1
|
New Frontiers in Breast Cancer Imaging: The Rise of AI. Bioengineering (Basel) 2024; 11:451. [PMID: 38790318 PMCID: PMC11117903 DOI: 10.3390/bioengineering11050451] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/2024] [Revised: 04/18/2024] [Accepted: 04/26/2024] [Indexed: 05/26/2024] Open
Abstract
Artificial intelligence (AI) has been implemented in multiple fields of medicine to assist in the diagnosis and treatment of patients. AI implementation in radiology, more specifically for breast imaging, has advanced considerably. Breast cancer is one of the most important causes of cancer mortality among women, and there has been increased attention towards creating more efficacious methods for breast cancer detection utilizing AI to improve radiologist accuracy and efficiency to meet the increasing demand of our patients. AI can be applied to imaging studies to improve image quality, increase interpretation accuracy, and improve time efficiency and cost efficiency. AI applied to mammography, ultrasound, and MRI allows for improved cancer detection and diagnosis while decreasing intra- and interobserver variability. The synergistic effect between a radiologist and AI has the potential to improve patient care in underserved populations with the intention of providing quality and equitable care for all. Additionally, AI has allowed for improved risk stratification. Further, AI application can have treatment implications as well by identifying upstage risk of ductal carcinoma in situ (DCIS) to invasive carcinoma and by better predicting individualized patient response to neoadjuvant chemotherapy. AI has potential for advancement in pre-operative 3-dimensional models of the breast as well as improved viability of reconstructive grafts.
Collapse
|
2
|
Maximizing Mentorship Throughout Your Breast Imaging Career. JOURNAL OF BREAST IMAGING 2024:wbae009. [PMID: 38554120 DOI: 10.1093/jbi/wbae009] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/15/2023] [Indexed: 04/01/2024]
Abstract
Unlike many other subspecialties in radiology, breast radiologists practice in a patient-facing and interdisciplinary environment where team building, communication, and leadership skills are critical. Although breast radiologists can improve these skills over time, strong mentorship can accelerate this process, leading to a more successful and satisfying career. In addition to providing advice, insight, feedback, and encouragement to mentees, mentors help advance the field of breast radiology by contributing to the development of the next generation of leaders. During the mentorship process, mentors continue to hone their listening, problem-solving, and networking skills, which in turn creates a more supportive and nurturing work environment for the entire breast care team. This article reviews important mentorship skills that are essential for all breast radiologists. Although some of the principles apply to all mentoring relationships, ensuring that every breast radiologist has the skills to be both an effective mentor and mentee is key to the future of the profession.
Collapse
|
3
|
Beyond the AJR: Breast MRI Finds More Breast Cancers Than Mammography. AJR Am J Roentgenol 2024. [PMID: 38170828 DOI: 10.2214/ajr.23.30782] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/05/2024]
|
4
|
Identifying Frequently Endorsed Benefits and Barriers to Breast Cancer Screening for African-Born Women in the NYC Metropolitan Area: a Pilot Study. J Racial Ethn Health Disparities 2023:10.1007/s40615-023-01865-2. [PMID: 38082068 DOI: 10.1007/s40615-023-01865-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/01/2023] [Revised: 11/02/2023] [Accepted: 11/04/2023] [Indexed: 03/01/2024]
Abstract
Most cancer screening data report on Black participants without distinguishing nativity, limiting our understanding of the needs of distinct groups within the African diaspora. The purpose of this pilot study was to assess demographic characteristics and perceptions of the benefits of and barriers to mammography among African immigrant women in New York City (NYC). Forty-two women who were 40 years or older, born in Africa, and English and/or French-speaking were recruited from African immigrant communities in NYC to complete a survey. Eighty percent of our sample aged 50 to 73 was adherent to the 2016 USPSTF mammography screening guideline. The most frequently endorsed benefits were that mammography will help find breast cancer early, could help find a breast lump before it is big enough to feel, and that if found early, breast cancer could be successfully treated. The most endorsed barriers were that having a mammogram is painful and that lack of insurance or being treated rudely at the mammogram center would keep participants from having a mammogram. Chi-square analyses assessed relationships between demographic characteristics and perceptions about mammography and revealed that endorsement of barriers to screening (e.g., health issues, transportation problems, pain, and time associated with mammography) varied by educational attainment. Findings suggest that future interventions should be multi-level and (1) support patients in accessing screening via resource sharing, (2) address other commonly cited barriers such as fear of pain during the procedure, and (3) support anti-racist healthcare environments especially in terms of treatment by providers.
Collapse
|
5
|
Breast MRI for Extent of Disease: Association of Demographic Factors and Biopsy Compliance on Surgical Decisions in Patients with BI-RADS 4 and 5 Findings. Am Surg 2023; 89:6013-6019. [PMID: 37311567 DOI: 10.1177/00031348231183116] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
BACKGROUND The decision to pursue bilateral mastectomy without pathological confirmation of additional preoperative MRI lesions is likely multifactorial. We investigated the association of demographic factors and biopsy compliance following preoperative breast MRI with changes in surgical management in patients with newly diagnosed breast cancer. METHODS A retrospective review of BI-RADS 4 and 5 MRIs performed across a health system from March 2018 to November 2021 for assessment of disease extent and preoperative planning. Patient characteristics, including demographics, Tyrer-Cuzick risk score, pathology from index cancer and biopsy of MRI findings, and pre- and post-MRI surgical plans were recorded. Analysis compared patients who underwent biopsy with those who did not. RESULTS The final cohort included 323 patients who underwent a biopsy and 89 who did not. Of patients who underwent a biopsy, 144/323 (44.6%) had additional cancer diagnoses. MRI did not change management in 179/323 patients (55.4%) who underwent biopsy and in 44/89 patients (51.7%) who did not. Patients with a biopsy were more likely to have additional breast conservation surgery (P < .001) and patients without a biopsy were more likely to have a change in management to bilateral mastectomy P = .009). Patients without a biopsy who underwent a management change to bilateral mastectomy were significantly younger (47.2 vs 58.6; P < .001) and more likely to be white (P = .02) compared to those choosing bilateral mastectomy after biopsy. DISCUSSION Biopsy compliance is associated with changes in surgical decisions, and younger, white women are more likely to pursue aggressive surgical management without definitive pathologic diagnoses.
Collapse
|
6
|
Optimizing the Patient Experience in Breast Imaging Facilities: AJR Expert Panel Narrative Review. AJR Am J Roentgenol 2023. [PMID: 37966035 DOI: 10.2214/ajr.23.29995] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2023]
Abstract
Breast imaging studies are complex examinations for patients and providers. Breast imaging providers and organizations invest significant resources in educating patients and referring providers to address variability in changing breast cancer screening recommendations, cultural biases, and socioeconomic barriers for patients. The breast imaging examination frequently involves multiple imaging modalities including interventional procedures, thus requiring multiple room types. Practices need to consider variables that affect workflow efficiency throughout the process of scheduling, examination performance, interpretation, and results delivery, as well as options in facilities design to create inviting yet functional environments for patients. Breast imaging appointments provide opportunity to capture individual breast cancer risk and to engage patients in health education and breast screening awareness. This AJR Expert Panel Narrative Review discusses ways in which breast imaging facilities can optimize patient experience throughout the complex process of a breast imaging examination, based on the authors' observations and opinions that include private and academic breast imaging experience.
Collapse
|
7
|
Validating racial and ethnic non-bias of artificial intelligence decision support for diagnostic breast ultrasound evaluation. J Med Imaging (Bellingham) 2023; 10:061108. [PMID: 38106815 PMCID: PMC10721939 DOI: 10.1117/1.jmi.10.6.061108] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/05/2023] [Revised: 10/19/2023] [Accepted: 11/15/2023] [Indexed: 12/19/2023] Open
Abstract
Purpose Breast ultrasound suffers from low positive predictive value and specificity. Artificial intelligence (AI) proposes to improve accuracy, reduce false negatives, reduce inter- and intra-observer variability and decrease the rate of benign biopsies. Perpetuating racial/ethnic disparities in healthcare and patient outcome is a potential risk when incorporating AI-based models into clinical practice; therefore, it is necessary to validate its non-bias before clinical use. Approach Our retrospective review assesses whether our AI decision support (DS) system demonstrates racial/ethnic bias by evaluating its performance on 1810 biopsy proven cases from nine breast imaging facilities within our health system from January 1, 2018 to October 28, 2021. Patient age, gender, race/ethnicity, AI DS output, and pathology results were obtained. Results Significant differences in breast pathology incidence were seen across different racial and ethnic groups. Stratified analysis showed that the difference in output by our AI DS system was due to underlying differences in pathology incidence for our specific cohort and did not demonstrate statistically significant bias in output among race/ethnic groups, suggesting similar effectiveness of our AI DS system among different races (p > 0.05 for all). Conclusions Our study shows promise that an AI DS system may serve as a valuable second opinion in the detection of breast cancer on diagnostic ultrasound without significant racial or ethnic bias. AI tools are not meant to replace the radiologist, but rather to aid in screening and diagnosis without perpetuating racial/ethnic disparities.
Collapse
|
8
|
Mammography Information Systems: A Survey of Breast Imaging Radiologist Satisfaction and Perspectives. JOURNAL OF BREAST IMAGING 2023; 5:565-574. [PMID: 38416917 DOI: 10.1093/jbi/wbad055] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/16/2023] [Indexed: 03/01/2024]
Abstract
OBJECTIVE To assess use of mammography information systems (MISs) and explore features associated with breast imaging radiologist satisfaction. METHODS A 22-question survey regarding MISs was distributed electronically to the Society of Breast Imaging membership between February 16, 2022 and June 28, 2022. Differences in responses between respondents satisfied and dissatisfied with their MIS were analyzed using Pearson chi-squared test, Fisher exact test, and multivariate logistic regression. RESULTS The response rate was 11.4% (228/2007). Most respondents used a commercial MIS (195/228, 85.5%). Most used were Epic (47/228, 21%), MagView (47/228, 21%), and PenRad (37/228, 16%). Only 4.4% (10/228) reported that patient tracking was not integrated with results reporting. The majority (129/226, 57%) reported satisfaction with their MIS. Satisfaction correlated (P < 0.05) with features such as picture archiving and communication system integration, structured reporting, access to physician outcomes metrics, and ability to query data. Less commonly reported features such as non-English language options and recognition of laterality and patient mismatch errors also correlated with satisfaction. Lack of these features correlated with dissatisfaction (P < 0.05). Satisfaction also correlated with adequate training (P < 0.001) and technology support (P < 0.001). On multivariate analysis, longer time using the current MIS was independently associated with satisfaction. CONCLUSION Most respondents used a commercial MIS and were satisfied with their system. Satisfied users reported several helpful MIS features and adequate training and support. The survey results could help MIS companies when designing new products and inform radiologists and administrators when considering a new MIS.
Collapse
|
9
|
Examination of fully automated mammographic density measures using LIBRA and breast cancer risk in a cohort of 21,000 non-Hispanic white women. Breast Cancer Res 2023; 25:92. [PMID: 37544983 PMCID: PMC10405373 DOI: 10.1186/s13058-023-01685-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/05/2023] [Accepted: 07/09/2023] [Indexed: 08/08/2023] Open
Abstract
BACKGROUND Breast density is strongly associated with breast cancer risk. Fully automated quantitative density assessment methods have recently been developed that could facilitate large-scale studies, although data on associations with long-term breast cancer risk are limited. We examined LIBRA assessments and breast cancer risk and compared results to prior assessments using Cumulus, an established computer-assisted method requiring manual thresholding. METHODS We conducted a cohort study among 21,150 non-Hispanic white female participants of the Research Program in Genes, Environment and Health of Kaiser Permanente Northern California who were 40-74 years at enrollment, followed for up to 10 years, and had archived processed screening mammograms acquired on Hologic or General Electric full-field digital mammography (FFDM) machines and prior Cumulus density assessments available for analysis. Dense area (DA), non-dense area (NDA), and percent density (PD) were assessed using LIBRA software. Cox regression was used to estimate hazard ratios (HRs) for breast cancer associated with DA, NDA and PD modeled continuously in standard deviation (SD) increments, adjusting for age, mammogram year, body mass index, parity, first-degree family history of breast cancer, and menopausal hormone use. We also examined differences by machine type and breast view. RESULTS The adjusted HRs for breast cancer associated with each SD increment of DA, NDA and PD were 1.36 (95% confidence interval, 1.18-1.57), 0.85 (0.77-0.93) and 1.44 (1.26-1.66) for LIBRA and 1.44 (1.33-1.55), 0.81 (0.74-0.89) and 1.54 (1.34-1.77) for Cumulus, respectively. LIBRA results were generally similar by machine type and breast view, although associations were strongest for Hologic machines and mediolateral oblique views. Results were also similar during the first 2 years, 2-5 years and 5-10 years after the baseline mammogram. CONCLUSION Associations with breast cancer risk were generally similar for LIBRA and Cumulus density measures and were sustained for up to 10 years. These findings support the suitability of fully automated LIBRA assessments on processed FFDM images for large-scale research on breast density and cancer risk.
Collapse
|
10
|
Investing in Peer Learning as a Qualifying Assessment Model in Breast Imaging: A Paradigm Shift from Peer Review to Peer Learning. CURRENT RADIOLOGY REPORTS 2022. [DOI: 10.1007/s40134-022-00409-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/29/2022]
|
11
|
Screening Mammogram Adherence in Medically Underserved Women: Does Language Preference Matter? JOURNAL OF CANCER EDUCATION : THE OFFICIAL JOURNAL OF THE AMERICAN ASSOCIATION FOR CANCER EDUCATION 2022; 37:1076-1082. [PMID: 33169336 PMCID: PMC8106692 DOI: 10.1007/s13187-020-01922-y] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Accepted: 11/04/2020] [Indexed: 06/11/2023]
Abstract
This study examines the relationship between language preference and screening mammogram adherence in medically underserved women in New York City. A survey was conducted with 518 women age 40 and over attending breast health education programs in English, Spanish, Chinese (Mandarin/Cantonese), and French. Women who preferred Chinese were 53% less likely to have had a mammogram within the past year compared to women who preferred English (p < .01). Women age 75 and older (p < .0001) and those without insurance (p < .05) were also found to be significantly less likely to have had a screening mammogram compared to women ages 55-74 and those with private insurance, respectively. This research indicates medically underserved women who prefer a non-English language may benefit from linguistically appropriate interventions to improve screening mammogram adherence. Future research should examine appropriateness of breast cancer screening for women age 75 and older and explore ways to improve screening mammogram use in the uninsured population.
Collapse
|
12
|
Delays in Follow-up Care for Abnormal Mammograms in Mobile Mammography Versus Fixed-Clinic Patients. J Gen Intern Med 2022; 37:1619-1625. [PMID: 35212876 PMCID: PMC9130416 DOI: 10.1007/s11606-021-07189-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/12/2021] [Accepted: 10/01/2021] [Indexed: 10/19/2022]
Abstract
BACKGROUND Mobile mammographic services (MM) have been shown to increase breast cancer screening in medically underserved women. However, little is known about MM patients' adherence to follow-up of abnormal mammograms and how this compares with patients from traditional, fixed clinics. OBJECTIVES To assess delays in follow-up of abnormal mammograms in women screened using MM versus fixed clinics. DESIGN Electronic medical record review of abnormal screening mammograms. SUBJECTS Women screened on a MM van or at a fixed clinic with an abnormal radiographic result in 2019 (N = 1,337). MAIN MEASURES Our outcome was delay in follow-up of an abnormal mammogram of 60 days or greater. Guided by Andersen's Behavioral Model of Health Services Utilization, we assessed the following: predisposing (age, ethnicity, marital status, preferred language), enabling (insurance, provider referral, clinic site), and need (personal breast cancer history, family history of breast/ovarian cancer) factors. KEY RESULTS Only 45% of MM patients had obtained recommended follow-up within 60 days of an abnormal screening compared to 72% of fixed-site patients (p < .001). After adjusting for predisposing, enabling, and need factors, MM patients were 2.1 times more likely to experience follow-up delays than fixed-site patients (CI: 1.5-3.1; p < .001). African American (OR: 1.5; CI: 1.0-2.1; p < .05) and self-referred (OR: 1.8; CI: 1.2-2.8; p < .01) women were significantly more likely to experience delays compared to Non-Hispanic White women or women with a provider referral, respectively. Women who were married (OR: 0.63; CI: 0.5-0.9; p < .01), had breast cancer previously (OR: 0.37; CI: 0.2-0.8; p < .05), or had a family history of breast/ovarian cancer (OR: 0.76; CI: 0.6-0.9; p < .05) were less likely to experience delayed care compared to unmarried women, women with no breast cancer history, or women without a family history of breast/ovarian cancer, respectively. CONCLUSIONS A substantial proportion of women screened using MM had follow-up delays. Women who are African American, self-referred, or unmarried are particularly at risk of experiencing delays in care for an abnormal mammogram.
Collapse
|
13
|
MRI Features of Free Liquid Silicone in the Transgender Female Breast. JOURNAL OF BREAST IMAGING 2021; 3:322-331. [PMID: 38424775 DOI: 10.1093/jbi/wbab016] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2020] [Indexed: 03/02/2024]
Abstract
OBJECTIVE To define MRI features of free liquid silicone injection (FLSI) of the breast in transgender women considering surgical management. METHODS This study was IRB-approved. MRI images from transgender women with FLSI imaged between 2009 and 2019 were reviewed. Presence and location of fibrotic masses (FMs) in the breast(s) and pectoralis muscle and patterns of granulomas were correlated with clinicopathologic findings. Background enhancement was quantified. Comparisons were performed using two-tailed Fisher exact and Student's t test. RESULTS Of 21 transgender women with FLSI (mean age 46.8 years), 13/21 (61.9%) had a dominant FM measuring over 4 cm; these were limited to breast and pectoralis in 6/21 (28.6%), breast in 9/21 (42.9%), and pectoralis only in 2/21 (9.5%). Four of 21 patients (19.0%) had no FMs, and 4/21 (19.0%) had masses under 4 cm. Mean size of the dominant FM was 7.4 cm (range 4-12 cm). FMs were enhancing in 5/13 (38.5%) and contained T2 high signal granulomas in 8/13 (61.5%). While 18/21 (85.8%) of cases showed mild to moderate overall background enhancement, the majority 7/13 (61.5%) of dominant FM were non-enhancing. About half of cases (11/21, 52.4%) had diffuse foci, and half (10/21, 47.6%) had diffuse foci and masses throughout the breast and pectoralis muscle. These foci and masses displayed T2 high signal in 13/21 (61.9%). There were no occult carcinomas observed. CONCLUSION MRI performed on symptomatic FLSI patients considering surgical treatment is helpful in assessing the extent of silicone infiltration and fibrotic reaction of the breast and pectoralis muscle.
Collapse
|
14
|
Developing a Culturally and Linguistically Targeted Breast Cancer Educational Program for a Multicultural Population. JOURNAL OF CANCER EDUCATION : THE OFFICIAL JOURNAL OF THE AMERICAN ASSOCIATION FOR CANCER EDUCATION 2021; 36:395-400. [PMID: 31713105 PMCID: PMC7211551 DOI: 10.1007/s13187-019-01643-x] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/05/2023]
Abstract
Breast cancer is the most commonly diagnosed cancer among women in the USA. Despite the availability of screening mammograms, significant disparities still exist in breast cancer outcomes of racial/ethnic and sexual/gender minorities. To address these disparities, the Mount Sinai Mobile Breast Health Program in New York City collaborated with local organizations to develop culturally and linguistically appropriate breast cancer education programs aimed at increasing screening mammogram utilization. Literature review of the barriers to mammography screening formed the basis to allow us to draft a narrative presentation for each targeted cultural group: African American, African-born, Chinese, Latina, and Muslim women, as well as LGBTQ individuals. The presentations were then tested with focus groups comprised of gatekeepers and members from local community and faith-based organizations which served the targeted populations. Feedback from focus groups and gatekeepers was incorporated into the presentations, and if necessary, the presentations were translated. Subsequently, the presentations were re-tested for appropriateness and reviewed for consistency in message, design, educational information, and slide sequencing. Our experience demonstrated the importance of collaborating with community organizations to provide educational content that is culturally and linguistically appropriate for minority groups facing barriers to uptake of screening mammography.
Collapse
|
15
|
Abstract
Low-dose CT screening for lung cancer provides images of the entire chest and upper abdomen. While the focus of screening is on finding early lung cancer, radiology leadership has embraced the fact that the information contained in the images presents a new challenge to the radiology profession. Other findings in the chest and upper abdomen were not the reason for obtaining the screening CT scan, nor symptom-prompted, but still need to be reported. Reporting these findings and making recommendations for further workup requires careful consideration to avoid unnecessary workup or interventions while still maximizing the benefit that early identification of these other diseases provided. Other potential findings, such as cardiovascular disease and chronic pulmonary obstructive diseases actually cause more deaths than lung cancer. Existing recommendations for workup of abnormal CT findings are based on symptom-prompted indications for imaging. These recommendations may be different when the abnormalities are identified in asymptomatic people undergoing CT screening for lung cancer. I-ELCAP, a large prospectively collected multi-institutional and multi-national database of screenings, was used to analyze CT findings identified in screening for lung cancer. These analyses and recommendations were made by radiologists in collaboration with clinicians in different medical specialties.
Collapse
|
16
|
Mammography, Breast Density, and Major Adverse Cardiac Events: Potential Buy-One-Get-One-Free Lifesaving Bonus Finding. JACC Cardiovasc Imaging 2020; 14:439-441. [PMID: 33248958 DOI: 10.1016/j.jcmg.2020.09.008] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/26/2020] [Revised: 08/28/2020] [Accepted: 09/02/2020] [Indexed: 11/15/2022]
|
17
|
Factors associated with mammography use: A side-by-side comparison of results from two national surveys. Cancer Med 2020; 9:6430-6451. [PMID: 32677744 PMCID: PMC7476827 DOI: 10.1002/cam4.3128] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2020] [Revised: 04/11/2020] [Accepted: 04/22/2020] [Indexed: 01/19/2023] Open
Abstract
BACKGROUND Mammography use is affected by multiple factors that may change as public health interventions are implemented. We examined two nationally representative, population-based surveys to seek consensus and identify inconsistencies in factors associated with mammography use in the entirety of the US population, and by black and white subgroups. METHODS Self-reported mammography use in the past year was extracted for 12 639 and 169 116 women aged 40-74 years from the 2016 National Health Interview Survey (NHIS) and the 2016 Behavioral Risk Factor Surveillance System (BRFSS), respectively. We applied a random forest algorithm to identify the risk factors of mammography use and used a subset of them in multivariable survey logistic regressions to examine their associations with mammography use, reporting predictive margins and effect sizes. RESULTS The weighted prevalence of past year mammography use was comparable across surveys: 54.31% overall, 54.50% in white, and 61.57% in black in NHIS and 53.24% overall, 56.97% in white, and 62.11% in black in BRFSS. Overall, mammography use was positively associated with black race, older age, higher income, and having health insurance, while negatively associated with having three or more children at home and residing in the Western region of the US. Overweight and moderate obesity were significantly associated with increased mammography use among black women (NHIS), while severe obesity was significantly associated with decreased mammography use among white women (BRFSS). CONCLUSION We found higher mammography use among black women than white women, a change in the historical trend. We also identified high parity as a risk factor for mammography use, which suggests a potential subpopulation to target with interventions aimed at increasing mammography use.
Collapse
|
18
|
Screening Mammography: Guidelines versus Clinical Practice. JOURNAL OF BREAST IMAGING 2020; 2:217-224. [PMID: 38424972 DOI: 10.1093/jbi/wbaa003] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/27/2019] [Indexed: 03/02/2024]
Abstract
OBJECTIVE To understand physicians' comprehension of breast cancer screening guidelines and the existing literature on breast cancer screening, and whether this contributes to how patient screening is implemented in clinical practice. METHODS A survey of 18 questions was distributed across the United States via e-mail and social media resources to physicians and medical students of all disciplines and levels of training. Responses from 728 physicians and medical students were reviewed. Respondents were from over 200 different institutions and over 60 different medical specialties. RESULTS Our survey demonstrates that more than half of the participants felt uncomfortable in their knowledge of breast cancer screening recommendations (399/728, 54.8%) and existing literature on breast cancer screening (555/728, 76.2%). When stratified based on level of training, those at the attending level reported a greater level of comfort in their knowledge of breast cancer screening recommendations (168/238, 70.6%) and literature (95/238, 39.9%) compared with respondents at the trainee level. Attending physicians are also more likely to recommend screening for patients between the ages of 40-49 years old (209/238, 87.7%) compared to those at the trainee level. Responses on whether to screen based on age were most consistent for patients ages 50-74, with greater than 90% of the respondents endorsing screening mammogram for this age group in all levels of training. There were greater inconsistencies in the support to screen age groups 40-49 and 75+ . CONCLUSIONS The results showed a disparity in screening practices by clinicians in all levels of training, particularly for patients ages 40-49 and 75+ , and for the interval of screening. Later initiation with less frequent intervals between screens may reduce the impact of screening on mortality reduction.
Collapse
|
19
|
Evaluation of Combined Artificial Intelligence and Radiologist Assessment to Interpret Screening Mammograms. JAMA Netw Open 2020; 3:e200265. [PMID: 32119094 PMCID: PMC7052735 DOI: 10.1001/jamanetworkopen.2020.0265] [Citation(s) in RCA: 157] [Impact Index Per Article: 39.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/12/2019] [Accepted: 12/26/2019] [Indexed: 12/18/2022] Open
Abstract
Importance Mammography screening currently relies on subjective human interpretation. Artificial intelligence (AI) advances could be used to increase mammography screening accuracy by reducing missed cancers and false positives. Objective To evaluate whether AI can overcome human mammography interpretation limitations with a rigorous, unbiased evaluation of machine learning algorithms. Design, Setting, and Participants In this diagnostic accuracy study conducted between September 2016 and November 2017, an international, crowdsourced challenge was hosted to foster AI algorithm development focused on interpreting screening mammography. More than 1100 participants comprising 126 teams from 44 countries participated. Analysis began November 18, 2016. Main Outcomes and Measurements Algorithms used images alone (challenge 1) or combined images, previous examinations (if available), and clinical and demographic risk factor data (challenge 2) and output a score that translated to cancer yes/no within 12 months. Algorithm accuracy for breast cancer detection was evaluated using area under the curve and algorithm specificity compared with radiologists' specificity with radiologists' sensitivity set at 85.9% (United States) and 83.9% (Sweden). An ensemble method aggregating top-performing AI algorithms and radiologists' recall assessment was developed and evaluated. Results Overall, 144 231 screening mammograms from 85 580 US women (952 cancer positive ≤12 months from screening) were used for algorithm training and validation. A second independent validation cohort included 166 578 examinations from 68 008 Swedish women (780 cancer positive). The top-performing algorithm achieved an area under the curve of 0.858 (United States) and 0.903 (Sweden) and 66.2% (United States) and 81.2% (Sweden) specificity at the radiologists' sensitivity, lower than community-practice radiologists' specificity of 90.5% (United States) and 98.5% (Sweden). Combining top-performing algorithms and US radiologist assessments resulted in a higher area under the curve of 0.942 and achieved a significantly improved specificity (92.0%) at the same sensitivity. Conclusions and Relevance While no single AI algorithm outperformed radiologists, an ensemble of AI algorithms combined with radiologist assessment in a single-reader screening environment improved overall accuracy. This study underscores the potential of using machine learning methods for enhancing mammography screening interpretation.
Collapse
|
20
|
Corrigendum to “Reactivation tuberculosis presenting with unilateral axillary lymphadenopathy” [Radiology Case Reports 13 (2018) 1188–1191]. Radiol Case Rep 2020; 15:161. [DOI: 10.1016/j.radcr.2019.10.026] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022] Open
|
21
|
Abstract
The rapid development of deep learning, a family of machine learning techniques, has spurred much interest in its application to medical imaging problems. Here, we develop a deep learning algorithm that can accurately detect breast cancer on screening mammograms using an "end-to-end" training approach that efficiently leverages training datasets with either complete clinical annotation or only the cancer status (label) of the whole image. In this approach, lesion annotations are required only in the initial training stage, and subsequent stages require only image-level labels, eliminating the reliance on rarely available lesion annotations. Our all convolutional network method for classifying screening mammograms attained excellent performance in comparison with previous methods. On an independent test set of digitized film mammograms from the Digital Database for Screening Mammography (CBIS-DDSM), the best single model achieved a per-image AUC of 0.88, and four-model averaging improved the AUC to 0.91 (sensitivity: 86.1%, specificity: 80.1%). On an independent test set of full-field digital mammography (FFDM) images from the INbreast database, the best single model achieved a per-image AUC of 0.95, and four-model averaging improved the AUC to 0.98 (sensitivity: 86.7%, specificity: 96.1%). We also demonstrate that a whole image classifier trained using our end-to-end approach on the CBIS-DDSM digitized film mammograms can be transferred to INbreast FFDM images using only a subset of the INbreast data for fine-tuning and without further reliance on the availability of lesion annotations. These findings show that automatic deep learning methods can be readily trained to attain high accuracy on heterogeneous mammography platforms, and hold tremendous promise for improving clinical tools to reduce false positive and false negative screening mammography results. Code and model available at: https://github.com/lishen/end2end-all-conv .
Collapse
|
22
|
Reactivation tuberculosis presenting with unilateral axillary lymphadenopathy. Radiol Case Rep 2018; 13:1188-1191. [PMID: 30233757 PMCID: PMC6141701 DOI: 10.1016/j.radcr.2018.07.014] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/25/2018] [Accepted: 07/08/2018] [Indexed: 11/25/2022] Open
Abstract
Unilateral axillary lymphadenopathy has various benign and malignant etiologies. Although benign causes are more common, it is important to exclude malignant causes, including metastasis from primary breast carcinoma. Benign etiologies include reactive adenopathy, granulomatous disease, and collagen vascular disease. We present a case of unilateral right axillary lymphadenopathy in a patient with rheumatoid arthritis. The pathologic diagnosis of granulomatous lymphadenitis and interval discovery of patient's history of latent tuberculosis led to a second biopsy for special mycobacterial staining and cultures with a final diagnosis of reactivation tuberculosis. The extrapulmonary manifestation of reactivation tuberculosis with tuberculous lymphadenitis is uncommon and particularly rare in the axillary lymph nodes.
Collapse
|
23
|
Mobile Mammography Participation Among Medically Underserved Women: A Systematic Review. Prev Chronic Dis 2018; 15:E140. [PMID: 30447104 PMCID: PMC6266518 DOI: 10.5888/pcd15.180291] [Citation(s) in RCA: 53] [Impact Index Per Article: 8.8] [Reference Citation Analysis] [Abstract] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/28/2023] Open
Abstract
Introduction Although breast cancer deaths have declined, the mortality rate among women from medically underserved communities is disproportionally high. Screening mammography is the most effective tool for detecting breast cancer in its early stages, yet many women from medically underserved communities do not have adequate access to screening mammograms. Mobile mammography may be able to bridge this gap by providing screening mammograms at no cost or low cost and delivering services to women in their own neighborhoods, thus eliminating cost and transportation barriers. The objective of this systematic review was to describe the scope and impact of mobile mammography programs in promoting mammographic screening participation among medically underserved women. Methods We searched electronic databases for English-language articles published in the United States from January 2010 through March 2018 by using the terms “mobile health unit,” “mammogram,” “mammography,” and “breast cancer screening.” Of the 93 articles initially identified, we screened 55; 16 were eligible to be assessed and 10 qualified for full text review and data extraction. Each study was coded for study purpose, research design, data collection, population targeted, location, sample size, outcomes, predictors, analytical methods, and findings. Results Of the 10 studies that qualified for review, 4 compared mobile mammography users with users of fixed units, and the other 6 characterized mobile mammography users only. All the mobile mammography units included reached underserved women. Most of the women screened in mobile units were African American or Latina, low income, and/or uninsured. Mobile mammography users reported low adherence to 1-year (12%–34%) and 2-year (40%–48%) screening guidelines. Some difficulties faced by mobile clinics were patient retention, patient follow-up of abnormal or inconclusive findings, and women inaccurately perceiving their breast cancer risk. Conclusion Mobile mammography clinics may be effective at reaching medically underserved women. Adding patient navigation to mobile mammography programs may promote attendance at mobile sites and increase follow-up adherence. Efforts to promote mammographic screening should target women from racial/ethnic minority groups, women from low-income households, and uninsured women. Future research is needed to understand how to best improve visits to mobile mammography clinics.
Collapse
|
24
|
The chest radiologist's role in invasive breast cancer detection. Clin Imaging 2018; 50:13-19. [DOI: 10.1016/j.clinimag.2017.12.002] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/28/2017] [Revised: 10/25/2017] [Accepted: 12/05/2017] [Indexed: 11/12/2022]
|
25
|
Abstract
PURPOSE OF REVIEW Probably benign (BI-RADS 3) causes confusion for interpreting physicians and referring physicians and can induce significant patient anxiety. The best uses and evidence for using this assessment category in mammography, breast ultrasound, and breast MRI will be reviewed; the reader will have a better understanding of how and when to use BI-RADS 3. RECENT FINDINGS Interobserver variability in the use of BI-RADS 3 has been documented. The 5th edition of the BI-RADS atlas details the appropriate use of BI-RADS 3 for diagnostic mammography, ultrasound, and MRI, and discourages its use in screening mammography. Data mining, elastography, and diffusion weighted MRI have been evaluated to maximize the accuracy of BI-RADS 3. SUMMARY BI-RADS 3 is an evolving assessment category. When used properly, it reduces the number of benign biopsies while allowing the breast imager to maintain a high sensitivity for the detection of early stage breast cancer.
Collapse
|
26
|
Utility of surveillance MRI in women with a personal history of breast cancer. Clin Imaging 2017; 46:33-36. [PMID: 28700966 DOI: 10.1016/j.clinimag.2017.06.007] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/08/2017] [Revised: 06/19/2017] [Accepted: 06/28/2017] [Indexed: 10/19/2022]
Abstract
PURPOSE To determine the utility and rate of biopsy in women with a positive history of breast cancer screened with MRI. METHODS Retrospective review of 491 breast MRI screening examinations in women with a personal history of breast cancer. RESULTS In total, 107 biopsies were performed, an average of 0.09 biopsies per person year. The positive predictive value for biopsies prompted by MRI findings was 0.24 (95% C.I. 0.10-0.38). Eight of the nine subsequent cancers were initially identified on screening MRI alone. CONCLUSION Surveillance MRI in breast cancer survivors may increase detection of subsequent cancers while increasing rate of biopsy.
Collapse
|
27
|
The mammary ridge-A case report of multiple ectopic breast masses. Clin Imaging 2017; 45:34-36. [PMID: 28600965 DOI: 10.1016/j.clinimag.2017.05.012] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/08/2017] [Revised: 05/08/2017] [Accepted: 05/10/2017] [Indexed: 10/19/2022]
Abstract
Ectopic or accessory breasts describe residual breast tissue that fails to regress during normal embryologic development anywhere outside the expected locations. Ectopic breast tissue is seen in 2-6% of the population and is categorized into two types: supernumerary and aberrant breast tissue . The extent of development of this accessory tissue varies from rudimentary to complete with organized glandular and ductal development. Given this, it is possible for the same pathology that affects normally positioned breast tissue to also affect accessory breast tissue.
Collapse
|
28
|
The implantable loop recorder and its mammographic appearance: A case based approach. Clin Imaging 2017; 43:1-5. [DOI: 10.1016/j.clinimag.2017.01.006] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/03/2017] [Accepted: 01/14/2017] [Indexed: 01/15/2023]
|
29
|
Cellular fibroadenoma on Core needle biopsy: management recommendations for the radiologist. Clin Imaging 2016; 40:587-90. [PMID: 27317201 DOI: 10.1016/j.clinimag.2016.02.009] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/01/2015] [Revised: 01/31/2016] [Accepted: 02/11/2016] [Indexed: 11/25/2022]
Abstract
INTRODUCTION Cellular fibroadenomas (CFA) are difficult to distinguish from phyllodes tumor (PT) at biopsy. This study's purpose was to determine what CFA characteristics were associated with recommendations to follow-up or excise and if the current algorithm was correct. MATERIALS AND METHODS Databases from 2002 to 2014 were reviewed. Mass characteristics and post biopsy recommendations were recorded. RESULTS 81 CFAs were diagnosed; 19 cellular and 62 with slightly cellular stroma. 21 masses were surgically excised with 2 PTs diagnosed. CONCLUSION Larger mass size and increased histologic cellularity were associated with excision recommendation, but only clinical growth was associated with PT.
Collapse
|
30
|
WITHDRAWN: Digital breast arterial calcium score is predictive of coronary calcium score. Clin Imaging 2015:S0899-7071(15)00060-1. [PMID: 25861880 DOI: 10.1016/j.clinimag.2015.02.016] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/16/2015] [Accepted: 02/22/2015] [Indexed: 12/01/2022]
Abstract
This article has been withdrawn at the request of the author(s) and/or editor. The Publisher apologizes for any inconvenience this may cause. The full Elsevier Policy on Article Withdrawal can be found at http://www.elsevier.com/locate/withdrawalpolicy.
Collapse
|
31
|
Early discussion of breast density and supplemental breast cancer screening: is it possible? Breast J 2014; 20:229-34. [PMID: 24689788 DOI: 10.1111/tbj.12251] [Citation(s) in RCA: 8] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Abstract
The purpose of this study is to determine whether it is possible to make breast cancer screening more efficient in those with dense breasts. Over 12 states require that patients with dense breasts receive notification about their breast density in lay letters that are sent after the screening mammogram. Some of these letters advise patients to speak with their primary care providers about the possibility of supplemental breast cancer screening. We sought to determine whether primary care providers can discuss breast density and recommend supplemental breast cancer screening using the density of the previous mammography. This would reduce the burden of additional appointments and might increase the number of patients choosing to have supplemental screening. The mammographic breast density of 250 consecutive patients from May 2011 to September 2011 was compared with the immediate prior mammogram. Patients whose prior mammograms were more than 36 months prior or less than 8 months prior to the current exam were excluded, leaving 217 patients. The proportion of patients with breast density change was analyzed. The concordance of breast density between the two exams was assessed and the effects of patient age and the length of time between mammograms were examined. The breast density of the current and most recent prior mammogram was stable for 86.6% of patients. Neither age nor length of time between mammograms affected concordance. Primary care providers can decrease the need for multiple appointments and decrease patient anxiety by discussing breast density and screening choices prior to the patient's screening mammography. The great majority of patients will receive the correct information about their breast density by using a prior report.
Collapse
|
32
|
Introductory pictorial atlas of 3D tomosynthesis. Clin Imaging 2014; 38:18-26. [DOI: 10.1016/j.clinimag.2013.05.004] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2013] [Accepted: 05/20/2013] [Indexed: 10/26/2022]
|
33
|
Routine admission chest x-ray in the management of hospitalized patients. Invest Radiol 1986; 21:296. [PMID: 3957607] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/08/2023]
|