, and 16.2% (23/142) in hybrid practice. Among respondents, the most common initial examination for evaluating implant integrity was MRI without contrast at 53.1% (76/143), followed by handheld US at 46.9% (67/143). Of respondents using US, 67.4% (91/135) also evaluated the breast tissue for abnormalities. Among respondents, 34.1% (46/135) reported being very confident or confident in US for diagnosing implant rupture. There was a range of reported intervals for performing implant integrity studies: 39.1% (43/110) every 2-3 years, 26.4% (29/110) every 4-5 years, 15.5% (17/110) every 6-10 years, and 19.1% (21/110) every 10 years. CONCLUSION: For assessment of implant integrity, the majority of respondents (53.2%, 76/143) reported MRI as initial imaging test. US is less costly, but the minority of respondents (34.1%, 46/135) had confidence in US performance. Also, the minority of respondents (39.1%, 43/110) performed implant integrity evaluations every 2-3 years per the FDA recommendations for asymptomatic surveillance.

Virtual Visiting Professorship Program as an Opportunity for Academic and Clinical Advancement Beyond the COVID-19 Pandemic: A Survey of Participants.

OBJECTIVE: To identify structure, benefits, and shortcomings of a multi-institutional virtual visiting professorship (VVP) program from 2020 to 2022, 2 years after inception and after gradual resumption of an in-person, prepandemic academic environment. METHODS: An IRB-exempt, 70-question survey about structure, benefits, and shortcomings of the VVP program was distributed to its participants (14 breast imaging departments across the U.S.), using the snowball sampling technique. RESULTS: A total of 72 responses were received; 54.2% (32/59) radiologists >5 years of experience, 18.6% (11/59) radiologists <5 years of experience, 15.3% (9/59) residents, and 8.5% (5/59) fellows. Radiologists' attendance increased from 8% (5/59) to 53% (31/59) over 2 years, with 69% (41/59) of respondents supporting continued participation. The most important factors for attendance were expanding breast imaging knowledge (86.4% [51/59]) and the virtual format (76.2% [45/59]). The number of presented lectures increased from 1 to 3 lectures in 43.7% (7/16) of programs in year 1 and from 4 to 9 lectures in 50% (8/16) of programs in year 2. The greatest professional benefits were collaborations on publications for organizers (56.3% [9/16]) and building academic portfolios for presenters (50% [7/14]). For trainees, attending the program increased their knowledge (64.3% [9/14]) and enthusiasm for breast imaging (50% [7/14]). CONCLUSION: The VVP program facilitated scholarly collaboration among breast imaging radiologists, promoted academic portfolios for junior faculty, and increased enthusiasm for breast imaging for trainees. These accomplishments extended beyond the COVID-19 pandemic, as evidenced by the growth of the program after resumption of an in-person academic environment. Future expansion to other programs would benefit more practicing radiologists.

Deep-learning model for background parenchymal enhancement classification in contrast-enhanced mammography.

Background.Breast background parenchymal enhancement (BPE) is correlated with the risk of breast cancer. BPE level is currently assessed by radiologists in contrast-enhanced mammography (CEM) using 4 classes: minimal, mild, moderate and marked, as described inbreast imaging reporting and data system(BI-RADS). However, BPE classification remains subject to intra- and inter-reader variability. Fully automated methods to assess BPE level have already been developed in breast contrast-enhanced MRI (CE-MRI) and have been shown to provide accurate and repeatable BPE level classification. However, to our knowledge, no BPE level classification tool is available in the literature for CEM.Materials and methods.A BPE level classification tool based on deep learning has been trained and optimized on 7012 CEM image pairs (low-energy and recombined images) and evaluated on a dataset of 1013 image pairs. The impact of image resolution, backbone architecture and loss function were analyzed, as well as the influence of lesion presence and type on BPE assessment. The evaluation of the model performance was conducted using different metrics including 4-class balanced accuracy and mean absolute error. The results of the optimized model for a binary classification: minimal/mild versus moderate/marked, were also investigated.Results.The optimized model achieved a 4-class balanced accuracy of 71.5% (95% CI: 71.2-71.9) with 98.8% of classification errors between adjacent classes. For binary classification, the accuracy reached 93.0%. A slight decrease in model accuracy is observed in the presence of lesions, but it is not statistically significant, suggesting that our model is robust to the presence of lesions in the image for a classification task. Visual assessment also confirms that the model is more affected by non-mass enhancements than by mass-like enhancements.Conclusion.The proposed BPE classification tool for CEM achieves similar results than what is published in the literature for CE-MRI.