Mammography Reports Research Articles

Breast Arterial Calcifications on Mammography: Awareness and Reporting Preferences Amongst Referring Physicians in Canada.

Purpose: Breast arterial calcifications (BAC) on mammography have been correlated with increased cardiovascular risk. The Canadian Society of Breast Imaging released a position statement on BAC reporting in January 2023. This study evaluates the awareness of the clinical significance of BAC and reporting preferences of referring physicians in Canada. Methods: A 15-question survey was distributed to Canadian physicians who may review mammography results via regional and subspecialty associations and on social media following local institutional ethical approval. Responses were collected over 10 weeks from February to April 2023. Results: Seventy-two complete responses were obtained. We are unable to determine the response rate, given the means of distribution. Only 17% (12/72) of responding physicians were previously aware of the association between BAC and increased cardiovascular risk, and 51% (37/72) preferred the inclusion of BAC in the mammography report. Fifty-six percent (40/72) indicated that BAC reporting would prompt further investigation, and 63% (45/72) would inform patients that their mammogram showed evidence of BAC. Sixty-nine percent (50/72) would find grading of BAC beneficial and 71% (51/72) agreed that there is a need for national guidelines. Conclusion: Less than a quarter of responding Canadian referring physicians were previously aware of the association between BAC and cardiovascular risk, although half of respondents indicated a preference for BAC reporting on mammography. Most participating physicians would inform their patients of the presence of BAC and consider further cardiovascular risk management. There was consensus that a national BAC grading system and clinical management guidelines would be beneficial.

Comparative evaluation of image-based vs. text-based vs. multimodal AI approaches for automatic breast density assessment in mammograms

Background and objectivesIn the last decade, there has been a growing interest in applying artificial intelligence (AI) systems to breast cancer assessment, including breast density evaluation. However, few models have been developed to integrate textual mammographic reports and mammographic images. Our aims are (1) to generate a natural language processing (NLP)-based AI system, (2) to evaluate an external image-based software, and (3) to develop a multimodal system, using the late fusion approach, by integrating image and text inferences for the automatic classification of breast density according to the American College of Radiology (ACR) guidelines in mammograms and radiological reports. MethodsWe first compared different NLP models, three based on n-gram term frequency – inverse document frequency and two transformer-based architectures, using 1533 unstructured mammogram reports as a training set and 303 reports as a test set. Subsequently, we evaluated an external image-based software using 303 mammogram images. Finally, we assessed our multimodal system taking into account both text and mammogram images. ResultsOur best NLP model achieved 88 % accuracy, while the external software and the multimodal system achieved 75 % and 80 % accuracy, respectively, in classifying ACR breast densities. ConclusionAlthough our multimodal system outperforms the image-based tool, it currently does not improve the results offered by the NLP model for ACR breast density classification. Nevertheless, the promising results observed here open the possibility to more comprehensive studies regarding the utilization of multimodal tools in the assessment of breast density.

Recall Laterality and Bilaterality: Possible New Screening Mammography Quality Metrics

Purpose: Current screening mammography quality metrics are important and helpful, but do not address all quality concerns. An individual screening mammography reader may be systematically insensitive to findings present in the breast of one side, laterality bias, evidenced by left versus right difference in advised immediate recalls. Current metrics are not designed to detect laterality bias. Whether a reader exhibits laterality bias, or what an appropriate ratio/range of bilateral versus unilateral recalls should be, have never been discussed in medical literature. Methods: As a trainee quality project, five attending (‘consultant’ in Europe) radiologists’ screening mammography reports over 2 years at an academically affiliated, public hospital were tallied with regard to laterality of recommended recall, and with respect to unilateral versus bilateral recalls advised. The chi-square (χ²) statistic was applied to reports advising unilateral recall. Findings: No group laterality bias was discovered. One radiologist (the most experienced) evidenced a consistent laterality bias over 2 years (p=0.07) against left-breast findings. Of reports recommending recall, the radiologists’ single-year range for recall regarding both breasts was 10.2–23.3%; for both years combined, the individual radiologists ranged from 13.6–17.9%. The group, 2-year mean recommending bilateral recall was 16.5%. Conclusion: A radiologist may exhibit laterality bias, favoring detection of findings in one breast over the other, a concern never before considered. Audit to discern such bias leads simultaneously to assessment of bilateral recall bias. Possible causes of these biases are discussed, and research regarding them as possible quality metrics is encouraged.

Interpretation of immediately released health information: Informing patient medical education in breast oncology

BackgroundThe Cures Act mandated immediately released health information. In this study, we investigated patient comprehension of mammography reports and the utility of online resources to aid report interpretation. MethodsPatients who received a normal mammogram from February to April 2022 were invited to complete semi-structured interviews paired with health literacy questionnaires to assess patient's report comprehension before and after internet search. ResultsThirteen selected patients via purposeful sampling completed interviews. Most patients described their initial understanding of the mammography report as “good” and improved to between “good” and “very good” after an internet search. Patients suggested “a little column on the side" for medical terminology, “an extra prompt" for making an appointment, or a recommendation for “good sites” to improve mammography reports. ConclusionPatients varied in their ability to independently interpret medical reports and seek additional resources. While online resources marginally improved patient understanding, actionable and clear resources are needed.

Automatic Classification of BI-RADS in Mammography Reports Using Data Fusion

Automatic Classification of BI-RADS in Mammography Reports Using Data Fusion

A novel technology for harmonizing and analyzing cancer data. Observations from integrating health connect in Newfoundland and Labrador, Canada.

Objective: This article aims to describe the implementation of a new health information technology system called Health Connect that is harmonizing cancer data in the Canadian province of Newfoundland and Labrador; explain high-level technical details of this technology; provide concrete examples of how this technology is helping to improve cancer care in the province, and to discuss its future expansion and implications. Methods: We give a technical description of the Health Connect architecture, how it integrated numerous data sources into a single, scalable health information system for cancer data and highlight its artificial intelligence and analytics capacity. Results: We illustrated two practical achievements of Health Connect. First, an analytical dashboard that was used to pinpoint variations in colon cancer screening uptake in small defined geographic regions of the province; and second, a natural language processing algorithm that provided AI-assisted decision support in interpreting appropriate follow-up action based on assessments of breast mammography reports. Conclusion: Health Connect is a cutting-edge, health systems solution for harmonizing cancer screening data for practical decision-making. The long term goal is to integrate all cancer care data holdings into Health Connect to build a comprehensive health information system for cancer care in the province.

Breast cancer screening outcomes and risk assessment among women of Abha city, Saudi Arabia

Breast cancer is one of the most common cancers among women and the leadingcause of death related to cancers. This study focuses on the screening of breast cancer for earlydetection of breast cancer and identification of risk factors for the development of breast cancer. This cross-sectional study was conducted among the female participants who were registered for the breast cancer screening program conducted by King Khalid University, Abha under the supervision of Family and Community Medicine, Department of College of Medicine. Convenience sampling was done and a total of 331 patients were selected for the study. The collected data were coded and entered into an Excel software (Microsoft Office Excel 2010) database. Data was analyzed using Statistical Package for Social Sciences, version 16 (SPSS, Inc., Chicago, IL, USA). p < 0.05 was considered statistically significant. Out of 331 individuals only 3 (0.9%) were diagnosed with breast cancer. Three cases ofinvasive ductal carcinoma were identified among individuals with breast cancer. While 4 (1.2%) individuals had benign findings, such as fibroadenoma, ductal ectasia, sclerosing adenosis, andtissue fibrosis. Past surgical history, past radiotherapy/chemotherapy, and maternal problemsduring pregnancy were significantly associated with varying levels of breast cancer risk. Breastcomplaints show a significant association with breast cancer indicating the need for furtherinvestigation. Findings from physical examinations, mammography reports, breast ultrasound, biopsy referrals, biopsy results, and management plans all show significant relationships withbreast cancer risk. Our study findings indicate the need for health education for the prevention of breastcancer risk factors and the implementation of regular screening programs for the early detectionof the disease in the community.

The challenging diagnosis of granular cell tumor of the breast: a case report

Conventional granular cell tumors, derived from Schwann cells, occur in soft tissues and are mostly benign. It is also recognized as Abrikossoff's tumor or granular cell myoblastoma, and the most common locations are found in the head, neck, arms, esophagus, and respiratory tract. The incidence in the breast is rare, representing only 8% of granular cell tumors. However, it is important to consider it as a differential diagnosis when investigating breast nodules due to its misleading presentation. This is a challenging diagnosis considering that the clinical examination and imaging workup may suggest signs of malignancy. Therefore, the lack of histopathological analysis may lead to erroneous conclusions and therapies. Due to non-specific imaging and physical examination findings, a biopsy of the lesion is mandatory for diagnosis. The tumor’s microscopic criteria consist of the presence of large polygonal cells, with eosinophilic, granular, and abundant cytoplasm. The cell borders are indistinct and the growth pattern is infiltrative, with perineural and possible perivascular involvement; however, mitotic figures are rare. The present case report demonstrates the importance of anatomopathological analysis for this diagnosis. It refers to a female patient, 28 years old, complaining of a breast node. She was followed up in the Mastology Department for further investigation, with a mammography report identifying a speculated nodule, with undefined margins, classified as Bi-Rads 5 in the right breast, and an ultrasound reporting a Bi-Rads 4C solid nodule. The clarification was made through biopsy, which determined microscopy compatible with the rare tumor of granular cells in the breast, in addition to the immunohistochemical profile, which differentiated the tumor variant of non-neural origin, composed of ovoid cells with eosinophilic granules, presenting nuclear pleomorphism, atypia, and mitotic figures.

Protocol for a pragmatic stepped wedge cluster randomized clinical trial testing behavioral economic implementation strategies to increase supplemental breast MRI screening among patients with extremely dense breasts

BackgroundIncreased breast density augments breast cancer risk and reduces mammography sensitivity. Supplemental breast MRI screening can significantly increase cancer detection among women with dense breasts. However, few women undergo this exam, and screening is consistently lower among racially minoritized populations. Implementation strategies informed by behavioral economics (“nudges”) can promote evidence-based practices by improving clinician decision-making under conditions of uncertainty. Nudges directed toward clinicians and patients may facilitate the implementation of supplemental breast MRI.MethodsApproximately 1600 patients identified as having extremely dense breasts after non-actionable mammograms, along with about 1100 clinicians involved with their care at 32 primary care or OB/GYN clinics across a racially diverse academically based health system, will be enrolled. A 2 × 2 randomized pragmatic trial will test nudges to patients, clinicians, both, or neither to promote supplemental breast MRI screening. Before implementation, rapid cycle approaches informed by clinician and patient experiences and behavioral economics and health equity frameworks guided nudge design. Clinicians will be clustered into clinic groups based on existing administrative departments and care patterns, and these clinic groups will be randomized to have the nudge activated at different times per a stepped wedge design. Clinicians will receive nudges integrated into the routine mammographic report or sent through electronic health record (EHR) in-basket messaging once their clinic group (i.e., wedge) is randomized to receive the intervention. Independently, patients will be randomized to receive text message nudges or not. The primary outcome will be defined as ordering or scheduling supplemental breast MRI. Secondary outcomes include MRI completion, cancer detection rates, and false-positive rates. Patient sociodemographic information and clinic-level variables will be examined as moderators of nudge effectiveness. Qualitative interviews conducted at the trial’s conclusion will examine barriers and facilitators to implementation.DiscussionThis study will add to the growing literature on the effectiveness of behavioral economics-informed implementation strategies to promote evidence-based interventions. The design will facilitate testing the relative effects of nudges to patients and clinicians and the effects of moderators of nudge effectiveness, including key indicators of health disparities. The results may inform the introduction of low-cost, scalable implementation strategies to promote early breast cancer detection.Trial registrationClinicalTrials.gov NCT05787249. Registered on March 28, 2023.

Construction of a knowledge graph for breast cancer diagnosis based on Chinese electronic medical records: development and usability study

BackgroundElectronic medical records (EMRs) contain a wealth of information related to breast cancer diagnosis and treatment. Extracting relevant features from these medical records and constructing a knowledge graph can significantly contribute to an efficient data analysis and decision support system for breast cancer diagnosis.MethodsAn approach was proposed to develop a workflow for effectively extracting breast cancer-related features from Chinese breast cancer mammography reports and constructing a knowledge graph for breast cancer diagnosis. Firstly, the concept layer of the knowledge graph for breast cancer diagnosis was constructed based on breast cancer diagnosis and treatment guidelines, along with insights from clinical experts. .Next, a BiLSTM-Highway-CRF model was designed to extract the mammography features, which formed the data layer of the knowledge graph. Finally, the knowledge graph was constructed by combining the concept layer and the data layer in a Neo4j graph data platform, and then applied in visualization analysis, semantic query and computer assisted diagnosis.ResultsMammographic features were extracted from a total of 1171 mammography examination reports. The overall extraction performance of the model achieved an accuracy rate of 97.16%, a recall rate of 98.06%, and a F1 score of 97.61%. Additionally, 47,660 relationships between entities were identified based on the four different types of relationships defined in the concept layer. The knowledge graph for breast cancer diagnosis was constructed after inputting mammographic features and relationships into the Neo4j graph data platform. The model was assessed from the concept layer, data layer, and application layer perspectives, and showed promising results.ConclusionsThe proposed workflow is applicable for constructing knowledge graphs for breast cancer diagnosis based on Chinese EMRs. This study serves as a reference for the rapid design, construction, and application of knowledge graphs for diagnosis and treatment of other diseases. Furthermore, it offers a potential solution to address the issues of limited data sharing and format inconsistencies present in Chinese EMR data.

Clinical-Epidemiologic Characterization of Patients with Breast Cancer in a Family Medicine Unit

Objective: analyze the clinical-epidemiological characterization of patients with breast cáncer in the Family Medicine Unit (umf) No. 9, of the Mexican Institute of Social Security (imss) in Acapulco, Mexico from 2018 to 2021. Methods: cross-sectional, descriptive, retrospective study which included 71 patients with a positive diagnosis of breast cancer, assigned to the FMU No. 9, in Acapulco, Mexico, from 2018 to 2021. The studied population was obtained from the Institutional Cancer Registry of the Epidemiology system; the source of information was the electronic clinical record, from which clinical-epidemiological information, mammography report, histopathological result, and clinical stage were collected. Descriptive statistics were performed using simple frequencies and percentages with the obtained data. Results: 46.4% (33/71) of breastcancer cases were registered in 2018. 32.4% were 61-70 years old, 98.6% were women, 42.3% were overweight, and 31.0% had type 2 diabetes mellitus (dm2). According to the bi-rads (b) classification, 38.0% presented a b4. Regarding the histopathological report, ductal carcinoma was the most common with 76.1% (54/71). Conclusions: a significant percentage of breast cancer was detected in patients who were overweight, and had type 2 diabetes mellitus, nearly 40% of the patients had lesions of intermediate suspicion of malignancy, while three quarters of the patients presented with ductal carcinoma. It is extremely important to strengthen the primary care level through health promotion, and encourage breast and clinical self-examination during the first medical contact to detect risk factors and clinical signs suggestive of the disease, which will reduce morbidity and mortality.

Comparison of the duration of generating radiological protocols with keyboard and voice input

BACKGROUND: Speech recognition is becoming increasingly common in the national healthcare system. One of the first specialties to implement this technology on a large scale was radiology. However, the efficiency of voice input and its effect on the length of time required to complete medical records remain unresolved.
 AIM: To assess the efficiency of speech recognition in generating radiological protocols of different modalities and types.
 METHODS: The retrospective study was conducted at the Moscow Reference Center of the Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies of the Moscow Department of Health. A total of 12,912 radiological reports on fluorography, mammography, chest computed tomography (CT), contrast-enhanced magnetic resonance imaging (MRI) of the brain, and contrast-enhanced CT of the abdomen and pelvis were included in the study by simple random sampling. The size of all samples exceeded 766 reports, calculated with regard to the size of the general population of over 100,000 reports. The Voice2Med software was used to fill in the radiological protocols. Intergroup comparison was performed using the MannWhitney U-test with a statistical significance level of 0.05.
 RESULTS: The average duration of generating fluorographic protocols in the keyboard and voice input groups was 189.9 s (0:03:09) and 236.2 s (0:03:56), respectively (p 0.0001). For mammographic reports, the duration was 387.1 s (0:06:27) and 444.8 s (0:07:24), respectively (p 0.0001). For radiographic reports, it amounted to 247.8 s (0:04:07) and 189.0 s (0: 03:09), respectively (p 0.0001), and for chest CT, it was 379.7 s (0:06:19) and 382.7 s (0:06:22), respectively (p=0.12). For MRI of the brain, the protocols were generated for 709.9 s (0:11:49) and 559.9 s (0: 09:19), respectively (p 0.0001), and for contrast-enhanced chest, abdominal, and pelvic CT scans, it took 2714.6 s (0:45:15) and 1778.4 s (0:29:38), respectively. Voice input slowed down the preparation time of mammographic and fluorographic protocols. This is due to the use of a structured electronic medical document in medical facilities to describe the results of the examinations. Speech recognition showed the greatest efficiency in generating MRI and CT protocols. Such reports contain a large number of pathological changes, both target and incidental findings, which requires a detailed description by the radiologist in the examination protocol.
 CONCLUSIONS: Speech recognition in generating radiological protocols showed different efficiency depending on the modality and type of the radiological protocol filled in using the voice input system. This approach is optimal for describing CT and MRI scans.

Pacemaker in patients undergoing mammography: A limitation for breast cancer diagnosis?

A pacemaker may affect the utility of a mammogram in several ways. The aim of this study is to summarize our institution's experience with mammograms among patients with a cardiac pacemaker, focusing on the diagnostic workup among patients with a newly diagnosed ipsilateral breast cancer. A retrospective search of all mammography reports between January 2011 and April 2021 was conducted for identifying cases of patients with a pacemaker. Demographic and clinical characteristics as well as mammography-derived quality parameters and findings were categorized and statistically compared. The incidence of pacemaker concurrence in mammographic examination, although apparently slightly under-documented, accounted for 0.33% of cases. Population mean age was 71.7 years, and most patients (79%) had a left-sided pacemaker. The pacemaker was much more likely to be projected on the medio-lateral-oblique (96%) than on the cranio-caudal view (10%), on the axilla rather than the breast, and on the retro-pectoral rather than the pre-pectoral region (P < 0.001 for all). Compression force decreased by up to 23.0% (P < 0.001) and breast thickness increased by up to 9.5% (P < 0.001) for the ipsilateral vs. the contralateral side. Among 11 patients with newly diagnosed ipsilateral breast cancer, the pacemaker partially projected on the tumour region in two cases, and significantly obscured the tumour in another two. Although rare, the coexistence of a pacemaker in patients undergoing mammography is associated with reduced image quality due to suboptimal breast visualization and reduced compression, and as a result, this may eventually lead to decreased diagnostic efficacy.

Abstract P6-05-38: Breast Density Notification: Impact on anxiety, breast cancer worry, and self-perceived risk among Latinas at a federally qualified medical center

Abstract Mammographic breast density (MBD) has been shown to be a strong, independent risk factor for breast cancer (BC) irrespective of race/ethnicity. Given the risk association of MBD and its potential to mask tumors on a mammogram, state and federal laws have mandated that women receive information regarding their personal MBD in their mammography reports. However, concerns have been raised regarding the impact of MBD notification on patient anxiety, especially written information for women who experience health disparities such as racial/ethnic minorities, lower health literacy, limited English proficiency and lower socioeconomic status. We performed a randomized controlled clinical trial to examine the impact of three different written and interpersonal approaches to MBD notification on patient anxiety, BC worry, and self-perceived BC risk, among Latinas receiving routine mammography screening at a federally qualified medical center (FQHC). We hypothesized that interpersonal education would reduce anxiety and worry, relative to the written notifications alone. The study was performed at the Baseline Clinic of Mountain Park Health Center, a FQHC in Phoenix, AZ. Women between ages 40 and 74 years presenting for screening mammogram were eligible. After providing signed informed consent, participants were randomized equally to usual care (UC- mailed notification letter); enhanced care (notification letter and MBD educational brochure designed for this study): interpersonal care (notification letter, brochure, promotora education via telephone). A stratified block randomization procedure was used with age &amp;gt; 50 years (yes vs no), ethnicity (Hispanic vs non-Hispanic), and language preference (Spanish vs. English) as strata. Study participants completed surveys at the time of enrollment/pre-intervention (T0), at two weeks to six months after intervention was delivered (T1), and about one year after randomization (T2). Anxiety state was measured using the state anxiety subscale of the State-Trait Anxiety Inventory scale (STAI-S) (range from 20-80). BC worry was probed using the question: “How frequently do you worry about getting breast cancer someday”. The self-perceived lifetime risk of BC was rated between 0% (no chance of BC) to 100% (definitely will get BC). The proportion of participants with an increase or persistence of higher level for each outcome between time points was compared between the three study groups. The study was approved by the Mayo Clinic Institutional Review Board. 1332 Latina women were enrolled and randomized between October 2016 and October 2019. All completed the baseline (T0) survey, 928 completed T1, 632 completed T2, and 516 completed both T1 and T2 surveys. At study entry, majority of the participants were young (64.1% between age 40-49 years), had no family history of breast cancer (81.0%), had less than high school education (68.8%), and were married or partnered (67.8%). At T0, the mean (SD) anxiety STAI score was 32.5 (11.1); 51.8% with moderate or severe anxiety (score &amp;gt; 30). With regard to BC worry, 41.3% reported worrying “sometimes”, “often”, or “almost all the time”. Further, 25.4% reported a self-perceived lifetime risk of developing BC of &amp;gt;10% while only 6.6% had a Gail model estimated lifetime risk score of &amp;gt;10%. There was no significant difference in changes in anxiety, BC worry or self-perceived risk from T0 to either T1 or T2 surveys between the intervention groups. In summary, this study found high levels of baseline anxiety and BC worry (despite the majority being 40-49 years old and having no family history of BC) which persisted regardless of how notification and education were delivered. Future work is needed to improve the understanding of factors that could lower anxiety and BC worry and improve risk perception in this population. Citation Format: Karthik Ghosh, Sarah Jenkins, Jennifer Ridgeway, Jessica D. Austin, Bijan Borah, Bhavika K. Patel, Deborah Rhodes, Aaron Norman, Edna P. Ramos, Matt Jewett, Crystal Gonzalez, Valentina Hernandez, Davinder Singh, Vera Suman, Celine Vachon. Breast Density Notification: Impact on anxiety, breast cancer worry, and self-perceived risk among Latinas at a federally qualified medical center. [abstract]. In: Proceedings of the 2022 San Antonio Breast Cancer Symposium; 2022 Dec 6-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2023;83(5 Suppl):Abstract nr P6-05-38.

One-year results of the national breast and cervical cancer screening program: Giresun province in the black sea region

Background/Aim: Increasing the survival rate of patients with breast and cervical cancers is possible by early diagnosis through screening individuals for cancer in the asymptomatic period. Especially during the COVID-19 pandemic period, the possibility of early diagnosis in breast and cervical cancers has decreased due to the decrease in cancer screening applications. The aim of cancer screening is to increase the survival of patients by detecting precancerous lesions early. The purpose of our study is to evaluate the application and results of breast and cervical cancer screening in the Black Sea region’s Giresun province. Methods: This is a cross-sectional and descriptive study. The results of patients who were admitted to the Giresun Early Diagnosis Cancer Screening and Education Center between July 1, 2021, and June 28, 2022, were examined. The mammography report results of women aged 40–69 years who applied to the cancer screening center for breast cancer screening, and the HPV and Pap smear results of the patients aged 30–65 years who applied for cervical cancer screening, were evaluated retrospectively through the public health management system. Mammography results were evaluated with BIRADS (Breast Imaging Reporting and Dated System) scoring. The type of HPV and the cytology results from cervical swab samples were analyzed for cervical cancer screening. Results: A total of 3567 people underwent mammography. Per the mammography results, the percentage of those with BIRADS 0 was 7.7% (n=278), the percentage of those with BIRADS 1–2 was 91% (n=3256), the percentage of those with BIRADS 4 was 0.7% (n=25), and the percentage of those with BIRADS 5 was 0.14% (n=5). HPV-DNA and cervical cytology examinations were performed for cervical cancer screening in 2326 patients. As a result of cervical cancer screening, HPV positivity was found in 6.44% (n=150) patients, and 14 different HPV types were found in the positive samples. When HPV types were examined, the two most common types were HPV type 16 (13.6%) and type 56 (11.9%). When the HPV types were examined in the positive samples, the two most common types were HPV type 16 (13.6%) and type 56 (11.9%). HPV type 18 was the least detected HPV type in patients (3.7%). When the Pap smear screening results of the 150 cases with positive screening results were examined, 3.33% were ASC-US (atypical squamous cells of undetermined significance), 22% were reported as infection, and 62.6% were normal. Conclusion: The role of primary care physicians directing patients registered in their coverage area to cancer screening programs is especially effective in raising society’s awareness and education on the issue. As a result, it is important that primary care physicians and related specialist physicians, together with cancer early detection and screening centers, adopt a supportive stance towards these programs in order for them to be implemented effectively.

Possibilities and limitations of using machine text-processing tools in Russian radiology reports

BACKGROUND: In radiology, important information can be found not only in medical images, but also in the accompanying text descriptions created by radiologists. Identification of study protocols containing certain data and extraction of these data can be useful primarily for clinical problems; however, given the large amount of such data, the development of machine analysis algorithms is necessary.&#x0D; AIM: To estimate the possibilities and limitations of using a tool for machine processing of radiology reports to search for pathological findings.&#x0D; MATERIALS AND METHODS: To create an algorithm for automatic analysis of radiology reports, use cases were selected that participated in the experiment on the use of innovative technologies in the computer vision for the analysis of medical images in 2020. Mammography, chest X-ray, chest computed tomography (CT), and LDCT, were among the use cases performed in Moscow. A dictionary of keywords has been compiled. After the automatic marking of the reports by the developed tool, the results were assessed by a radiologist. The number of protocols analyzed by the radiologist for training and validation of the algorithms was 977 for mammography, 4,804 for all chest X-ray scans, 4,074 for chest CT, and 398 for chest LDCT. For the final testing of the developed algorithms, test datasets of 1,032 studies for mammography, 544 for chest X-ray, 5,000 for CT of the chest, and 1,082 studies for the LDCT of the chest were additionally labeled.&#x0D; RESULTS: The best results were achieved in the search for viral pneumonia in chest CT reports (accuracy 0.996, sensitivity 0.998, and specificity 0.989) and breast cancer in mammography reports (accuracy 1.0, sensitivity 1.0, and specificity 1.0). When searching for signs of lung cancer by the algorithm, the metrics were as follows: accuracy 0.895, sensitivity 0.829, and specificity 0.936, when searching for pathological changes in the chest organs in radiography and fluorography protocols (accuracy 0.912, sensitivity 1.000, and specificity 0.844).&#x0D; CONCLUSIONS: Machine methods with high accuracy can be used to automatically classify the radiology reports of mammography and chest CT with viral pneumonia. The achieved accuracy is sufficient for successful application to automatically compare the conclusions of physicians and artificial intelligence models when searching for signs of lung cancer in chest CT and LDCT, pathological findings in chest X-ray.

Association of coffee intake and its polyphenols with mammographic findings in women who visited the Brazilian Public Health Service.

Objective: this study aimed to evaluate if there is an association of intake of coffee and its polyphenols with mammographic findings in women treated at a breast care service unit of the Unified Health System (SUS), Brazil. Research methods and procedures: this was a cross-sectional study with 532 women treated at a health service. The participants were divided according to their mammographic reports into two groups: without and with altered findings. Two 24-h dietary recalls were applied and coffee consumption was categorized into three groups (less than 1 cup, 1 to 3 cups, and more than 3 cups). Phenolic acids were determined using the Phenol Explorer program. The intake of polyphenols was calculated by adding the values obtained from the total amount of coffee consumed during the day. The Multiple Source Method (MSM) was applied to analyze the usual intake. Results: of the 532 women, 178 (33.5 %) had altered mammographic findings. The participants' average daily coffee intake was 193.4 mL. No significant association was found between coffee consumption and mammographic findings. However, it was found that the second tertile of polyphenols was a protective factor for breast changes. Conclusion: Coffee polyphenols are protective against breast changes in the group evaluated and, thus, can help prevent breast cancer.

Abstract 12241: Correlation of Breast and Coronary Artery Calcification and Associated Cardiovascular Risks

Introduction: There is a known association between microvascular breast artery calcifications (BAC) and atherosclerotic cardiovascular disease. Similarly, coronary artery calcification (CAC) has been shown to have association with 10-year ASCVD risk. Using an investigational artificial intelligence software, we sought to determine if a relationship exists between BAC and CAC severity on CT imaging obtained for non-cardiac reasons and whether this relationship has prognostic implications for major adverse cardiac events (MACE). Methods: A single center retrospective pilot study of patients who underwent CT chest imaging for non-cardiac issues and had also undergone a routine screening mammogram within one year. A database created by our central imaging archives for patients with known CAC and BAC was utilized. CAC severity was scored using the semi-quantitative Weston method. BAC severity (termed Bradley score) was scored by cmAngio R , an automated software created by CureMetrix. Results: Seventy-three patients were included for BAC analysis during a median follow-up of 85 months. A mean Bradley score by cmAngio of 10.40 was significantly associated with low risk of CAC (0-2 Weston). A mean Bradley score for moderate (3-7 Weston) and high (&gt; 7 Weston) risk of CAC was 19.70 and 42.64, respectively. The results were statistically significant (p=0.0222). A CAC total score ≥5 was previously published by us to be the optimal cutoff value for predicting MACEs. Conclusions: This retrospective pilot study confirms a relationship exists between patients found to have BAC as identified by an investigational artificial intelligence software on routine mammogram and CAC on CT imaging obtained for non-cardiac reasons. The addition of routine disclosure of BAC on mammographic reports may be of clinical value to capture patients who may not meet traditional guidelines for coronary atherosclerosis risk stratification and may help primary care clinicians begin discussions about lifestyle modifications and potential treatment directed towards primary prevention of MACE.

Patient and Radiologist Demographics Influence Perceptions of Screening Mammography Reports.

The aim of this study was to test whether patient and radiologist demographics influence perceptions of screening mammography reports and the interpreting radiologist. Patients presenting for breast imaging were surveyed. Demographics were collected, and each participant was shown five mock screening mammography reports with BI-RADS category 2 findings, each with a recommendation for 1-year screening. Each report included a picture of the interpreting radiologist, who was Black or White and male or female. Participants answered seven questions, on a Likert-type scale, about understanding, satisfaction, and trust in the report and radiologist. Generalized estimating equation ordinal logistic regression compared responses on the basis of participant and radiologist demographics. A total of 178 women participated, with a mean age of 55.1 ± 10.2 years. Most participants self-identified as White (71%) orBlack (20%) and non-Hispanic (98%), with broad educational representation (28% with bachelor's degrees and 28% with master's degrees). After controlling for demographics, Black participants reported greater agreement regarding trust in the report's finding (P=.037) if the radiologist was also Black. Black participants were less likely to be satisfied in the report quality (P= .043). Additionally, participants without any college education reported lower agreement that they were satisfied with the report quality (P=.020) and felt the radiologist cares about his or her patients (P= .037). There were no significant associations for radiologist sex or participant age. Participant perceptions of screening mammography reports and the interpreting radiologist can be influenced by participant and provider race as well as participant education. These findings could have implications for mammography adherence, breast radiologist recruitment, and developing patient-centric reports.

Introduction to Breast Screening and Diagnosis

In this focus issue on emerging topics in breast cancer, many diverse themes are explored and are timely given the current state of this topic as well as the changing landscape of breast cancer detection and care. Miles et al. [1] show that general health-related cost concerns is associated with decreased screening mammography utilization. This highlights the importance of understanding the social context of our patients to continue to improve care delivery. For example, as practices continue to focus on diversity, equity and inclusion efforts to ensure that physicians and providers reflect the range of patients’ lived experiences, Grimm et al demonstrate patient trust in screening mammography reports are associated with radiologist-patient race concordance among Black patients [2].