Long-term Accuracy of Breast Cancer Risk Assessment Combining Classic Risk Factors and Breast Density

Validation of the Mirai model for predicting breast cancer risk in Mexican women

OBJECTIVES

To validate the performance of Mirai, a mammography-based deep learning model, in predicting breast cancer risk over a 1-5-year period in Mexican women.

METHODS

This retrospective single-center study included mammograms in Mexican women who underwent screening mammography between January 2014 and December 2016. For women with consecutive mammograms during the study period, only the initial mammogram was included. Pathology and imaging follow-up served as the reference standard. Model performance in the entire dataset was evaluated, including the concordance index (C-Index) and area under the receiver operating characteristic curve (AUC). Mirai's performance in terms of AUC was also evaluated between mammography systems (Hologic versus IMS). Clinical utility was evaluated by determining a cutoff point for Mirai's continuous risk index based on identifying the top 10% of patients in the high-risk category.

RESULTS

Of 3110 patients (median age 52.6 years ± 8.9), throughout the 5-year follow-up period, 3034 patients remained cancer-free, while 76 patients developed breast cancer. Mirai achieved a C-index of 0.63 (95% CI: 0.6-0.7) for the entire dataset. Mirai achieved a higher mean C-index in the Hologic subgroup (0.63 [95% CI: 0.5-0.7]) versus the IMS subgroup (0.55 [95% CI: 0.4-0.7]). With a Mirai index score > 0.029 (10% threshold) to identify high-risk individuals, the study revealed that individuals in the high-risk group had nearly three times the risk of developing breast cancer compared to those in the low-risk group.

CONCLUSIONS

Mirai has a moderate performance in predicting future breast cancer among Mexican women.

CRITICAL RELEVANCE STATEMENT

Prospective efforts should refine and apply the Mirai model, especially to minority populations and women aged between 30 and 40 years who are currently not targeted for routine screening.

KEY POINTS

The applicability of AI models to non-White, minority populations remains understudied. The Mirai model is linked to future cancer events in Mexican women. Further research is needed to enhance model performance and establish usage guidelines.

The Impact of a Breast Cancer Risk Assessment on the Decision for Gender-Affirming Chest Masculinization Surgery in Transgender and Gender-Diverse Individuals: A Pilot Single-Arm Educational Intervention Trial

BACKGROUND

Persons assigned female or intersex at birth and identify as transgender and/or gender-diverse (TGD) may undergo gender-affirming chest masculinization surgery (GACMS); however, GACMS is not considered equivalent to risk-reducing mastectomies (RRM). This study aimed to estimate the prevalence of elevated breast cancer (BC) risk in TGD persons, compare self-perceived versus calculated risk, and determine how risk impacts the decision for GACMS versus RRM.

METHODS

A prospective single-arm pilot educational intervention trial was conducted in individuals assigned female or intersex at birth, age ≥ 18 years, considering GACMS, without a BC history or a known pathogenic variant. BC risk was calculated using the Tyrer-Cuzik (all) and Gail models (age ≥ 35 years). Elevated risk was defined as ≥ 17%.

RESULTS

Twenty-five (N = 25) participants were enrolled with a median age of 24.0 years (interquartile range, IQR 20.0-30.0 years). All were assigned female sex at birth, most (84%) were Non-Hispanic (NH)-White, 48% identified as transgender and 40% as nonbinary, and 52% had a first- and/or second-degree family member with BC. Thirteen (52%) had elevated risk (prevalence 95% confidence interval (CI) 31.3-72.2%). Median self-perceived risk was 12% versus 17.5% calculated risk (p = 0.60). Of the 13 with elevated risk, 5 (38.5%) underwent/are scheduled to undergo GACMS, 3 (23%) of whom underwent/are undergoing RRM.

CONCLUSIONS

Over half of the cohort had elevated risk, and most of those who moved forward with surgery chose to undergo RRM. A BC risk assessment should be performed for TGD persons considering GACMS. Future work is needed to examine BC incidence and collect patient-reported outcomes. Trial Registration Number ClinicalTrials.gov (No. NCT06239766).

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

BACKGROUND AND OBJECTIVES

In 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.

METHODS

We 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.

RESULTS

Our 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.

CONCLUSION

Although 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.

Clinical Significance of Combined Density and Deep-Learning-Based Texture Analysis for Stratifying the Risk of Short-Term and Long-Term Breast Cancer in Screening

Assessing a woman's risk of breast cancer is important for personalized screening. Mammographic density is a strong risk factor for breast cancer, but parenchymal texture patterns offer additional information which cannot be captured by density. We aimed to combine BI-RADS density score 4th Edition and a deep-learning-based texture score to stratify women in screening and compare rates among the combinations. This retrospective study cohort study included 216,564 women from a Danish populations-based screening program. Baseline mammograms were evaluated using BI-RADS density scores (1-4) and a deep-learning texture risk model, with scores categorized into four quartiles (1-4). The incidence rate ratio (IRR) for screen-detected, interval, and long-term cancer were adjusted for age, year of screening and screening clinic. Compared with subgroup B1-T1, the highest IRR for screen-detected cancer were within the T4 category (3.44 (95% CI: 2.43-4.82)-4.57 (95% CI: 3.66-5.76)). IRR for interval cancer was highest in the BI-RADS 4 category (95% CI: 5.36 (1.77-13.45)-16.94 (95% CI: 9.93-30.15)). IRR for long-term cancer increased both with increasing BI-RADS and increasing texture reaching 5.15 (4.31-6.16) for the combination of B4-T4 compared with B1-T1. Deep-learning-based texture analysis combined with BI-RADS density categories can reveal subgroups with increased rates beyond what density alone can ascertain, suggesting the potential of combining texture and density to improve risk stratification in breast cancer screening.

Constructing the Optimal Classification Model for Benign and Malignant Breast Tumors Based on Multifeature Analysis from Multimodal Images

The purpose of this study was to fuse conventional radiomic and deep features from digital breast tomosynthesis craniocaudal projection (DBT-CC) and ultrasound (US) images to establish a multimodal benign-malignant classification model and evaluate its clinical value. Data were obtained from a total of 487 patients at three centers, each of whom underwent DBT-CC and US examinations. A total of 322 patients from dataset 1 were used to construct the model, while 165 patients from datasets 2 and 3 formed the prospective testing cohort. Two radiologists with 10-20 years of work experience and three sonographers with 12-20 years of work experience semiautomatically segmented the lesions using ITK-SNAP software while considering the surrounding tissue. For the experiments, we extracted conventional radiomic and deep features from tumors from DBT-CCs and US images using PyRadiomics and Inception-v3. Additionally, we extracted conventional radiomic features from four peritumoral layers around the tumors via DBT-CC and US images. Features were fused separately from the intratumoral and peritumoral regions. For the models, we tested the SVM, KNN, decision tree, RF, XGBoost, and LightGBM classifiers. Early fusion and late fusion (ensemble and stacking) strategies were employed for feature fusion. Using the SVM classifier, stacking fusion of deep features and three peritumoral radiomic features from tumors in DBT-CC and US images achieved the optimal performance, with an accuracy and AUC of 0.953 and 0.959 [CI: 0.886-0.996], a sensitivity and specificity of 0.952 [CI: 0.888-0.992] and 0.955 [0.868-0.985], and a precision of 0.976. The experimental results indicate that the fusion model of deep features and peritumoral radiomic features from tumors in DBT-CC and US images shows promise in differentiating benign and malignant breast tumors.

Validation of a clinical breast cancer risk assessment tool combining a polygenic score for all ancestries with traditional risk factors

PURPOSE

We previously described a combined risk score (CRS) that integrates a multiple-ancestry polygenic risk score (MA-PRS) with the Tyrer-Cuzick (TC) model to assess breast cancer (BC) risk. Here, we present a longitudinal validation of CRS in a real-world cohort.

METHODS

This study included 130,058 patients referred for hereditary cancer genetic testing and negative for germline pathogenic variants in BC-associated genes. Data were obtained by linking genetic test results to medical claims (median follow-up 12.1 months). CRS calibration was evaluated by the ratio of observed to expected BCs.

RESULTS

Three hundred forty BCs were observed over 148,349 patient-years. CRS was well-calibrated and demonstrated superior calibration compared with TC in high-risk deciles. MA-PRS alone had greater discriminatory accuracy than TC, and CRS had approximately 2-fold greater discriminatory accuracy than MA-PRS or TC. Among those classified as high risk by TC, 32.6% were low risk by CRS, and of those classified as low risk by TC, 4.3% were high risk by CRS. In cases where CRS and TC classifications disagreed, CRS was more accurate in predicting incident BC.

CONCLUSION

CRS was well-calibrated and significantly improved BC risk stratification. Short-term follow-up suggests that clinical implementation of CRS should improve outcomes for patients of all ancestries through personalized risk-based screening and prevention.

Awareness, Knowledge, and Current Practice of Breast Cancer Among Surgeons in Jordan

PURPOSE

Breast cancer (BC) is the most prevalent cancer in Jordan. De-escalation in treatment reflects a paradigm shift in BC treatment. More tailored strategies and the adoption of a multidisciplinary approach are essential to apply recent changes in management. In the era of breast surgery fellowship, adopting well-structured training is essential to apply recent therapeutic guidelines and meet patients' expectations.

METHODS

A cross-sectional study using a customized, self-reported questionnaire was used. Data collection occurred anonymously using a link via WhatsApp in the period between February 2023 and April 2023.

RESULTS

A total of 89 surgeons were involved in this study, and only 14 (15.7%) completed a subspecialty in breast surgery. About 58.4% considered the age of 40 years as the starting point for screening, and 84.3% reported that mammogram screening is associated with improved BC survival. Only 10.1% and 28.1% acknowledged the applicability of both tomosynthesis and breast magnetic resonance imaging in screening, respectively. A significant difference in the mean knowledge score about BC is observed between general surgeon and those with subspecialty. Varying levels of awareness concerning different risk factors and their correlation with the likelihood of BC occurrence observed. Although 56.2% of participants could offer breast conserving surgery and consider it oncological safe, only 48.3% defined it correctly. Of the participants, 61.8% and 76.4% stated that sentinel lymph node biopsy can be safely applied in clinically negative or suspicious axillary nodes, respectively, with <50% of surgeon performing it in their practice.

CONCLUSION

More efforts are required to enhance the knowledge and practice of surgeons in the field of breast surgery. Adopting national guidelines can facilitate the acceptance and improvement of current practices among surgeons in Jordan.

Deep learning of mammogram images to reduce unnecessary breast biopsies: a preliminary study

BACKGROUND

Patients with a Breast Imaging Reporting and Data System (BI-RADS) 4 mammogram are currently recommended for biopsy. However, 70-80% of the biopsies are negative/benign. In this study, we developed a deep learning classification algorithm on mammogram images to classify BI-RADS 4 suspicious lesions aiming to reduce unnecessary breast biopsies.

MATERIALS AND METHODS

This retrospective study included 847 patients with a BI-RADS 4 breast lesion that underwent biopsy at a single institution and included 200 invasive breast cancers, 200 ductal carcinoma in-situ (DCIS), 198 pure atypias, 194 benign, and 55 atypias upstaged to malignancy after excisional biopsy. We employed convolutional neural networks to perform 4 binary classification tasks: (I) benign vs. all atypia + invasive + DCIS, aiming to identify the benign cases for whom biopsy may be avoided; (II) benign + pure atypia vs. atypia-upstaged + invasive + DCIS, aiming to reduce excision of atypia that is not upgraded to cancer at surgery; (III) benign vs. each of the other 3 classes individually (atypia, DCIS, invasive), aiming for a precise diagnosis; and (IV) pure atypia vs. atypia-upstaged, aiming to reduce unnecessary excisional biopsies on atypia patients.

RESULTS

A 95% sensitivity for the "higher stage disease" class was ensured for all tasks. The specificity value was 33% in Task I, and 25% in Task II, respectively. In Task III, the respective specificity value was 30% (vs. atypia), 30% (vs. DCIS), and 46% (vs. invasive tumor). In Task IV, the specificity was 35%. The AUC values for the 4 tasks were 0.72, 0.67, 0.70/0.73/0.72, and 0.67, respectively.

CONCLUSION

Deep learning of digital mammograms containing BI-RADS 4 findings can identify lesions that may not need breast biopsy, leading to potential reduction of unnecessary procedures and the attendant costs and stress.

Effects of joint screening for prostate, lung, colorectal, and ovarian cancer - results from a controlled trial

Background

Although screening is widely used to reduce cancer burden, untargeted cancers are frequently missed after single cancer screening. Joint cancer screening is presumed as a more effective strategy to reduce overall cancer burden.

Methods

Gender-specific screening effects on PLCO cancer incidence, PLCO cancer mortality, all-neoplasms mortality and all-cause mortality were evaluated, and meta-analyses based on gender-specific screening effects were conducted to achieve the pooled effects. The cut-off value of time-dependent receiver-operating-characteristic curve of 10-year combined PLCO cancer risk was used to reclassify participants into low- and high-risk subgroups. Further analyses were conducted to investigate screening effects stratified by risk groups and screening compliance.

Results

After a median follow-up of 10.48 years for incidence and 16.85 years for mortality, a total of 5,506 PLCO cancer cases, 1,845 PLCO cancer deaths, 3,970 all-neoplasms deaths, and 14,221 all-cause deaths were documented in the screening arm, while 6,261, 2,417, 5,091, and 18,516 outcome-specific events in the control arm. Joint cancer screening did not significantly reduce PLCO cancer incidence, but significantly reduced male-specific PLCO cancer mortality (hazard ratio and 95% confidence intervals [HR(95%CIs)]: 0.88(0.82, 0.95)) and pooled mortality [0.89(0.84, 0.95)]. More importantly, joint cancer screening significantly reduced both gender-specific all-neoplasm mortality [0.91(0.86, 0.96) for males, 0.91(0.85, 0.98) for females, and 0.91(0.87, 0.95) for meta-analyses] and all-cause mortality [0.90(0.88, 0.93) for male, 0.88(0.85, 0.92) for female, and 0.89(0.87, 0.91) for meta-analyses]. Further analyses showed decreased risks of all-neoplasm mortality was observed with good compliance [0.72(0.67, 0.77) for male and 0.72(0.65, 0.80) for female] and increased risks with poor compliance [1.61(1.40, 1.85) for male and 1.30(1.13, 1.40) for female].

Conclusion

Joint cancer screening could be recommended as a potentially strategy to reduce the overall cancer burden. More compliance, more benefits. However, organizing a joint cancer screening not only requires more ingenious design, but also needs more attentions to the potential harms.

Trial registration

NCT00002540 (Prostate), NCT01696968 (Lung), NCT01696981 (Colorectal), NCT01696994 (Ovarian).

Role of Breast Cancer Risk Estimation Models to Identify Women Eligible for Genetic Testing and Risk-Reducing Surgery

Hereditary breast and ovarian cancer (HBOC) syndrome is responsible for approximately 10% of breast cancers (BCs). The HBOC gene panel includes both high-risk genes, i.e., a four times higher risk of BC (BRCA1, BRCA2, PALB2, CDH1, PTEN, STK11 and TP53), and moderate-risk genes, i.e., a two to four times higher risk of BC (BARD1, CHEK2, RAD51C, RAD51D and ATM). Pathogenic germline variants (PGVs) in HBOC genes confer an absolute risk of BC that changes according to the gene considered. We illustrate and compare different BC risk estimation models, also describing their limitations. These models allow us to identify women eligible for genetic testing and possibly to offer surgical strategies for primary prevention, i.e., risk-reducing mastectomies and salpingo-oophorectomies.

Extending the Breast Cancer Surveillance Consortium Model of Invasive Breast Cancer

PURPOSE

We extended the Breast Cancer Surveillance Consortium (BCSC) version 2 (v2) model of invasive breast cancer risk to include BMI, extended family history of breast cancer, and age at first live birth (version 3 [v3]) to better inform appropriate breast cancer prevention therapies and risk-based screening.

METHODS

We used Cox proportional hazards regression to estimate the age- and race- and ethnicity-specific relative hazards for family history of breast cancer, breast density, history of benign breast biopsy, BMI, and age at first live birth for invasive breast cancer in the BCSC cohort. We evaluated calibration using the ratio of expected-to-observed (E/O) invasive breast cancers in the cohort and discrimination using the area under the receiver operating characteristic curve (AUROC).

RESULTS

We analyzed data from 1,455,493 women age 35-79 years without a history of breast cancer. During a mean follow-up of 7.3 years, 30,266 women were diagnosed with invasive breast cancer. The BCSC v3 model had an E/O of 1.03 (95% CI, 1.01 to 1.04) and an AUROC of 0.646 for 5-year risk. Compared with the v2 model, discrimination of the v3 model improved most in Asian, White, and Black women. Among women with a BMI of 30.0-34.9 kg/m2, the true-positive rate in women with an estimated 5-year risk of 3% or higher increased from 10.0% (v2) to 19.8% (v3) and the improvement was greater among women with a BMI of ≥35 kg/m2 (7.6%-19.8%).

CONCLUSION

The BCSC v3 model updates an already well-calibrated and validated breast cancer risk assessment tool to include additional important risk factors. The inclusion of BMI was associated with the largest improvement in estimated risk for individual women.

Development and implementation of a prognostic model for clear cell renal cell carcinoma based on heterogeneous TLR4 expression

Objective

Clear cell renal cell carcinoma (ccRCC) is the most common subtype among renal cell carcinomas and has the worst prognosis, originating from renal tubular epithelial cells. Toll-like receptor 4 (TLR4) plays a crucial role in ccRCC proliferation, infiltration, and metastasis. The aim of this study was to construct a prognostic scoring model for ccRCC based on TLR4 expression heterogeneity and to explore its association with immune infiltration, thereby providing insights for the treatment and prognostic evaluation of ccRCC.

Methods

Using R software, a differential analysis was conducted on normal samples and ccRCC samples, and in conjunction with the KEGG database, a correlation analysis for the clear cell renal cell carcinoma pathway (hsa05211) was carried out. We observed the expression heterogeneity of TLR4 in the TCGA-KIRC cohort and identified its related differential genes (TRGs). Based on the expression levels of TRGs, consensus clustering was employed to identify TLR4-related subtypes, and further clustering heatmaps, principal component, and single-sample gene set enrichment analyses were conducted. Overlapping differential genes (ODEGs) between subtypes were analysed, and combined with survival data, univariate Cox regression, LASSO, and multivariate Cox regression were used to establish a prognostic risk model for ccRCC. This model was subsequently evaluated through ROC analysis, risk factor correlation analysis, independent prognostic factor analysis, and intergroup differential analysis. The ssGSEA model was employed to explore immune heterogeneity in ccRCC, and the performance of the model in predicting patient prognosis was evaluated using box plots and the oncoPredict software package.

Results

In the TCGA-KIRC cohort, TLR4 expression was notably elevated in ccRCC samples compared to normal samples, correlating with improved survival in the high-expression group. The study identified distinct TLR4-related differential genes and categorized ccRCC into three subtypes with varied survival outcomes. A risk prognosis model based on overlapping differential genes was established, showing significant associations with immune cell infiltration and key immune checkpoints (PD-1, PD-L1, CTLA4). Additionally, drug sensitivity differences were observed between risk groups.

Conclusion

In the TCGA-KIRC cohort, the expression of TLR4 in ccRCC samples exhibited significant heterogeneity. Through clustering analysis, we identified that the primary immune cells across subtypes are myeloid-derived suppressor cells, central memory CD4 T cells, and regulatory T cells. Furthermore, we successfully constructed a prognostic risk model for ccRCC composed of 17 genes. This model provides valuable references for the prognosis prediction and treatment of ccRCC patients.

Development and evaluation of a method to assess breast cancer risk using a longitudinal history of mammographic density: a cohort study

BACKGROUND

Women with dense breasts have an increased risk of breast cancer. However, breast density is measured with variability, which may reduce the reliability and accuracy of its association with breast cancer risk. This is particularly relevant when visually assessing breast density due to variation in inter- and intra-reader assessments. To address this issue, we developed a longitudinal breast density measure which uses an individual woman's entire history of mammographic density, and we evaluated its association with breast cancer risk as well as its predictive ability.

METHODS

In total, 132,439 women, aged 40-73 yr, who were enrolled in Kaiser Permanente Washington and had multiple screening mammograms taken between 1996 and 2013 were followed up for invasive breast cancer through 2014. Breast Imaging Reporting and Data System (BI-RADS) density was assessed at each screen. Continuous and derived categorical longitudinal density measures were developed using a linear mixed model that allowed for longitudinal density to be updated at each screen. Predictive ability was assessed using (1) age and body mass index-adjusted hazard ratios (HR) for breast density (time-varying covariate), (2) likelihood-ratio statistics (ΔLR-χ2) and (3) concordance indices.

RESULTS

In total, 2704 invasive breast cancers were diagnosed during follow-up (median = 5.2 yr; median mammograms per woman = 3). When compared with an age- and body mass index-only model, the gain in statistical information provided by the continuous longitudinal density measure was 23% greater than that provided by BI-RADS density (follow-up after baseline mammogram: ΔLR-χ2 = 379.6 (degrees of freedom (df) = 2) vs. 307.7 (df = 3)), which increased to 35% (ΔLR-χ2 = 251.2 vs. 186.7) for follow-up after three mammograms (n = 76,313, 2169 cancers). There was a sixfold difference in observed risk between densest and fattiest eight-category longitudinal density (HR = 6.3, 95% CI 4.7-8.7), versus a fourfold difference with BI-RADS density (HR = 4.3, 95% CI 3.4-5.5). Discriminatory accuracy was marginally greater for longitudinal versus BI-RADS density (c-index = 0.64 vs. 0.63, mean difference = 0.008, 95% CI 0.003-0.012).

CONCLUSIONS

Estimating mammographic density using a woman's history of breast density is likely to be more reliable than using the most recent observation only, which may lead to more reliable and accurate estimates of individual breast cancer risk. Longitudinal breast density has the potential to improve personal breast cancer risk estimation in women attending mammography screening.

Impact of BMI on Prevalence of Dense Breasts by Race and Ethnicity

BACKGROUND

Density notification laws require notifying women of dense breasts with dense breast prevalence varying by race/ethnicity. We evaluated whether differences in body mass index (BMI) account for differences in dense breasts prevalence by race/ethnicity.

METHODS

Prevalence of dense breasts (heterogeneously or extremely dense) according to Breast Imaging Reporting and Data System and obesity (BMI > 30 kg/m2) were estimated from 2,667,207 mammography examinations among 866,033 women in the Breast Cancer Surveillance Consortium (BCSC) from January 2005 through April 2021. Prevalence ratios (PR) for dense breasts relative to overall prevalence by race/ethnicity were estimated by standardizing race/ethnicity prevalence in the BCSC to the 2020 U.S. population, and adjusting for age, menopausal status, and BMI using logistic regression.

RESULTS

Dense breasts were most prevalent among Asian women (66.0%) followed by non-Hispanic/Latina (NH) White (45.5%), Hispanic/Latina (45.3%), and NH Black (37.0%) women. Obesity was most prevalent in Black women (58.4%) followed by Hispanic/Latina (39.3%), NH White (30.6%), and Asian (8.5%) women. The adjusted prevalence of dense breasts was 19% higher [PR = 1.19; 95% confidence interval (CI), 1.19-1.20] in Asian women, 8% higher (PR = 1.08; 95% CI, 1.07-1.08) in Black women, the same in Hispanic/Latina women (PR = 1.00; 95% CI, 0.99-1.01), and 4% lower (PR = 0.96; 95% CI, 0.96-0.97) in NH White women relative to the overall prevalence.

CONCLUSIONS

Clinically important differences in breast density prevalence are present across racial/ethnic groups after accounting for age, menopausal status, and BMI.

IMPACT

If breast density is the sole criterion used to notify women of dense breasts and discuss supplemental screening it may result in implementing inequitable screening strategies across racial/ethnic groups. See related In the Spotlight, p. 1479.

Differences and similarities in false interpretations by AI CAD and radiologists in screening mammography

OBJECTIVE

We aimed to evaluate the false interpretations between artificial intelligence (AI) and radiologists in screening mammography to get a better understanding of how the distribution of diagnostic mistakes might change when moving from entirely radiologist-driven to AI-integrated breast cancer screening.

METHODS AND MATERIALS

This retrospective case-control study was based on a mammography screening cohort from 2008 to 2015. The final study population included screening examinations for 714 women diagnosed with breast cancer and 8029 randomly selected healthy controls. Oversampling of controls was applied to attain a similar cancer proportion as in the source screening cohort. We examined how false-positive (FP) and false-negative (FN) assessments by AI, the first reader (RAD 1) and the second reader (RAD 2), were associated with age, density, tumor histology and cancer invasiveness in a single- and double-reader setting.

RESULTS

For each reader, the FN assessments were distributed between low- and high-density females with 53 (42%) and 72 (58%) for AI; 59 (36%) and 104 (64%) for RAD 1 and 47 (36%) and 84 (64%) for RAD 2. The corresponding numbers for FP assessments were 1820 (47%) and 2016 (53%) for AI; 1568 (46%) and 1834 (54%) for RAD 1 and 1190 (43%) and 1610 (58%) for RAD 2. For ductal cancer, the FN assessments were 79 (77%) for AI CAD; with 120 (83%) for RAD 1 and with 96 (16%) for RAD 2. For the double-reading simulation, the FP assessments were distributed between younger and older females with 2828 (2.5%) and 1554 (1.4%) for RAD 1 + RAD 2; 3850 (3.4%) and 2940 (2.6%) for AI+RAD 1 and 3430 (3%) and 2772 (2.5%) for AI+RAD 2.

CONCLUSION

The most pronounced decrease in FN assessments was noted for females over the age of 55 and for high density-women. In conclusion, AI could have an important complementary role when combined with radiologists to increase sensitivity for high-density and older females.

ADVANCES IN KNOWLEDGE

Our results highlight the potential impact of integrating AI in breast cancer screening, particularly to improve interpretation accuracy. The use of AI could enhance screening outcomes for high-density and older females.

Breast Cancer Risk Reduction: Current Status and Emerging Trends to Increase Efficacy and Reduce Toxicity of Preventive Medication

The primary prevention of breast cancer is a worthwhile goal for which the efficacy of antiestrogens is well established. However, implementation has been problematic related to low prioritization by providers and the reluctance of high-risk women to experience medication side effects. Emerging solutions include improved risk estimation through the use of polygenic risk scores and the application of radiomics to screening mammograms; and optimization of medication dose to limit toxicity. The identification of agents to prevent estrogen receptor negative or HER2-positive tumors is being pursued, but personalization of medical risk reduction requires the prediction of tumor subtypes.

Association and Prediction Utilizing Craniocaudal and Mediolateral Oblique View Digital Mammography and Long-Term Breast Cancer Risk

Mammographic percentage of volumetric density is an important risk factor for breast cancer. Epidemiology studies historically used film images often limited to craniocaudal (CC) views to estimate area-based breast density. More recent studies using digital mammography images typically use the averaged density between craniocaudal (CC) and mediolateral oblique (MLO) view mammography for 5- and 10-year risk prediction. The performance in using either and both mammogram views has not been well-investigated. We use 3,804 full-field digital mammograms from the Joanne Knight Breast Health Cohort (294 incident cases and 657 controls), to quantity the association between volumetric percentage of density extracted from either and both mammography views and to assess the 5 and 10-year breast cancer risk prediction performance. Our results show that the association between percent volumetric density from CC, MLO, and the average between the two, retain essentially the same association with breast cancer risk. The 5- and 10-year risk prediction also shows similar prediction accuracy. Thus, one view is sufficient to assess association and predict future risk of breast cancer over a 5 or 10-year interval.

PREVENTION RELEVANCE

Expanding use of digital mammography and repeated screening provides opportunities for risk assessment. To use these images for risk estimates and guide risk management in real time requires efficient processing. Evaluating the contribution of different views to prediction performance can guide future applications for risk management in routine care.

Breast Cancer Screening for Women at Higher-Than-Average Risk: Updated Recommendations From the ACR

Early detection decreases breast cancer death. The ACR recommends annual screening beginning at age 40 for women of average risk and earlier and/or more intensive screening for women at higher-than-average risk. For most women at higher-than-average risk, the supplemental screening method of choice is breast MRI. Women with genetics-based increased risk, those with a calculated lifetime risk of 20% or more, and those exposed to chest radiation at young ages are recommended to undergo MRI surveillance starting at ages 25 to 30 and annual mammography (with a variable starting age between 25 and 40, depending on the type of risk). Mutation carriers can delay mammographic screening until age 40 if annual screening breast MRI is performed as recommended. Women diagnosed with breast cancer before age 50 or with personal histories of breast cancer and dense breasts should undergo annual supplemental breast MRI. Others with personal histories, and those with atypia at biopsy, should strongly consider MRI screening, especially if other risk factors are present. For women with dense breasts who desire supplemental screening, breast MRI is recommended. For those who qualify for but cannot undergo breast MRI, contrast-enhanced mammography or ultrasound could be considered. All women should undergo risk assessment by age 25, especially Black women and women of Ashkenazi Jewish heritage, so that those at higher-than-average risk can be identified and appropriate screening initiated.

PACS-integrated machine learning breast density classifier: clinical validation

OBJECTIVE

To test the performance of a novel machine learning-based breast density tool. The tool utilizes a convolutional neural network to predict the BI-RADS based density assessment of a study. The clinical density assessments of 33,000 mammographic examinations (164,000 images) from one academic medical center (Site A) were used for training.

MATERIALS AND METHODS

This was an IRB approved HIPAA compliant study performed at two academic medical centers. The validation data set was composed of 500 studies from one site (Site A) and 700 from another (Site B). At Site A, each study was assessed by three breast radiologists and the majority (consensus) assessment was used as truth. At Site B, if the tool agreed with the clinical reading, then it was considered to have correctly predicted the clinical reading. In cases where the tool and the clinical reading disagreed, then the study was evaluated by three radiologists and the consensus reading was used as the clinical reading.

RESULTS

For the classification into the four categories of the Breast Imaging Reporting and Data System (BI-RADS®), the AI classifier had an accuracy of 84.6% at Site A and 89.7% at Site B. For binary classification (dense vs. non-dense), the AI classifier had an accuracy of 94.4% at Site A and 97.4% at Site B. In no case did the classifier disagree with the consensus reading by more than one category.

CONCLUSIONS

The automated breast density tool showed high agreement with radiologists' assessments of breast density.

Menopausal Hormone Therapy in Older Women: Examining the Current Balance of Evidence

Menopause occurs in all women. During the menopause transition, 80% of women experience vasomotor symptoms that can last an average of 7-10 years or longer, sometimes into the seventh and eighth decades of life. Understanding how to manage vasomotor symptoms (VMS) in older menopausal women is important since these symptoms can negatively impact quality of life. This review provides a practical guide on how to approach VMS treatment either with menopausal hormone therapy or non-hormone options. When initiating, as well as continuing hormone therapy, the factors clinicians should consider as they weigh risks and benefits include assessing a woman's risks related to cardiovascular disease, breast cancer, and osteoporosis. Utilizing a shared decision-making approach in regard to menopausal symptom management should aim to support women and help them maintain health and quality of life.

Comparison of Mammography AI Algorithms with a Clinical Risk Model for 5-year Breast Cancer Risk Prediction: An Observational Study

Background Although several clinical breast cancer risk models are used to guide screening and prevention, they have only moderate discrimination. Purpose To compare selected existing mammography artificial intelligence (AI) algorithms and the Breast Cancer Surveillance Consortium (BCSC) risk model for prediction of 5-year risk. Materials and Methods This retrospective case-cohort study included data in women with a negative screening mammographic examination (no visible evidence of cancer) in 2016, who were followed until 2021 at Kaiser Permanente Northern California. Women with prior breast cancer or a highly penetrant gene mutation were excluded. Of the 324 009 eligible women, a random subcohort was selected, regardless of cancer status, to which all additional patients with breast cancer were added. The index screening mammographic examination was used as input for five AI algorithms to generate continuous scores that were compared with the BCSC clinical risk score. Risk estimates for incident breast cancer 0 to 5 years after the initial mammographic examination were calculated using a time-dependent area under the receiver operating characteristic curve (AUC). Results The subcohort included 13 628 patients, of whom 193 had incident cancer. Incident cancers in eligible patients (additional 4391 of 324 009) were also included. For incident cancers at 0 to 5 years, the time-dependent AUC for BCSC was 0.61 (95% CI: 0.60, 0.62). AI algorithms had higher time-dependent AUCs than did BCSC, ranging from 0.63 to 0.67 (Bonferroni-adjusted P < .0016). Time-dependent AUCs for combined BCSC and AI models were slightly higher than AI alone (AI with BCSC time-dependent AUC range, 0.66-0.68; Bonferroni-adjusted P < .0016). Conclusion When using a negative screening examination, AI algorithms performed better than the BCSC risk model for predicting breast cancer risk at 0 to 5 years. Combined AI and BCSC models further improved prediction. © RSNA, 2023 Supplemental material is available for this article.

Validation Study on Risk-Reduction Activities after Exposure to a Personalized Breast Cancer Risk-Assessment Education Tool in High-Risk Women in the WISDOM Study

We performed a 318-participant validation study of an individualized risk assessment tool in women identified as having high- or highest-risk of breast cancer in the personalized arm of the Women Informed to Screen Depending on Measures of risk (WISDOM) trial. Per protocol, these women were educated about their risk and risk reducing options using the Breast Health Decisions (BHD) tool, which uses patient-friendly visuals and 8th grade reading level language to convey risk and prevention options. Prior to exposure to the educational tool, 4.7% of women were already taking endocrine risk reduction, 38.7% were reducing alcohol intake, and 62.6% were exercising. Three months after initial use of BHD, 8.4% of women who considered endocrine risk reduction, 33% of women who considered alcohol reduction, and 46% of women who considered exercise pursued the risk-reducing activities. Unlike lifestyle interventions which are under the control of the patient, additional barriers at the level of the healthcare provider may be impeding the targeted use of endocrine risk reduction medications in women with elevated breast cancer risk.

Will Absolute Risk Estimation for Time to Next Screen Work for an Asian Mammography Screening Population?

Personalized breast cancer risk profiling has the potential to promote shared decision-making and improve compliance with routine screening. We assessed the Gail model's performance in predicting the short-term (2- and 5-year) and the long-term (10- and 15-year) absolute risks in 28,234 asymptomatic Asian women. Absolute risks were calculated using different relative risk estimates and Breast cancer incidence and mortality rates (White, Asian-American, or the Singapore Asian population). Using linear models, we tested the association of absolute risk and age at breast cancer occurrence. Model discrimination was moderate (AUC range: 0.580-0.628). Calibration was better for longer-term prediction horizons (E/O_{long-term ranges}: 0.86-1.71; E/O_{short-term ranges}:1.24-3.36). Subgroup analyses show that the model underestimates risk in women with breast cancer family history, positive recall status, and prior breast biopsy, and overestimates risk in underweight women. The Gail model absolute risk does not predict the age of breast cancer occurrence. Breast cancer risk prediction tools performed better with population-specific parameters. Two-year absolute risk estimation is attractive for breast cancer screening programs, but the models tested are not suitable for identifying Asian women at increased risk within this short interval.

Automatic assessment of mammographic density using a deep transfer learning method

Purpose

Mammographic breast density is one of the strongest risk factors for cancer. Density assessed by radiologists using visual analogue scales has been shown to provide better risk predictions than other methods. Our purpose is to build automated models using deep learning and train on radiologist scores to make accurate and consistent predictions.

Approach

We used a dataset of almost 160,000 mammograms, each with two independent density scores made by expert medical practitioners. We used two pretrained deep networks and adapted them to produce feature vectors, which were then used for both linear and nonlinear regression to make density predictions. We also simulated an "optimal method," which allowed us to compare the quality of our results with a simulated upper bound on performance.

Results

Our deep learning method produced estimates with a root mean squared error (RMSE) of 8.79 ± 0.21 . The model estimates of cancer risk perform at a similar level to human experts, within uncertainty bounds. We made comparisons between different model variants and demonstrated the high level of consistency of the model predictions. Our modeled "optimal method" produced image predictions with a RMSE of between 7.98 and 8.90 for cranial caudal images.

Conclusion

We demonstrated a deep learning framework based upon a transfer learning approach to make density estimates based on radiologists' visual scores. Our approach requires modest computational resources and has the potential to be trained with limited quantities of data.

Breast Cancer Risk Assessment Tools for Stratifying Women into Risk Groups: A Systematic Review

BACKGROUND

The benefits and harms of breast screening may be better balanced through a risk-stratified approach. We conducted a systematic review assessing the accuracy of questionnaire-based risk assessment tools for this purpose.

METHODS

Population: asymptomatic women aged ≥40 years; Intervention: questionnaire-based risk assessment tool (incorporating breast density and polygenic risk where available); Comparison: different tool applied to the same population; Primary outcome: breast cancer incidence; Scope: external validation studies identified from databases including Medline and Embase (period 1 January 2008-20 July 2021). We assessed calibration (goodness-of-fit) between expected and observed cancers and compared observed cancer rates by risk group. Risk of bias was assessed with PROBAST.

RESULTS

Of 5124 records, 13 were included examining 11 tools across 15 cohorts. The Gail tool was most represented (n = 11), followed by Tyrer-Cuzick (n = 5), BRCAPRO and iCARE-Lit (n = 3). No tool was consistently well-calibrated across multiple studies and breast density or polygenic risk scores did not improve calibration. Most tools identified a risk group with higher rates of observed cancers, but few tools identified lower-risk groups across different settings. All tools demonstrated a high risk of bias.

CONCLUSION

Some risk tools can identify groups of women at higher or lower breast cancer risk, but this is highly dependent on the setting and population.

Association of Longitudinal Mammographic Breast Density Changes with Subsequent Breast Cancer Risk

Background Although Breast Imaging Reporting and Data System (BI-RADS) density classification has been used to assess future breast cancer risk, its reliability and validity are still debated in literature. Purpose To determine the association between overall longitudinal changes in mammographic breast density and breast cancer risk stratified by menopausal status. Materials and Methods In a retrospective cohort study using the Korean National Health Insurance Service database, women aged at least 40 years without a history of cancer who underwent three consecutive biennial mammographic screenings in 2009-2014 were followed up through December 2020. Participants were divided according to baseline breast density: fatty (BI-RADS categories a, b) versus dense (BI-RADS categories c, d) and then into subgroups on the basis of changes from the first to second and from second to third screenings. Women without change in breast density were used as the reference group. Main outcomes were incident breast cancer events, both invasive breast cancer and ductal carcinoma in situ. Cox proportion hazard regression was used to calculate the hazard ratio (HR) with adjustment for other covariables. Results Among 2 253 963 women (mean age, 59 years ± 9) there were 22 439 detected breast cancers. Premenopausal women with fatty breasts at the first screening had a higher risk of breast cancer as density increased in the second and third screenings (fatty-to-dense HR, 1.45 [95% CI: 1.27, 1.65]; dense-to-fatty HR, 1.53 [95% CI: 1.34, 1.74]; dense-to-dense HR, 1.93 [95% CI: 1.75, 2.13]). In premenopausal women with dense breasts at baseline, those in whom density continuously decreased had a 0.62-fold lower risk (95% CI: 0.56, 0.69). Similar results were observed in postmenopausal women, remaining significant after adjustment for baseline breast density or changes in body mass index (fatty-to-dense HR, 1.50 [95% CI: 1.39, 1.62]; dense-to-fatty HR, 1.42 [95% CI: 1.31, 1.53]; dense-to-dense HR, 1.62 [95% CI: 1.51, 1.75]). Conclusion In both premenopausal and postmenopausal women undergoing three consecutive biennial mammographic screenings, a consecutive increase in breast density augmented the future breast cancer risk whereas a continuous decrease was associated with a lower risk. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Kataoka et al in this issue.

Mammographic Breast Density: Current Assessment Methods, Clinical Implications, and Future Directions

Mammographic breast density is widely accepted as an independent risk factor for the development of breast cancer. In addition, because dense breast tissue may mask breast malignancies, breast density is inversely related to the sensitivity of screening mammography. Given the risks associated with breast density, as well as ongoing efforts to stratify individual risk and personalize breast cancer screening and prevention, numerous studies have sought to better understand the factors that impact breast density, and to develop and implement reproducible, quantitative methods to assess mammographic density. Breast density assessments have been incorporated into risk assessment models to improve risk stratification. Recently, novel techniques for analyzing mammographic parenchymal complexity, or texture, have been explored as potential means of refining mammographic tissue-based risk assessment beyond breast density.

Studies of parenchymal texture added to mammographic breast density and risk of breast cancer: a systematic review of the methods used in the literature

This systematic review aimed to assess the methods used to classify mammographic breast parenchymal features in relation to the prediction of future breast cancer. The databases including Medline (Ovid) 1946-, Embase.com 1947-, CINAHL Plus 1937-, Scopus 1823-, Cochrane Library (including CENTRAL), and Clinicaltrials.gov were searched through October 2021 to extract published articles in English describing the relationship of parenchymal texture features with the risk of breast cancer. Twenty-eight articles published since 2016 were included in the final review. The identification of parenchymal texture features varied from using a predefined list to machine-driven identification. A reduction in the number of features chosen for subsequent analysis in relation to cancer incidence then varied across statistical approaches and machine learning methods. The variation in approach and number of features identified for inclusion in analysis precluded generating a quantitative summary or meta-analysis of the value of these features to improve predicting risk of future breast cancers. This updated overview of the state of the art revealed research gaps; based on these, we provide recommendations for future studies using parenchymal features for mammogram images to make use of accumulating image data, and external validation of prediction models that extend to 5 and 10 years to guide clinical risk management. Following these recommendations could enhance the applicability of models, helping improve risk classification and risk prediction for women to tailor screening and prevention strategies to the level of risk.

Feasibility Study and Clinical Impact of Incorporating Breast Tissue Density in High-Risk Breast Cancer Screening Assessment

Breast tissue density (BTD) is known to increase the risk of breast cancer but is not routinely used in the risk assessment of the population-based High-Risk Ontario Breast Screening Program (HROBSP). This prospective, IRB-approved study assessed the feasibility and impact of incorporating breast tissue density (BTD) into the risk assessment of women referred to HROBSP who were not genetic mutation carriers. All consecutive women aged 40-69 years who met criteria for HROBSP assessment and referred to Genetics from 1 December 2020 to 31 July 2021 had their lifetime risk calculated with and without BTD using Tyrer-Cuzick model version 8 (IBISv8) to gauge overall impact. McNemar's test was performed to compare eligibility with and without density. 140 women were referred, and 1 was excluded (BRCA gene mutation carrier and automatically eligible). Eight of 139 (5.8%) never had a mammogram, while 17/131 (13%) did not have BTD reported on their mammogram and required radiologist review. Of 131 patients, 22 (16.8%) were clinically impacted by incorporation of BTD: 9/131 (6.9%) became eligible for HROBSP, while 13/131 (9.9%) became ineligible (p = 0.394). It was feasible for the Genetics clinic to incorporate BTD for better risk stratification of eligible women. This did not significantly impact the number of eligible women while optimizing the use of high-risk supplemental MRI screening.

Mammography radiomics features at diagnosis and progression-free survival among patients with breast cancer

BACKGROUND

The associations between mammographic radiomics and breast cancer clinical endpoints are unclear. We aimed to identify mammographic radiomics features associated with breast cancer prognosis.

METHODS

Nested from a large breast cancer cohort in our institution, we conducted an extreme case-control study consisting of 207 cases with any invasive disease-free survival (iDFS) endpoint <5 years and 207 molecular subtype-matched controls with >5-year iDFS. A total of 632 radiomics features in craniocaudal (CC) and mediolateral oblique (MLO) views were extracted from pre-treatment mammography. Logistic regression was used to identify iDFS-associated features with multiple testing corrections (Benjamini-Hochberg method). In a subsample with RNA-seq data (n = 96), gene set enrichment analysis was employed to identify pathways associated with lead features.

RESULTS

We identified 15 iDFS-associated features from CC-view yet none from MLO-view. S(1,-1)SumAverg and WavEnLL_s-6 were the lead ones and associated with favourable (OR 0.64, 95% CI 0.42-0.87, P = 0.01) and poor iDFS (OR 1.53, 95% CI 1.31-1.76, P = 0.01), respectively. Both features were associated with eight pathways (primarily involving cell cycle regulation) in tumour but not adjacent normal tissues.

CONCLUSION

Our findings suggest mammographic radiomics features are associated with breast cancer iDFS, potentially through pathways involving cell cycle regulation.

External Validation of a Mammography-Derived AI-Based Risk Model in a U.S. Breast Cancer Screening Cohort of White and Black Women

Despite the demonstrated potential of artificial intelligence (AI) in breast cancer risk assessment for personalizing screening recommendations, further validation is required regarding AI model bias and generalizability. We performed external validation on a U.S. screening cohort of a mammography-derived AI breast cancer risk model originally developed for European screening cohorts. We retrospectively identified 176 breast cancers with exams 3 months to 2 years prior to cancer diagnosis and a random sample of 4963 controls from women with at least one-year negative follow-up. A risk score for each woman was calculated via the AI risk model. Age-adjusted areas under the ROC curves (AUCs) were estimated for the entire cohort and separately for White and Black women. The Gail 5-year risk model was also evaluated for comparison. The overall AUC was 0.68 (95% CIs 0.64−0.72) for all women, 0.67 (0.61−0.72) for White women, and 0.70 (0.65−0.76) for Black women. The AI risk model significantly outperformed the Gail risk model for all women p < 0.01 and for Black women p < 0.01, but not for White women p = 0.38. The performance of the mammography-derived AI risk model was comparable to previously reported European validation results; non-significantly different when comparing White and Black women; and overall, significantly higher than that of the Gail model.

Implementing Risk-Stratified Breast Screening in England: An Agenda Setting Meeting

It is now possible to accurately assess breast cancer risk at routine NHS Breast Screening Programme (NHSBSP) appointments, provide risk feedback and offer risk management strategies to women at higher risk. These strategies include National Institute for Health and Care Excellence (NICE) approved additional breast screening and risk-reducing medication. However, the NHSBSP invites nearly all women three-yearly, regardless of risk. In March 2022, a one-day agenda setting meeting took place in Manchester to discuss the feasibility and desirability of implementation of risk-stratified screening in the NHSBSP. Fifty-eight individuals participated (38 face-to-face, 20 virtual) with relevant expertise from academic, clinical and/or policy-making perspectives. Key findings were presented from the PROCAS2 NIHR programme grant regarding feasibility of risk-stratified screening in the NHSBSP. Participants discussed key uncertainties in seven groups, followed by a plenary session. Discussions were audio-recorded and thematically analysed to produce descriptive themes. Five themes were developed: (i) risk and health economic modelling; (ii) health inequalities and communication with women; (iii); extending screening intervals for low-risk women; (iv) integration with existing NHSBSP; and (v) potential new service models. Most attendees expected some form of risk-stratified breast screening to be implemented in England and collectively identified key issues to be resolved to facilitate this.

Artificial Intelligence (AI) for Screening Mammography, From the AJR Special Series on AI Applications

Artificial intelligence (AI) applications for screening mammography are being marketed for clinical use in the interpretative domains of lesion detection and diagnosis, triage, and breast density assessment and in the noninterpretive domains of breast cancer risk assessment, image quality control, image acquisition, and dose reduction. Evidence in support of these nascent applications, particularly for lesion detection and diagnosis, is largely based on multireader studies with cancer-enriched datasets rather than rigorous clinical evaluation aligned with the application's specific intended clinical use. This article reviews commercial AI algorithms for screening mammography that are currently available for clinical practice, their use, and evidence supporting their performance. Clinical implementation considerations, such as workflow integration, governance, and ethical issues, are also described. In addition, the future of AI for screening mammography is discussed, including the development of interpretive and noninterpretive AI applications and strategic priorities for research and development.

Breast Density: Current Knowledge, Assessment Methods, and Clinical Implications

Breast density is an accepted independent risk factor for the future development of breast cancer, and greater breast density has the potential to mask malignancies on mammography, thus lowering the sensitivity of screening mammography. The risk associated with dense breast tissue has been shown to be modifiable with changes in breast density. Numerous studies have sought to identify factors that influence breast density, including age, genetic, racial/ethnic, prepubertal, adolescent, lifestyle, environmental, hormonal, and reproductive history factors. Qualitative, semiquantitative, and quantitative methods of breast density assessment have been developed, but to date there is no consensus assessment method or reference standard for breast density. Breast density has been incorporated into breast cancer risk models, and there is growing consciousness of the clinical implications of dense breast tissue in both the medical community and public arena. Efforts to improve breast cancer screening sensitivity for women with dense breasts have led to increased attention to supplemental screening methods in recent years, prompting the American College of Radiology to publish Appropriateness Criteria for supplemental screening based on breast density.

Utility of U-Net for the objective segmentation of the fibroglandular tissue region on clinical digital mammograms

This study investigates the equivalence or compatibility between U-Net and visual segmentations of fibroglandular tissue regions by mammography experts for calculating the breast density and mean glandular dose (MGD). A total of 703 mediolateral oblique-view mammograms were used for segmentation. Two region types were set as the ground truth (determined visually): (1) one type included only the region where fibroglandular tissue was identifiable (called the 'dense region'); (2) the other type included the region where the fibroglandular tissue may have existed in the past, provided that apparent adipose-only parts, such as the retromammary space, are excluded (the 'diffuse region'). U-Net was trained to segment the fibroglandular tissue region with an adaptive moment estimation optimiser, five-fold cross-validated with 400 training and 100 validation mammograms, and tested with 203 mammograms. The breast density and MGD were calculated using the van Engeland and Dance formulas, respectively, and compared between U-Net and the ground truth with the Dice similarity coefficient and Bland-Altman analysis. Dice similarity coefficients between U-Net and the ground truth were 0.895 and 0.939 for the dense and diffuse regions, respectively. In the Bland-Altman analysis, no proportional or fixed errors were discovered in either the dense or diffuse region for breast density, whereas a slight proportional error was discovered in both regions for the MGD (the slopes of the regression lines were -0.0299 and -0.0443 for the dense and diffuse regions, respectively). Consequently, the U-Net and ground truth were deemed equivalent (interchangeable) for breast density and compatible (interchangeable following four simple arithmetic operations) for MGD. U-Net-based segmentation of the fibroglandular tissue region was satisfactory for both regions, providing reliable segmentation for breast density and MGD calculations. U-Net will be useful in developing a reliable individualised screening-mammography programme, instead of relying on the visual judgement of mammography experts.

Breast cancer screening in women with extremely dense breasts recommendations of the European Society of Breast Imaging (EUSOBI)

Breast density is an independent risk factor for the development of breast cancer and also decreases the sensitivity of mammography for screening. Consequently, women with extremely dense breasts face an increased risk of late diagnosis of breast cancer. These women are, therefore, underserved with current mammographic screening programs. The results of recent studies reporting on contrast-enhanced breast MRI as a screening method in women with extremely dense breasts provide compelling evidence that this approach can enable an important reduction in breast cancer mortality for these women and is cost-effective. Because there is now a valid option to improve breast cancer screening, the European Society of Breast Imaging (EUSOBI) recommends that women should be informed about their breast density. EUSOBI thus calls on all providers of mammography screening to share density information with the women being screened. In light of the available evidence, in women aged 50 to 70 years with extremely dense breasts, the EUSOBI now recommends offering screening breast MRI every 2 to 4 years. The EUSOBI acknowledges that it may currently not be possible to offer breast MRI immediately and everywhere and underscores that quality assurance procedures need to be established, but urges radiological societies and policymakers to act on this now. Since the wishes and values of individual women differ, in screening the principles of shared decision-making should be embraced. In particular, women should be counselled on the benefits and risks of mammography and MRI-based screening, so that they are capable of making an informed choice about their preferred screening method. KEY POINTS: • The recommendations in Figure 1 summarize the key points of the manuscript.

Mammographic Breast Density, Benign Breast Disease, and Subsequent Breast Cancer Risk in 3.9 Million Korean Women

Background Mammographic breast density and benign breast disease are strong risk factors for breast cancer. Accordingly, women with both risk factors may have a markedly high risk for developing breast cancer. Purpose To investigate the risk of breast cancer associated with the combination of mammographic density and benign breast disease in Korean women, where population-based mammographic breast cancer screening is provided for all women aged at least 40 years. Materials and Methods This is a retrospective analysis of data from a nationwide breast cancer screening program linked with the national cancer registry. The study included Korean women between 40-74 years of age screened for breast cancer between January 2009 and December 2010 and observed up to December 2020 (median follow-up of 10.6 years). Benign breast disease and breast density were extracted from mammography screening results. Cox proportional hazard regression analysis was used to calculate adjusted hazard ratios (HRs) for breast cancer risk. Results In this study, 3 911 348 women (mean age, 53 years ± 9 [SD]) were analyzed. During follow-up (median, 10.6 years), 58 321 women developed breast cancer. At screening, 10 729 (18.4%) cases of benign breast disease were detected among women who developed breast cancer. Women with extremely dense breasts (Breast Imaging Reporting and Data System [BI-RADS] density category D) and benign breast disease had a greater risk of breast cancer when compared with women presenting with fatty breast (BI-RADS density category A) and those without benign breast disease (HR, 2.75; 95% CI: 2.63, 2.88; P < .001). Women with benign breast disease and fatty breasts (HR, 1.49; 95% CI: 1.40, 1.58; P < .001) and women with extremely dense breasts and without benign breast disease (HR, 2.28; 95% CI: 2.20, 2.35; P < .001) also had an elevated breast cancer risk compared with women with fatty breast tissue. Conclusion Women with dense breasts and benign breast disease at screening mammography had an elevated risk of future breast cancer. © RSNA, 2022 Online supplemental material is available for this article.

Interval Cancer Detection Using a Neural Network and Breast Density in Women with Negative Screening Mammograms

Background Inclusion of mammographic breast density (BD) in breast cancer risk models improves accuracy, but accuracy remains modest. Interval cancer (IC) risk prediction may be improved by combining assessments of BD and an artificial intelligence (AI) cancer detection system. Purpose To evaluate the performance of a neural network (NN)-based model that combines the assessments of BD and an AI system in the prediction of risk of developing IC among women with negative screening mammography results. Materials and Methods This retrospective nested case-control study performed with screening examinations included women who developed IC and women with normal follow-up findings (from January 2011 to January 2015). An AI cancer detection system analyzed all studies yielding a score of 1-10, representing increasing likelihood of malignancy. BD was automatically computed using publicly available software. An NN model was trained by combining the AI score and BD using 10-fold cross-validation. Bootstrap analysis was used to calculate the area under the receiver operating characteristic curve (AUC), sensitivity at 90% specificity, and 95% CIs of the AI, BD, and NN models. Results A total of 2222 women with IC and 4661 women in the control group were included (mean age, 61 years; age range, 49-76 years). AUC of the NN model was 0.79 (95% CI: 0.77,0.81), which was higher than AUC of the AI cancer detection system or BD alone (AUC, 0.73 [95% CI: 0.71, 0.76] and 0.69 [95% CI: 0.67, 0.71], respectively; P < .001 for both). At 90% specificity, the NN model had a sensitivity of 50.9% (339 of 666 women; 95% CI: 45.2, 56.3) for prediction of IC, which was higher than that of the AI system (37.5%; 250 of 666 women; 95% CI: 33.0, 43.7; P < .001) or BD percentage alone (22.4%; 149 of 666 women; 95% CI: 17.9, 28.5; P < .001). Conclusion The combined assessment of an artificial intelligence detection system and breast density measurements enabled identification of a larger proportion of women who would develop interval cancer compared with either method alone. Published under a CC BY 4.0 license.

Identifying and Managing Patients with Elevated Breast Cancer Risk Presenting for Screening Mammography

BACKGROUND

Identifying the prevalence and management of patients at high-risk for breast cancer can improve resource utilization and provide individualized screening strategies.

OBJECTIVE

The purpose of this study was to identify the prevalence of high-risk patients in our institution who presented for screening mammography and to understand how they utilized downstream resources offered to them.

MATERIALS AND METHODS

This single institution retrospective study utilized the Tyrer-Cuzick risk assessment model to provide lifetime risk of breast cancer of patients presenting for screening mammography over a one-year period. Their subsequent management and resource utilization were collated.

RESULTS

High-risk patients comprised 7.7% (701/9061) of our screening population. Of those high-risk women offered a Breast Center (BC) consultation, 75.2% (276/367) participated in the consultation, with 51.1% (141/276) of those patients completing MRI for supplemental screening. Risk reducing medication was adopted by 7.6% (6/79) of those offered. Of patients offered a genetics consultation, 66.3% (53/80) participated in the consultation, and 50.0% (40/80) completed genetic testing.

CONCLUSIONS

Identifying and understanding high-risk patient cohorts, whether locally or in a population-based context, is important for individualized patient care and practice efficiency.

Prostate cancer risk stratification improvement across multiple ancestries with new polygenic hazard score

BACKGROUND

Prostate cancer risk stratification using single-nucleotide polymorphisms (SNPs) demonstrates considerable promise in men of European, Asian, and African genetic ancestries, but there is still need for increased accuracy. We evaluated whether including additional SNPs in a prostate cancer polygenic hazard score (PHS) would improve associations with clinically significant prostate cancer in multi-ancestry datasets.

METHODS

In total, 299 SNPs previously associated with prostate cancer were evaluated for inclusion in a new PHS, using a LASSO-regularized Cox proportional hazards model in a training dataset of 72,181 men from the PRACTICAL Consortium. The PHS model was evaluated in four testing datasets: African ancestry, Asian ancestry, and two of European Ancestry-the Cohort of Swedish Men (COSM) and the ProtecT study. Hazard ratios (HRs) were estimated to compare men with high versus low PHS for association with clinically significant, with any, and with fatal prostate cancer. The impact of genetic risk stratification on the positive predictive value (PPV) of PSA testing for clinically significant prostate cancer was also measured.

RESULTS

The final model (PHS290) had 290 SNPs with non-zero coefficients. Comparing, for example, the highest and lowest quintiles of PHS290, the hazard ratios (HRs) for clinically significant prostate cancer were 13.73 [95% CI: 12.43-15.16] in ProtecT, 7.07 [6.58-7.60] in African ancestry, 10.31 [9.58-11.11] in Asian ancestry, and 11.18 [10.34-12.09] in COSM. Similar results were seen for association with any and fatal prostate cancer. Without PHS stratification, the PPV of PSA testing for clinically significant prostate cancer in ProtecT was 0.12 (0.11-0.14). For the top 20% and top 5% of PHS290, the PPV of PSA testing was 0.19 (0.15-0.22) and 0.26 (0.19-0.33), respectively.

CONCLUSIONS

We demonstrate better genetic risk stratification for clinically significant prostate cancer than prior versions of PHS in multi-ancestry datasets. This is promising for implementing precision-medicine approaches to prostate cancer screening decisions in diverse populations.

Effective Surveillance of High-Risk Women

BACKGROUND

This study addresses the effectiveness of risk models and screening breast magnetic resonance imaging (MRI) in women who have atypical hyperplasia (AH), lobular carcinoma in situ (LCIS), or a family history of breast cancer, but not a genetic mutation.

PATIENTS AND METHODS

A retrospective review of 444 women who had 458 breast screening MRIs at a community teaching hospital over a 12-month period between March 25, 2014 and March 31, 2015 was performed. The patients underwent high risk screening with breast MRIs alternating with mammograms every 6 months. After excluding patients with prior breast or ovarian cancer, genetic mutations, and chest wall radiation, 200 remaining patients constituted the study cohort. Over the following 5 years, the patients were screened with MRIs alternating with mammograms every 6 months. A total of 961 total MRI screenings were performed over the entire 5-year period of the study.

RESULTS

A total of 200 women fit the study criteria. Of these 103 had a prior history of AH or LCIS. Over the 5-year period, 60 women dropped out of the screening regimen, 6 patients were diagnosed with breast cancer on screening MRIs, and 2 additional patients were diagnosed with breast cancer on screening mammograms. Surprisingly, the highest Tyrer-Cuzick (T-C) scores did not correlate with increased development of breast cancers in our population.

CONCLUSIONS

This study shows that there is wide variation in the results of risk assessment models. Risk models may overestimate breast cancer risk, suggesting that re-evaluation of current risk assessment and screening protocols is warranted.

The current status of risk-stratified breast screening

Apart from high-risk scenarios such as the presence of highly penetrant genetic mutations, breast screening typically comprises mammography or tomosynthesis strategies defined by age. However, age-based screening ignores the range of breast cancer risks that individual women may possess and is antithetical to the ambitions of personalised early detection. Whilst screening mammography reduces breast cancer mortality, this is at the risk of potentially significant harms including overdiagnosis with overtreatment, and psychological morbidity associated with false positives. In risk-stratified screening, individualised risk assessment may inform screening intensity/interval, starting age, imaging modality used, or even decisions not to screen. However, clear evidence for its benefits and harms needs to be established. In this scoping review, the authors summarise the established and emerging evidence regarding several critical dependencies for successful risk-stratified breast screening: risk prediction model performance, epidemiological studies, retrospective clinical evaluations, health economic evaluations and qualitative research on feasibility and acceptability. Family history, breast density or reproductive factors are not on their own suitable for precisely estimating risk and risk prediction models increasingly incorporate combinations of demographic, clinical, genetic and imaging-related parameters. Clinical evaluations of risk-stratified screening are currently limited. Epidemiological evidence is sparse, and randomised trials only began in recent years.

Novel Interactive Tool for Breast and Ovarian Cancer Risk Assessment (Bright Pink Assess Your Risk): Development and Usability Study

Background

The lifetime risk of breast and ovarian cancer is significantly higher among women with genetic susceptibility or a strong family history. However, current risk assessment tools and clinical practices may identify only 10% of asymptomatic carriers of susceptibility genes. Bright Pink developed the Assess Your Risk (AYR) tool to estimate breast and ovarian cancer risk through a user-friendly, informative web-based quiz for risk assessment at the population level.

Objective

This study aims to present the AYR tool, describe AYR users, and present evidence that AYR works as expected by comparing classification using the AYR tool with gold standard genetic testing guidelines.

Methods

The AYR is a recently developed population-level risk assessment tool that includes 26 questions based on the National Comprehensive Cancer Network (NCCN) guidelines and factors from other commonly used risk assessment tools. We included all women who completed the AYR between November 2018 and January 2019, with the exception of self-reported cancer or no knowledge of family history. We compared AYR classifications with those that were independently created using NCCN criteria using measures of validity and the McNemar test.

Results

There were 143,657 AYR completions, and most participants were either at increased or average risk for breast cancer or ovarian cancer (137,315/143,657, 95.59%). Using our estimates of increased and average risk as the gold standard, based on the NCCN guidelines, we estimated the sensitivity and specificity for the AYR algorithm–generated risk categories as 100% and 89.9%, respectively (P<.001). The specificity improved when we considered the additional questions asked by the AYR to define increased risk, which were not examined by the NCCN criteria. By race, ethnicity, and age group; we found that the lowest observed specificity was for the Asian race (85.9%) and the 30 to 39 years age group (87.6%) for the AYR-generated categories compared with the NCCN criteria.

Conclusions

These results demonstrate that Bright Pink’s AYR is an accurate tool for use by the general population to identify women at increased risk of breast and ovarian cancer. We plan to validate the tool longitudinally in future studies, including the impact of race, ethnicity, and age on breast and ovarian cancer risk assessment.

Prospective evaluation of a breast-cancer risk model integrating classical risk factors and polygenic risk in 15 cohorts from six countries

BACKGROUND

Rigorous evaluation of the calibration and discrimination of breast-cancer risk-prediction models in prospective cohorts is critical for applications under clinical guidelines. We comprehensively evaluated an integrated model incorporating classical risk factors and a 313-variant polygenic risk score (PRS) to predict breast-cancer risk.

METHODS

Fifteen prospective cohorts from six countries with 239 340 women (7646 incident breast-cancer cases) of European ancestry aged 19-75 years were included. Calibration of 5-year risk was assessed by comparing expected and observed proportions of cases overall and within risk categories. Risk stratification for women of European ancestry aged 50-70 years in those countries was evaluated by the proportion of women and future cases crossing clinically relevant risk thresholds.

RESULTS

Among women <50 years old, the median (range) expected-to-observed ratio for the integrated model across 15 cohorts was 0.9 (0.7-1.0) overall and 0.9 (0.7-1.4) at the highest-risk decile; among women ≥50 years old, these were 1.0 (0.7-1.3) and 1.2 (0.7-1.6), respectively. The proportion of women identified above a 3% 5-year risk threshold (used for recommending risk-reducing medications in the USA) ranged from 7.0% in Germany (∼841 000 of 12 million) to 17.7% in the USA (∼5.3 of 30 million). At this threshold, 14.7% of US women were reclassified by adding the PRS to classical risk factors, with identification of 12.2% of additional future cases.

CONCLUSION

Integrating a 313-variant PRS with classical risk factors can improve the identification of European-ancestry women at elevated risk who could benefit from targeted risk-reducing strategies under current clinical guidelines.

The Value of Tyrer-Cuzick Versus Gail Risk Modeling in Predicting Benefit from Screening MRI in Breast Cancer

OBJECTIVE

Breast cancer is the most commonly diagnosed malignancy in US women. Risk assessment tools such as the Gail and Tyrer-Cuzick (TC) models calculate risk for breast cancer based on modifiable and non-modifiable factors in order to guide screening and prevention for high-risk patients. Screening with magnetic resonance imaging (MRI) in addition to mammography is recommended in high-risk patients (>20% lifetime risk on TC or other familial based models). Currently, no published data indicate these recommendations improve cancer detection.

MATERIALS AND METHODS

With the aim to determine what percentage lifetime risk (LR%) is associated with a statistically significant increase in cancer detection, the Virginia Commonwealth University (VCU) breast imaging database was reviewed to identify patients who received screening MRI.

RESULTS

The receiver operating characteristics (ROC) curves for the Gail and TC models and the rate of cancer detection correlated to 20% LR% were calculated. The Gail model was considered the control model as it is NOT considered a validated screening tool for MRI. TC is not more accurate than Gail when predicting benefit of breast MRI screening. (area under the curve (AUC): 0.6841, 0.6543 respectively, p = 0.828). Univariate analysis failed to demonstrate a statistically significant relationship between the Gail or TC LR % and diagnosis of breast cancer when using 20% as the cutoff for high-risk classification (p = 1.0, 0.369 respectively). Neither the TC nor the Gail risk calculators demonstrated a significant correlation between risk and the likelihood of diagnosis of breast cancer when screened with MRI.

CONCLUSION

Larger cohort studies are necessary to determine the risk percentage most predictive of a breast cancer diagnosis using MRI as screening.

Validation of Breast Cancer Risk Models by Race/Ethnicity, Family History and Molecular Subtypes

(1) Background: The purpose of this study is to compare the performance of four breast cancer risk prediction models by race, molecular subtype, family history of breast cancer, age, and BMI. (2) Methods: Using a cohort of women aged 40-84 without prior history of breast cancer who underwent screening mammography from 2006 to 2015, we generated breast cancer risk estimates using the Breast Cancer Risk Assessment tool (BCRAT), BRCAPRO, Breast Cancer Surveillance Consortium (BCSC) and combined BRCAPRO+BCRAT models. Model calibration and discrimination were compared using observed-to-expected ratios (O/E) and the area under the receiver operator curve (AUC) among patients with at least five years of follow-up. (3) Results: We observed comparable discrimination and calibration across models. There was no significant difference in model performance between Black and White women. Model discrimination was poorer for HER2+ and triple-negative subtypes compared with ER/PR+HER2-. The BRCAPRO+BCRAT model displayed improved calibration and discrimination compared to BRCAPRO among women with a family history of breast cancer. Across models, discriminatory accuracy was greater among obese than non-obese women. When defining high risk as a 5-year risk of 1.67% or greater, models demonstrated discordance in 2.9% to 19.7% of patients. (4) Conclusions: Our results can inform the implementation of risk assessment and risk-based screening among women undergoing screening mammography.

Mammography screening and mortality by risk status in the California teachers study

Background

The debate continues among medical professionals regarding the frequency, starting age, and stopping age for mammography screening. Some experts suggest tailoring recommendations based on individuals’ personal breast cancer risk. Previous studies have not compared the impact of annual versus biennial mammography stratified by age group and risk category. The purpose of this study was to examine the relationship between mammography frequency and mortality by age group and risk category in the California Teachers Study.

Methods

Using data from study questionnaires from 93,438 women between the ages of 40 and 85 and linkages to the California Cancer Registry and other indices, overall and breast cancer-specific mortality by mammography frequency were estimated using multivariable Cox proportional hazards models, stratified by age group and risk category at baseline as determined by the Gail breast cancer risk model.

Results

During the follow-up period of 20 years, overall mortality risk was lower in women who had annual or biennial mammography compared to less frequent or no mammography in all age groups. Annual mammography was associated with lower overall mortality risk compared to biennial mammography among women age 50–85. This difference was especially apparent in women age 60–74, regardless of estimated Gail risk category at baseline. Breast cancer-specific mortality was lower among women who had annual mammography compared to biennial or less frequent mammography among women age 60–74, regardless of their baseline risk.

Conclusions

Our findings suggest that at least biennial mammography is beneficial to most women age 40–85 and that annual mammography is more beneficial than biennial mammography to most women age 50–85 in terms of overall mortality.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12885-021-09071-1.