Screening Mammograms Research Articles

Discrimination in the medical setting among LGBTQ+ adults and associations with cancer screening.

Lesbian, gay, bisexual, transgender, queer, and other sexual and gender diverse (LGBTQ+) individuals experience disparities in cancer screening. We examined whether experience of LGBTQ+ -related discrimination in medical settings was associated with cancer screening disparities. Participants were recruited via social media for a cross-sectional survey study. Those who self-reported as LGBTQ+ , being 40+ years of age, and residing in the US were eligible. Participants reported their clinical and demographic characteristics, cancer screening history, and experiences of discrimination in a medical setting. We examined the odds (OR) of ever undergoing cancer screening by experienced discrimination, stratified by sex assigned at birth. Participants (n = 310) were on average 54.4 ± 9.0years old and primarily White (92.9%). Most identified as lesbian (38.1%) or gay (40.0%) while 17.1% were transgender or gender diverse. Nearly half (45.5%) reported experiencing LGBTQ+ -related discrimination in the medical setting. Participants assigned female at birth with discriminatory experiences had significantly lower odds of ever undergoing colonoscopy/sigmoidoscopy compared to those without discriminatory experiences (OR: 0.37; 95% Confidence Interval (CI) 0.15-0.90). No significant differences in colonoscopy/sigmoidoscopy uptake were observed in those assigned male at birth by discriminatory experiences (OR: 2.02; 95% CI 0.59-6.91). Pap tests, mammogram, and stool colorectal cancer screening did not differ by discriminatory experience. Discrimination in medical settings was commonly reported by LGBTQ+ individuals in this study. When treating LGBTQ+ patients, clinicians should ask about prior experiences and continue to promote cancer screening. Future studies should examine discrimination as a key driver of LGBTQ+ disparities in cancer screening.

Mammographic density and breast cancer risk among Black American women.

High mammographic density is a well-established risk factor for breast cancer; however, data from Black women are limited. It is largely unknown how mammographic density is associated with breast cancer subtypes among Black women. We examined the association between percent mammographic density (PMD) and breast cancer risk among participants in the Black Women's Health Study. Digital screening mammograms were available for 363 cases and 5541 non-cases. Cumulus software was used to assess PMD. We used inverse probability of sampling weights and Cox proportional hazards models, adjusted for age and body mass index, to estimate hazard ratios (HRs) and 95% confidence intervals (CIs) overall and by age at mammography and estrogen receptor (ER) status of the breast tumors. Multivariable models included additional breast cancer risk factors. Tests of statistical significance were 2-sided. In simple models, women in the highest quartile of PMD had 53% increased odds of breast cancer compared to those in the lowest quartile (HR 1.53; 95% CI: 1.11, 2.11). HRs were 1.37 (95% CI: 0.83, 2.24) among women <55 years of age and 1.68 (95% CI: 1.10, 2.56) among women aged ≥55 years. HRs were 1.49 (95% CI: 1.02, 2.16) for ER+ cancer and 1.45 (95% CI: 0.73, 2.87) for ER- cancer. Associations were largely unchanged in multivariable models. In this study of U.S. Black women, higher PMD was associated with ER+ and ER- breast cancer risk. Findings from this study reinforce the importance of breast density as a risk factor for breast cancer in Black women.

External Validation of a Commercial Artificial Intelligence Algorithm on a Diverse Population for Detection of False Negative Breast Cancers.

There are limited data on the application of artificial intelligence (AI) on nonenriched, real-world screening mammograms. This work aims to evaluate the ability of AI to detect false negative cancers not detected at the time of screening when reviewed by the radiologist alone. A commercially available AI algorithm was retrospectively applied to patients undergoing screening full-field digital mammography (FFDM) or digital breast tomosynthesis (DBT) at a single institution from 2010 to 2019. Ground truth was established based on 1-year follow-up data. Descriptive statistics were performed with attention focused on AI detection of false negative cancers within these subsets. A total of 26 694 FFDM and 3183 DBT examinations were analyzed. Artificial intelligence was able to detect 7/13 false negative cancers (54%) in the FFDM cohort and 4/10 (40%) in the DBT cohort on the preceding screening mammogram that was interpreted as negative by the radiologist. Of these, 4 in the FFDM cohort and 4 in the DBT cohort were identified in breast densities of C or greater. False negative cancers detected by AI were predominantly luminal A invasive malignancies (9/11, 82%). Artificial intelligence was able to detect these false negative cancers a median time of 272 days sooner in the FFDM cohort and 248 days sooner in the DBT cohort compared to the radiologist. Artificial intelligence was able to detect cancers at the time of screening that were missed by the radiologist. Prospective studies are needed to evaluate the synergy of AI and the radiologist in real-world settings, especially on DBT examinations.

Radiomic Analysis of Cohort-Specific Diagnostic Errors in Reading Dense Mammograms Using Artificial Intelligence.

This study aims to investigate radiologists' interpretation errors when reading dense screening mammograms using a radiomics-based artificial intelligence approach. Thirty-six radiologists from China and Australia read 60 dense mammograms. For each cohort, we identified normal areas that looked suspicious of cancer and the malignant areas containing cancers. Then radiomic features were extracted from these identified areas and random forest models were trained to recognize the areas that were most frequently linked to diagnostic errors within each cohort. The performance of the model and discriminatory power of significant radiomic features were assessed. We found that in the Chinese cohort, the AUC values for predicting false positives were 0.864 (CC) and 0.829 (MLO), while in the Australian cohort, they were 0.652 (CC) and 0.747 (MLO). For false negatives, the AUC values in the Chinese cohort were 0.677 (CC) and 0.673 (MLO), and in the Australian cohort, they were 0.600 (CC) and 0.505 (MLO). In both cohorts, regions with higher Gabor and maximum response filter outputs were more prone to false positives, while areas with significant intensity changes and coarse textures were more likely to yield false negatives. This cohort-based pipeline proves effective in identifying common errors for specific reader cohorts based on image-derived radiomic features. This study demonstrates that radiomics-based AI can effectively identify and predict radiologists' interpretation errors in dense mammograms, with distinct radiomic features linked to false positives and false negatives in Chinese and Australian cohorts.

Exploring the impact of work experience on the detection of specific cancers across different breast density levels on screening mammograms

PurposeThis study explores the attributes of true positive and false positive rates in screening mammogram test sets assessed by breast screening radiologists in order to identify the combined impact of prior images, breast density and lesion features with experience factors linked to diagnostic performance. Methods869 radiologists’ first-time readings across nine mammogram BREAST test sets with 361 normal and 179 cancer mammograms were collected between 2014 and 2023. Participants viewed digital mammograms on diagnostic monitors and localized abnormal lesions. The performances of readers in normal and cancer cases were compared with the ground truth and analyzed in four quartiles of breast density, lesion types and the availability of prior images using Man-Whitney U and Kruskal Wallis tests. The general linear model was applied to determine independent and significant covariates that affected the true positives and false positives. The correlation of the readers’ experience with the performances in different case and lesion features was explored using Spearman test. ResultsThe combination of lesion appearance and the availability of prior images had a significant impact on false positive results (P=0.033). The model that included lesion appearance, breast density, and no prior image status significantly influenced case true positives of readers (P=0.026). Meanwhile, the model considering only lesion appearance and breast density (P=0.002) had a significant effect on lesion true positives. There was a positive correlation observed between the number of cases read per week and readers’ performances, including TP rates and lesion sensitivity across various lesion types (P<0.05). Radiologists reading over 100 cases weekly achieved 80 % true positive rate for architectural distortion, asymmetric density, and masses, while this threshold increased to over 150 cases for calcifications. Detecting mixed lesion types required reading more than 60 cases weekly. Radiologists with over 5 years’ experience achieved 70–75 % accuracy in localizing cancer lesions. ConclusionFindings highlight the significant combined impact of breast density, prior image availability, lesion characteristics, and breast screening readers’ experience on breast cancer detection.

An approach for classification of breast cancer using lightweight deep convolution neural network

The rapid advancement of deep learning has generated considerable enthusiasm regarding its utilization in addressing medical imaging issues. Machine learning (ML) methods can help radiologists to diagnose breast cancer (BCs) barring invasive measures. Informative hand-crafted features are essential prerequisites for traditional machine learning classifiers to achieve accurate results, which are time-consuming to extract. In this paper, our deep learning algorithm is created to precisely identify breast cancers on screening mammograms, employing a training method that effectively utilizes training datasets with either full clinical annotation or solely the cancer status of the entire image. The proposed approach utilizes Lightweight Convolutional Neural Network (LWCNN) that allows automatic extraction features in an end-to-end manner. We have tested LWCNN model in two experiments. In the first experiment, the model was tested with two cases' original and enhancement datasets 1. It achieved 95 %, 93 %, 99 % and 98 % for training and testing accuracy respectively. In the second experiment, the model has been tested with two cases' original and enhancement datasets 2. It achieved 95 %, 91 %, 99 % and 92 % for training and testing accuracy respectively. Our proposed method, which uses various convolutional network to classify screening mammograms achieved exceptional performance when compared to other methods. The findings from these experiments clearly indicate that automatic deep learning techniques can be trained effectively to attain remarkable accuracy across a wide range of mammography datasets. This holds significant promise for improving clinical tools and reducing both false positive and false negative outcomes in screening mammography.

Association between mammographic screening history and stage at diagnosis among women with screen-detected breast cancer.

145 Background: Although screening mammography is an effective means of detecting breast cancer at earlier stages, some women are still diagnosed with later stage disease despite screening mammography. We hypothesized that screening history prior to diagnosis may impact stage at diagnosis and breast cancer mortality among women with screen-detected breast cancer. Methods: Retrospective cohort study of women aged 70+ in the SEER-Medicare database, diagnosed with ER+/HER2- breast cancer from 2010-2017, and enrolled in fee-for service Medicare Parts A and B from 5-years prior to diagnosis through 1 year after. We used validated claims-based algorithms to identify cancers that were detected by screening mammogram. We quantified 5-year screening history by number of prior screens. Stage at diagnosis was dichotomized into very early (T1N0) vs. later stage (T2+ or N+) disease. Multivariable logistic regression was used to assess the association between screening history and stage at diagnosis and Cox proportional hazards used to examine breast cancer mortality. Models were adjusted for demographic and clinical covariates associated with later stage disease in bivariate analyses. Results: We included 13,029 women with screen-detected breast cancer; 3,813 (29.27%) women had later stage disease at diagnosis, and 10,095 (77.48%) had at least one prior negative screening mammogram within the past five years. During this time, 2,359 (18.11%) women had only one prior mammogram, 3,132 (24.03%) had two, and 4,604 (35.34%) had three or four. Having at least one prior mammogram was associated with 56% lower odds of being diagnosed with later stage disease (OR: 0.44, 95% CI=0.40-0.48). Sociodemographic factors associated with increased odds of later stage disease included living in an area with greater poverty (20-100% vs. 0-5% of residents, OR: 1.19, 1.00-1.40), non-Hispanic Black race (OR: 1.18, 1.00-1.38), and Medicare/Medicaid dual eligibility (OR: 1.20, 1.06-1.36). Factors associated with later stage disease included living in an area with a more people with a high-school education (30-40% vs. 0-30% of residents, OR: 0.87, 0.77-0.97). At total of 696 deaths from breast cancer were observed, including 273 deaths among 2,935 women with no prior screening (9.3%) and 423 deaths among 10,097 women who had undergone screening within the past five years (4.2%, P &lt; 0.001). Receiving at least one negative screening prior to diagnosis was associated with decreased breast cancer-specific Mortality in adjusted analysis (HR: 0.48, 0.40-0.57). Conclusions: The use of prior routine screening mammography was associated with lower risk of being diagnosed with later stage disease and dying from breast cancer in elderly women with screen-detected breast cancer. Future research is warranted regarding the impact of routine vs. sporadic screening on potential morbidity and mortality in this age group.

Racial Disparities and Strategies for Improving Equity in Diagnostic Follow-Up for Abnormal Screening Mammograms.

Black and White women undergo screening mammography at similar rates, but racial disparities in breast cancer outcomes persist. To assess potential contributors, we investigated delays in follow-up after abnormal imaging by race/ethnicity. Women who underwent screening mammography at our urban academic center from January 2015 to February 2018 and received a Breast Imaging Reporting and Data System 0 assessment were included. Kaplan-Meier estimates described distributions of time between diagnostic events from (1) screening to diagnostic imaging and (2) diagnostic imaging to biopsy. Multivariable logistic regression models estimated the associations between race/ethnicity and receipt of follow-up within 15 and 30 days. Two thousand five hundred and fifty-four women were included (48.6% non-Hispanic [NH] Black, 38.2% NH White, 13.1% other/unknown). Median time between screening and diagnostic imaging varied by race/ethnicity (White: 7 days [IQR, 2-14]; Black: 12 days [IQR, 7-23]; other/unknown: 9 days [IQR, 5-21]). There were similar disparities in days between diagnostic imaging and biopsy (White: 12 [IQR, 7-24]; Black: 21 [IQR, 13-37]; other/unknown: 16 [IQR, 9-30]) and between screening and biopsy (White: 20 [IQR, 11-41]; Black: 35 [IQR, 22-63]; other/unknown: 27.5 [IQR, 17-42]). After adjustment, odds of diagnostic imaging follow-up within 15 days of screening were lower for Black versus White women (odds ratio, 0.59 [95% CI, 0.44 to 0.80]; P < .001). In this diverse cohort, disparities in timely diagnostic follow-up after abnormal breast screening were observed, with Black women waiting 1.75 times as long as White women to obtain a tissue diagnosis. National guidelines for time to diagnostic follow-up may facilitate more timely breast cancer care and potentially affect outcomes.

An initial exploration of factors that may impact radiographer performance in reporting mammograms

ObjectivesIn the United Kingdom, radiographers with a qualification in image interpretation have interpreted mammograms since 1995. These radiographers work under the title of radiography advanced practitioners (RAP) or Consultant Radiographer. This study extends upon what has been very recently published by exploring further clinical, non-clinical and experiential factors that may impact the reporting performance of RAPs. MethodsFifteen RAPs interpreted an image test set of 60 2D mammograms of known truth using the Detected-X software platform. Unknown to the reader, twenty cases contained a malignancy. Sensitivity, specificity, lesion sensitivity, receiver operating characteristic (ROC) and jack-knife free response operating characteristic (AFROC) values were established for each RAP. Specific features that had significant impact on accuracy were identified using Student's-T and Mann Whitney tests. ResultsRAPs with more than 10 years' experience in image interpretation, compared to those with less than 10 years’ experience, demonstrated lower specificity (51.3% vs 84.8%, p = 0.0264), ROC (0.83 vs 0.91, p = 0.0264) and AFROC (0.75 vs 0.87, p = 0.0037) values. Further, higher sensitivity values of 90.7% were seen in those RAPs who had an eye test in the last year compared to those who had not, 82% (p = 0.021). Other changes are presented in the paper. ConclusionThese data reveal previously unidentified factors that impact the diagnostic efficacy of RAPs when interpreting mammographic images. Highlighting such findings will empower screening authorities to better examine ways of standardising performance and offer a baseline for performance benchmarks. Implications for practiceThis study for the first time performs an initial exploration of the factors that may be associated with RAP performance when interpreting screening mammograms.

A New Paradigm for Reading Screening Mammograms.

A New Paradigm for Reading Screening Mammograms.

Enhancing Radiologist Reading Performance by Ordering Screening Mammograms Based on Characteristics That Promote Visual Adaptation.

Background Mammographic background characteristics may stimulate human visual adaptation, allowing radiologists to detect abnormalities more effectively. However, it is unclear whether density, or another image characteristic, drives visual adaptation. Purpose To investigate whether screening performance improves when screening mammography examinations are ordered for batch reading according to mammographic characteristics that may promote visual adaptation. Materials and Methods This retrospective multireader multicase study was performed with mammograms obtained between September 2016 and May 2019. The screening examinations, each consisting of four mammograms, were interpreted by 13 radiologists in three distinct orders: randomly, by increasing volumetric breast density (VBD), and based on a self-supervised learning (SSL) encoding (examinations automatically grouped as "looking similar"). An eye tracker recorded radiologists' eye movements during interpretation. The area under the receiver operating characteristic curve (AUC), sensitivity, and specificity of random-ordered readings were compared with those of VBD- and SSL-ordered readings using mixed-model analysis of variance. Reading time, fixation metrics, and perceived density were compared using Wilcoxon signed-rank tests. Results Mammography examinations (75 with breast cancer, 75 without breast cancer) from 150 women (median age, 55 years [IQR, 50-63]) were read. The examinations ordered by increasing VBD versus randomly had an increased AUC (0.93 [95% CI: 0.91, 0.96] vs 0.92 [95% CI: 0.89, 0.95]; P = .009), without evidence of a difference in specificity (89% [871 of 975] vs 86% [837 of 975], P = .04) and sensitivity (both 81% [794 of 975 vs 788 of 975], P = .78), and a reduced reading time (24.3 vs 27.9 seconds, P < .001), fixation count (47 vs 52, P < .001), and fixation time in malignant regions (3.7 vs 4.6 seconds, P < .001). For SSL-ordered readings, there was no evidence of differences in AUC (0.92 [95% CI: 0.89, 0.95]; P = .70), specificity (84% [820 of 975], P = .37), sensitivity (80% [784 of 975], P = .79), fixation count (54, P = .05), or fixation time in malignant regions (4.6 seconds, P > .99) compared with random-ordered readings. Reading times were significantly higher for SSL-ordered readings compared with random-ordered readings (28.4 seconds, P = .02). Conclusion Screening mammography examinations ordered from low to high VBD improved screening performance while reducing reading and fixation times. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Grimm in this issue.

Usefulness of intralesional contrast injection as a prebiopsy confirmation technique in a case of breast hemangioma

Hemangiomas are uncommon benign vascular lesions of breast. They have nonspecific imaging features and can be isoechoic or hypoechoic or of heterogeneous echotexture in ultrasound (USG). When isoechoic, it may be difficult to identify these lesions with confidence against a fatty background. Here, we report such a case of a high-density lesion detected in screening mammogram, which was not so obvious in USG. We used the technique of intralesional contrast injection into the probable USG correlate for confirmation, before proceeding with the biopsy and establishing the diagnosis of hemangioma. Thus, this simple prebiopsy confirmation technique helps in identifying the definitive USG correlate, thereby facilitating a USG-guided biopsy. This is very useful, especially in the peripheral healthcare centers where stereotactic facility may not be available. Another learning point from this case is that in case of superficially located lesions that are readily visible in mammogram but less conspicuous in USG, the possibility of hemangioma can be considered in the differentials. This observation has been mentioned in other case reports as well and reiterated in our case. However, due to the nonspecific imaging features and low incidence, it is difficult to make diagnosis of hemangioma without tissue sampling. The imaging features of breast hemangioma in mammogram and ultrasound are reviewed and described in this case report with an emphasis on the role of intralesional contrast injection in lesion localization.

ANALYTICAL STUDY ON FACTORS AFFECTING THE ATTITUDE AND PERSPECTIVES OF FEMALE PATIENTS ON THE USE OF ARTIFICIAL INTELLIGENCE IN THE ASSESSMENT OF SCREENING MAMMOGRAMS

Background: Breast cancer is one of the most common cancers among Indian women, with an incidence of 25.8 per 100,000 women according to the Ministry of Health and Family Welfare. Late detection is responsible for poor quality of life (QOL), and it is the leading cause of death. Studies have shown that people are positive towards AI performing assessment tasks in healthcare in general and in mammography screening. Moreover, it is challenging to implement strategies based on self-breast inspection or do mammography in rural regions or low and middle income nations for a variety of reasons. Objective: This study was conducted to assess the perception and attitude of various female patients reporting to the radiology unit of a tertiary care centre regarding the use of Artificial Intelligence in routine mammogram screening. Study Design: A cross sectional questionnaire based study was conducted female patients attending the radiology unit of a tertiary Care Centre in Central Kerala. Methods: After obtaining, informed written consent was taken from the study participants. A predesigned, pretested, validated checklist was used to collect the required data. The Knowledge, attitude and practice was ascertained through Likerts scale and scoring done accordingly. Statistical tests of significance was employed to assess the possible associations between various variables with the knowledge, attitude and perceptions regarding Artifical Intelligence based Mammogram Results: Among the 170 study subjects analysed, 68.6% had a satisfactory knowledge about Artificial intelligence. Among the 170 study subjects analysed, 86% had a good attitude about being screened through AI enabled mammogram techniques. 92% of the total study subjects registered for mammogram had done it based on self choice. The association between age and willingness to get screened was found to be statistically significant. It was also seen that there was a statistically very high significance between Knowledge regarding AI and the independent decision to get screened. There was also a statistically significant association between age and scores &gt;60% regarding knowledge and attitude regarding the vaccination among the study subjects. Conclusions: Majority of the study population was having a satisfactory knowledge regarding AI usage in healthcare.

Abstract A130: Examining breast cancer screening completion: Comparing patient self-report and electronic health record data at a Federally Qualified Health Center during the SARS-CoV-2 pandemic

Abstract Intro: There is evidence to suggest that preventive services, such as breast cancer screening, were impacted during the SARS-CoV-2 pandemic with interruption in screening mammogram services during March-July 2020. Federally Qualified Health Centers (FQHCs) are a critical health system to help better understand pandemic sequelae among diverse patient populations so teams can better prepare for a future pandemic. US Preventive Services Task Force (USPSTF) recommends average-risk patients aged 50-74 screen for breast cancer biyearly. Based on USPSTF recommendations in 2021, 76% of non-Hispanic White women and 74 % of Latina women were up-to-date on mammography screening. Our study, RESTORE, focuses on understanding patient barriers and facilitators to completing breast cancer screening at one large urban FQHC during the pandemic. Here, we compare FQHC patient self-reported completion of breast cancer screening to documented breast cancer screening found in the electric health record (EHR). Methods: Patients (n=20) were interviewed between July 2023 and February 2024 about their healthcare utilization, breast cancer screening (including medical site), and health literacy throughout the COVID period (2018-2022). When a screening date was documented in the EHR, interviewers mentioned the screening date to participants during the interview. Interviews were audio recorded and transcribed. A preliminary review of these interviews was conducted to collect self-reported breast cancer screening date and compare it to the date in the EHR. Results: Interviewees’ average age was 65.1 years; 70 % were Spanish-speaking; 60% were Latino, and 95% were female. Of the Spanish-speakers, 8 out of 14 patients self-reported completing a mammogram between 2018-2022, with 2 of 8 reporting having completed it with an onsite vendor. Only 3 of these 8 mammograms were captured in the EHR. Of these three, 2 patients were prompted with the EHR date during the interview: one patient agreed with the date while the other rejected the date. Among the English-speaking patients, 4 out of 6 patients self-reported completing a mammogram between years 2018-2022, all of these 4 self-reported dates were captured in the EHR. Of these 4 patients, all were prompted with the EHR date, 3 agreed to the date and one rejected the date, with 3 of 4 reporting having completed it with an onsite vendor.Conclusion: Throughout COVID, FQHC patients sought mammogram screening; however, gaps in data systems limited completeness of the health system’s mammogram EHR data. Time delays between patient experience and interview dates, complicated our understanding of patients’ COVID experiences. The inconsistency between self-reported dates and EHR dates also creates challenges educating and convincing patients to stay up-to-date on screenings based on recommended intervals. Missing EHR data could have also impacted staff not accurately following-up for mammograms or referrals. Additional work is needed to understand the opportunities to better integrate FQHC EHR with mammogram vendor data systems. Citation Format: Anne Escaron, Crystal Gomez, Jennifer Schneider, Jennifer Rivelli, Fabian Hidalgo, Gloria Coronado. Examining breast cancer screening completion: Comparing patient self-report and electronic health record data at a Federally Qualified Health Center during the SARS-CoV-2 pandemic [abstract]. In: Proceedings of the 17th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2024 Sep 21-24; Los Angeles, CA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2024;33(9 Suppl):Abstract nr A130.

Abstract B050: Health and faith in the Korean community: Increasing breast and colorectal cancer education and screening in Los Angeles

Abstract Background: Koreatown in Los Angeles is home to over 115 churches within 3 miles. Korean churches are sanctuaries that provide support and nurture social connections, especially among Korean immigrants with limited English proficiency, who face challenges in accessing cancer care, including language barriers, lack of health insurance, and fears associated with cancer screening procedures and treatments. Koreans experience higher incidence and prevalence rates of breast and colorectal cancers compared to non-Hispanic White and other Asian subgroups, respectively. To address this, a Health and Faith Initiative was launched in 2018, utilizing evidence-based strategies recommended by Center for Disease Control and Prevention Community Guide and the use of a Cancer 101 curriculum developed by the Fred Hutchinson Cancer Center. METHODS: A three-stage Partnership Development Framework (networking, education, program and research development) was used to grow deep connections and sustainable cancer screening programs with church pastors and leaders, patient navigators, Federally Qualified Health Centers, State Breast and Cervical Early Detection Program providers, Diagnostic facilities, Hospitals and Community Outreach and Engagement staff. Bi- lingual church leaders was selected by pastors and elders at churches were trained as lay community navigators to conduct cancer education workshops using a Cancer 101 curriculum, as well as to support for church member to navigate across the cancer continuum. Church pastors and community health clinics determine outreach, engagement, and research priorities through active participation in Community Advisory Board and research studies. The initiative is sustained through coordination of 2 outreach staff and financial assistance from community benefit and research grants at Cedars Sinai Cancer Center. RESULTS: From June 2023 to May 2024, Community Outreach and Engagement (COE) have led the coordination of 6 breast cancer health education workshops and screening events with 165 people screened (128 screening mammograms, 37 diagnostic mammograms &amp; ultra sounds) in partnership with Koryo Health Foundation. Two patients were diagnosed with breast cancer and were referred to Cedars Sinai for treatment. For colorectal cancer, 8 health education workshops were conducted, and 122 Fit Kits were distributed with 72 kits returned, a 59% return rate. Cancer education workshops using American Cancer Society cancer screening guidelines for breast, colorectal, prostate, cervical, lung cancer has reached 810 people during 5 tabling events. Those who were not up to date were referred to our partnered health clinics for screening. CONCLUSION: Engaging Korean church leaders and training community navigators is an effective outreach strategy to build long-lasting partnership for successful implementation of cancer screening interventions but also support patients in needed follow up care that help immigrant populations to navigate across the cancer continuum. Citation Format: Dong Hee Kim, Min Jung Sung, Moon Ju Kim, Jeong Yup Lee, Reener Balingit, Zul Surani. Health and faith in the Korean community: Increasing breast and colorectal cancer education and screening in Los Angeles [abstract]. In: Proceedings of the 17th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2024 Sep 21-24; Los Angeles, CA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2024;33(9 Suppl):Abstract nr B050.

Artificial intelligence as an initial reader for double reading in breast cancer screening: a prospective initial study of 32,822 mammograms of the Egyptian population

BackgroundAlthough artificial intelligence (AI) has potential in the field of screening of breast cancer, there are still issues. It is vital to make sure AI does not overlook cancer or cause needless recalls. The aim of this work was to investigate the effectiveness of indulging AI in combination with one radiologist in the routine double reading of mammography for breast cancer screening. The study prospectively analyzed 32,822 screening mammograms. Reading was performed in a blind-paired style by (i) two radiologists and (ii) one radiologist paired with AI. A heatmap and abnormality scoring percentage were provided by AI for abnormalities detected on mammograms. Negative mammograms and benign-looking lesions that were not biopsied were confirmed by a 2-year follow-up.ResultsDouble reading by the radiologist and AI detected 1324 cancers (6.4%); on the other side, reading by two radiologists revealed 1293 cancers (6.2%) and presented a relative proportion of 1·02 (p < 0·0001). At the recall stage, suspicion and biopsy recommendation were more presented by the AI plus one radiologist combination than by the two radiologists. The interpretation of the mammogram by AI plus only one radiologist showed a sensitivity of 94.03%, a specificity of 99.75%, a positive predictive value of 96.571%, a negative predictive value of 99.567%, and an accuracy of 99.369% (from 99.252 to 99.472%). The positive likelihood ratio was 387.260, negative likelihood ratio was 0.060, and AUC “area under the curve” was 0.969 (0.967–0.971).ConclusionsAI could be used as an initial reader for the evaluation of screening mammography in routine workflow. Implementation of AI enhanced the opportunity to reduce false negative cases and supported the decision to recall or biopsy.

Factors impacting breast cancer survivors' performance of annual follow-up mammograms: A nationally representative study.

ObjectiveGuided by the PRECEDE-PROCEDE model, this study explores the factors associated with completing an annual screening mammogram among breast cancer survivors (BCS). MethodsWe used multiple cycles of survey data from the Health Information National Trends Survey (HINTS) (2017–2020). Logistic regression analyses were conducted to examine the correlates of past year mammograms among breast cancer survivors. ResultsWe included a sample of 909 breast cancer survivors in the study. Seventy percent of the sample reported at least one mammography screening in the prior 12 months. The more time since diagnosis, the fewer participants performed screening. Consistent with the PRECEDE-PROCEDE Model, annual screening was associated with enabling factors (having health insurance), reinforcing factors (trust in doctors, patient-centered communication), and predisposing factors (cancer-related worry and quality of care). ConclusionsFindings suggest that thirty percent of BCS may experience barriers to receipt of follow-up mammograms. Additional research is needed to identify strategies that address demographic, enabling, reinforcing, and predisposing factors with the ultimate goal of improving access to follow-up mammography and ensuring the well-being of breast cancer survivors.Practice ImplicationsCancer surveillance among BCS is vital to improving health outcomes. Provider and practice-based interventions can potentially increase access and engagement with annual screening recommendations.

Evidence from an Applied Health Research Question: Health Equity Profiles of Community Health Centre (CHC) and non-CHC clients

Objective/ApproachThe Black Health Equity Working Group's Applied Health Research Question aimed to compare cancer screening rates and surgical wait times between community health centre (CHC) clients based on race-related data and non-CHC clients. CHC client data was categorized by self-identified racial groups, with Black self-identification compared to non-Black racialized, White, and missing racial self-identification, and non-CHC clients. Health card numbers were encrypted to link individuals to the Primary Care Population dataset for breast, cervical, and colorectal cancer screening rates. Surgical wait time indicators, such as the number of patients undergoing surgery and average wait times for initial consultation and completed surgeries, were derived from the Wait Time Information System. Assessments were conducted semi-annually from fiscal year 2018 to 2021. ResultsFollowing the onset of COVID-19, CHC clients self-identifying as Black experienced the most significant decrease (6.8%) in colorectal screenings compared to other groups. Mammogram screenings remained consistently higher for CHC clients self-identifying as Black pre- and post-pandemic. Average cervical cancer screening rates were approximately 8% higher among CHC clients compared to non-CHC clients, irrespective of racial self-identification. However, due to small sample sizes and missing data among self-identified racial groups, trends in surgical wait times for both CHC and non-CHC clients were unstable. Conclusion/ImplicationsTailored interventions targeting Black CHC clients can enhance cancer screening rates, particularly colorectal screenings. The analysis of CHC data offers valuable insights into race-based disparities in health outcomes. Improved data completeness is essential for accurately assessing health outcome variations among different racial groups.

Potential Impact of an Artificial Intelligence-based Mammography Triage Algorithm on Performance and Workload in a Population-based Screening Sample.

To evaluate potential screening mammography performance and workload impact using a commercial artificial intelligence (AI)-based triage device in a population-based screening sample. In this retrospective study, a sample of 2129 women who underwent screening mammograms were evaluated. The performance of a commercial AI-based triage device was compared with radiologists' reports, actual outcomes, and national benchmarks using commonly used mammography metrics. Up to 5 years of follow-up examination results were evaluated in cases to establish benignity. The algorithm sorted cases into groups of "suspicious" and "low suspicion." A theoretical workload reduction was calculated by subtracting cases triaged as "low suspicion" from the sample. At the default 93% sensitivity setting, there was significant improvement (P <.05) in the following triage simulation mean performance measures compared with actual outcome: 45.5% improvement in recall rate (13.4% to 7.3%; 95% CI, 6.2-8.3), 119% improvement in positive predictive value (PPV) 1 (5.3% to 11.6%; 95% CI, 9.96-13.4), 28.5% improvement in PPV2 (24.6% to 31.6%; 95% CI, 24.8-39.1), 20% improvement in sensitivity (83.3% to 100%; 95% CI, 100-100), and 7.2% improvement in specificity (87.2% to 93.5%; 95% CI, 92.4-94.5). A theoretical 62.5% workload reduction was possible. At the ultrahigh 99% sensitivity setting, a theoretical 27% workload reduction was possible. No cancers were missed by the algorithm at either sensitivity. Artificial intelligence-based triage in this simulation demonstrated potential for significant improvement in mammography performance and predicted substantial theoretical workload reduction without any missed cancers.

Breast cancer characterization using region-based convolutional neural network with screening and diagnostic mammogram

Background: Detection and classification of microcalcifications in breast tissues is crucial for early breast cancer diagnosis and long-term treatment. Objective: This paper aims to propose a robust model capable of detection and classification of breast cancer calcifications in digital mammogram images using Deep Convolutional Neural Networks (DCNN). Materials and methods: An expert breast radiologist annotated the 3,265 clinical mammogram images to create a comprehensive ground truth dataset comprising 2,500 annotations for malignant and benign calcifications. This dataset was utilized to train our model, a two-stage detection system incorporating a Region-based Convolutional Neural Network (RCNN) with AlexNet and support vector machines to enhance the system’s robustness. The proposed model was compared to the one-stage detection, utilizing YOLOv4 combined with the Cross-Stage Partial Darknet53 (CSPDarknet53) architecture. A separate dataset of 504 mammogram images was explicitly set aside for model testing. The efficacy of the proposed model was evaluated based on key performance metrics, including precision, recall, F1 score, and mean average precision (mAP). Results: The results showed that the proposed RCNN-2 model could automatically identify and categorize calcifications as malignant or benign, outperforming the YOLOv4 models. The RCNN-2’s overall effectiveness, as evaluated by precision, recall, F1 score, and mean average precision (mAP), achieved scores of 0.82, 0.85, 0.83, and 0.74, respectively. Conclusion: The proposed RCNN-2 model demonstrates very effective detection and classification of calcification in mammogram images, especially in high-dense breast images. The performance of the proposed model was compared to that of YOLOv4, and it can be concluded that the proposed RCNN model yields outstanding performance. The model can be a helpful tool for radiologists.