Breast Density Patterns Research Articles

Concordant and discordant breast density patterns by different approaches for assessing breast density and breast cancer risk.

To examine the discrepancy in breast density assessments by radiologists, LIBRA software, and AI algorithm and their association with breast cancer risk. Among 74,610 Korean women aged ≥ 34years, who underwent screening mammography, density estimates obtained from both LIBRA and the AI algorithm were compared to radiologists using BI-RADS density categories (A-D, designating C and D as dense breasts). The breast cancer risks were compared according to concordant or discordant dense breasts identified by radiologists, LIBRA, and AI. Cox-proportional hazards models were used to determine adjusted hazard ratios (aHRs) [95% confidence intervals (CIs)]. During a median follow-up of 9.9years, 479 breast cancer cases developed. Compared to the reference non-dense breast group, the aHRs (95% CIs) for breast cancer were 2.37 (1.68-3.36) for radiologist-classified dense breasts, 1.30 (1.05-1.62) for LIBRA, and 2.55 (1.84-3.56) for AI. For different combinations of breast density assessment, aHRs (95% CI) for breast cancer were 2.40 (1.69-3.41) for radiologist-dense/LIBRA-non-dense, 11.99 (1.64-87.62) for radiologist-non-dense/LIBRA-dense, and 2.99 (1.99-4.50) for both dense breasts, compared to concordant non-dense breasts. Similar trends were observed with radiologists/AI classification: the aHRs (95% CI) were 1.79 (1.02-3.12) for radiologist-dense/AI-non-dense, 2.43 (1.24-4.78) for radiologist-non-dense/AI-dense, and 3.23 (2.15-4.86) for both dense breasts. The risk of breast cancer was highest in concordant dense breasts. Discordant dense breast cases also had a significantly higher risk of breast cancer, especially when identified as dense by either AI or LIBRA, but not radiologists, compared to concordant non-dense breast cases.

A Nomogram Using Imaging Features to Predict Ipsilateral Breast Tumor Recurrence After Breast-Conserving Surgery for Ductal Carcinoma In Situ.

To develop a nomogram that integrates clinical-pathologic and imaging variables to predict ipsilateral breast tumor recurrence (IBTR) in women with ductal carcinoma in situ (DCIS) treated with breast-conserving surgery (BCS). This retrospective study included consecutive women with DCIS who underwent BCS at two hospitals. Patients who underwent BCS between 2003 and 2016 in one hospital and between 2005 and 2013 in another were classified into development and validation cohorts, respectively. Twelve clinical-pathologic variables (age, family history, initial presentation, nuclear grade, necrosis, margin width, number of excisions, DCIS size, estrogen receptor, progesterone receptor, radiation therapy, and endocrine therapy) and six mammography and ultrasound variables (breast density, detection modality, mammography and ultrasound patterns, morphology and distribution of calcifications) were analyzed. A nomogram for predicting 10-year IBTR probabilities was constructed using the variables associated with IBTR identified from the Cox proportional hazard regression analysis in the development cohort. The performance of the developed nomogram was evaluated in the external validation cohort using a calibration plot and 10-year area under the receiver operating characteristic curve (AUROC) and compared with the Memorial Sloan-Kettering Cancer Center (MSKCC) nomogram. The development cohort included 702 women (median age [interquartile range], 50 [44-56] years), of whom 30 (4%) women experienced IBTR. The validation cohort included 182 women (48 [43-54] years), 18 (10%) of whom developed IBTR. A nomogram was constructed using three clinical-pathologic variables (age, margin, and use of adjuvant radiation therapy) and two mammographic variables (breast density and calcification morphology). The nomogram was appropriately calibrated and demonstrated a comparable 10-year AUROC to the MSKCC nomogram (0.73 vs. 0.66, P = 0.534) in the validation cohort. Our nomogram provided individualized risk estimates for women with DCIS treated with BCS, demonstrating a discriminative ability comparable to that of the MSKCC nomogram.

Challenges in the management of inconclusive breast findings on mammography in educated Nigerian women

Introduction: Breast cancer is one of the leading causes of morbidity and mortality among women in middle to low-income countries with most women presenting with late disease. Mammography is a major screening tool for the early detection of breast cancer with wide coverage in developed countries when compared to low-income countries. This study aims to evaluate the mammographic findings of women in southwest Nigeria, and also the follow-up rate of women with inconclusive findings on mammograms, Methodology: This is a descriptive study of findings in women who presented for mammography at the Radiology Department of LAUTECH Teaching Hospital, Ogbomoso. Mammograms with two standard views were performed after the completion of a structured questionnaire and informed consent. The data was entered and analyzed using SPSS version 26 with a p-value ≤ 0.5. Results: A total of 250 women participated in the study with an average age of 52.3±8.70 years and an age range of 36-86 years. Diagnostic mammography (55.2%) was more common than screening mammography and the commonest indication was breast lumps (25.2%). Heterogeneously dense breast density pattern (BIRADS C) which may obscure small masses is the most common (40.8%) while the most common final BIRADS category is 2, benign findings (51.6%), followed by BIRADS 0 (20%). Only 13 out of the 51 cases of BIRADS 0 had complementary imaging studies, and 38 (75%) failed to show up. Further, telephone interviews revealed that the most common reason for failure of follow up is poor counselling and ignorance. Conclusion: There is a need to increase the awareness of regular mammograms for screening purposes in this environment as observed in developed climes and also for women to understand the clinical implication of their breast density pattern to reduce anxiety and increase their cooperation for further imaging studies.

Age-related ultrasonographic mammary gland density patterns

Introduction: Mammary gland/breast density is important because it is a known biomarker for breast cancer risk. However, the sensitivity of mammography decreases with high breast density found in younger age group. Ultrasound is considered as the first-line examination in the classification of breast density and in the detection and characterization of breast lesions. This study aims to evaluate the relationship between age and ultrasonographic breast density pattern and its implication for breast cancer risk. Materials and Methods: This was a community-based cross-sectional, exploratory, descriptive study involving 658 females. Breast ultrasonographic scans were performed using a Sonoace X1 Machine with a 7.5 MHz transducer. The lesions detected and classified by ultrasonography as benign or malignant were further subjected to cytopathology. Results: Modal age group of the participants ranged from 33 to 43 years representing 29.8%. There was significant correlation (P<0.01) between ultrasonographic mammary gland density pattern and age, the age group of <33 years demonstrated predominant fibroglandular density pattern with mostly benign lesions, while the age group of 33–53 years demonstrated predominant heterogeneous breast density pattern with most of the malignant lesions in this age group, making it the high-risk group for breast cancer. Conclusion: The relationship between age and ultrasonographic breast density is inversely proportional and not absolute. It also concludes that ultrasonography is a reliable screening tool in the diagnostic process for mammary gland lesions, and as an imaging tool, it is the preferred modality in dense breast. The heterogeneous fibroglandular pattern emerged as the high-risk group for breast cancer, especially in middle age.

Mammographic density patterns in women from Torreon, Coahuila

Breast cancer is the main cause of death by cancer in Mexican women. High mammographic breast density is a well-established breast cancer risk factor that also increases the risk of death. However, there is limited data of breast density patterns among Mexican women and their association with breast cancer incidence and mortality. To determine the distribution of breast density patterns and BI-RADS (Breast Imaging Reporting and Data System) among women from Torreon, Coahuila. Observational and retrospective study. Mammographic reports of women from Torreon, Mexico, were analyzed. Reports came from IMSS HGZ#16, Sanatorio Español and a private radiological office. Only mammographic records which described age, breast density and Bi-RADS reports were included. Differences on breast density distribution were analyzed with the Chi-Square test according to age, economic sectors and BI-RADS classification. A total of 2,187 women were included, representing about 1% of the total adult women population of Torreon. The mean age was 54.4 years, and the mammographic density patterns distribution was: 19.15% fatty, 47.76% fibroglandular density, 27.10% heterogeneously dense, and 5.99% extremely dense. The main pattern in this Mexican population is the fibroglandular density, and extremely dense breast was only 6%. Our results suggest that non-dense breast tissue could increase breast cancer risk. Further studies on related risk factors, like body mass index are required.

The Positive Predictive Values of the Breast Imaging Reporting and Data System (BI-RADS) 4 Lesions and its Mammographic Morphological Features.

The Breast Imaging Reporting and Data System (BI-RADS) is a comprehensive guideline to systematize breast imaging reporting, and as per its recommendations, any lesion with likelihoods of malignancy greater than 2% is deemed as suspicious and tissue diagnosis is recommended. The aim of the study is to determine the positive predictive value (PPV) of BI-RADS categories 4a, 4b, and 4c for malignancy and association of mammographic morphological features of BI-RADS 4 subgroups with malignant outcomes. We retrospectively reviewed all the patients undergoing mammography with BI-RADS score of 4 followed by biopsy from May 2019 to April 2020. The predictive values of BI-RADS 4 subcategories and morphological features with malignancy are performed taking histopathology report as the gold standard. The PPV of BI-RADS subcategories 4a, 4b, and 4c for malignancies were 34, 89, and 97%, respectively. BI-RADS 4c patients tend to be older (50.2 ± 12.2 vs. 44.6 ± 10.3 years) with larger mass (44 ± 16 vs. 32.9 ± 16.8 mm) at presentation than 4a. Postmenopausal state (P = 0.03) and older age (P = 0.019) were significantly associated with malignancy. There is no meaningful difference observed in the predictability of BI-RADS category 4c lesions among different breast density patterns. The overall higher PPV for BI-RADS 4a and 4b reflects subjectivity in subcategory assignments of BI-RADS 4. In patients, less than 40 years with the BI-RADS 4a category on mammograms may undergo supplementary imaging with MRI which may downscale the lesion classification in turn reducing unnecessary biopsy and surgery.

Outcome of mammography examination in asymptomatic women.

Background:Early detection of breast cancer is important in reducing mortality, morbidity, and high socioeconomic burden associated with it. Mammography is currently the primary imaging modality used as a screening tool to detect early breast cancer in women experiencing no symptoms as they are most curable in the early stage with availability of breast conservative therapies.Objective:This study aimed at determining the mammographic breast density patterns and outcome in asymptomatic women who presented for mammographic examination in Abuja.Materials and Methods:This descriptive cross-sectional study comprises of 113 asymptomatic women who presented for mammographic examination at the Radiology Department of University of Abuja Teaching Hospital, Gwagwalada from March 2015 to December 2018. Two basic views (craniocaudal and mediolateral views) of the breast were obtained using EXR-650 mammographic machine.Results:The mean age of study population was 40.72 ± 10.45 years with age range of 35 and 65 years. Base on mammographic breast density, breast imaging, reporting, and data system 1 and 2 were the most prevalent. There was a positive correlation between mammographic breast density and age of respondents. This relationship was statistically significant (Pearson correlation = 0.56, P = 0.000). The mammographic outcome among asymptomatic women who had mammographic examination was negative in 69 (61.1%) women and positive in 44 (38.9%). The positive outcome noted in mammograms of women examined was: benign mass in 18 (15.9%) women; 9 (8.0%) had benign calcification; 7 (6.2%) showed architectural distortion; 5 (4.4%) was inconclusive; focal asymmetry in 3 (2.6%); and suspicious mass in 2 (1.8%).Conclusion:In this study, screening of women reveals various benign and malignant breast pathologies which necessitate early interventions.

Engineering the Extracellular Matrix to Model the Evolving Tumor Microenvironment.

SummaryClinical evidence supports a role for the extracellular matrix (ECM) in cancer risk and prognosis across multiple tumor types, and numerous studies have demonstrated that individual ECM components impact key hallmarks of tumor progression (e.g., proliferation, migration, angiogenesis). However, the ECM is a complex network of fibrillar proteins, glycoproteins, and proteoglycans that undergoes dramatic changes in composition and organization during tumor development. In this review, we will highlight how engineering approaches can be used to examine the impact of changes in tissue architecture, ECM composition (i.e., identity and levels of individual ECM components), and cellular- and tissue-level mechanics on tumor progression. In addition, we will discuss recently developed methods to model the ECM that have not yet been applied to the study of cancer.

Is it worth to perform preoperative MRI for breast cancer after mammography, tomosynthesis and ultrasound?

BackgroundThe use of preoperative breast MRI remains controversial despite being the most sensitive technique for the detection of breast malignancies. PurposeTo evaluate the benefit of preoperative breast MRI after performing the three conventional techniques (DM, US, DBT). To analyze the influence of breast density in the sensitivity of the different imaging techniques. Material and methodsRetrospective review of 280 histologically confirmed breast cancers in 192 women. We reviewed the medical records and evaluated the change of treatment induced by MRI. Also, we assessed the reports of DM and the combination of the different imaging techniques, and categorized them according to ACR density (a–d) and as negative (BI-RADS 1-3) or positive (BIRADS 4 or 5). The gold standard was the pathologic assessment of the surgical specimen. The sensitivity of the different techniques was compared using McNemar test. ResultsAmong these 192 women the use of MRI did not significantly increase the mastectomy rate (from 16.6% to 17.6%; p = 0.5). The addition of any technique demonstrated a higher sensitivity than DM alone. The sensitivity of DM alone was 52.5% while using all the techniques, including MRI, was 94.3% (p < 0.001). Regardless of breast density pattern, the addition of any technique significantly increased the sensitivity of DM (p < 0.001). ConclusionsThe addition of MRI to the three conventional techniques increased the sensitivity but did not significantly modify the rate of mastectomies. Additional techniques increased the sensitivity of DM in both dense and non-dense breasts.

Breast density pattern characterization by histogram features and texture descriptors

Introduction Breast cancer is the first leading cause of death for women in Brazil as well as in most countries in the world. Due to the relation between the breast density and the risk of breast cancer, in medical practice, the breast density classification is merely visual and dependent on professional experience, making this task very subjective. The purpose of this paper is to investigate image features based on histograms and Haralick texture descriptors so as to separate mammographic images into categories of breast density using an Artificial Neural Network. Methods We used 307 mammographic images from the INbreast digital database, extracting histogram features and texture descriptors of all mammograms and selecting them with the K-means technique. Then, these groups of selected features were used as inputs of an Artificial Neural Network to classify the images automatically into the four categories reported by radiologists. Results An average accuracy of 92.9% was obtained in a few tests using only some of the Haralick texture descriptors. Also, the accuracy rate increased to 98.95% when texture descriptors were mixed with some features based on a histogram. Conclusion Texture descriptors have proven to be better than gray levels features at differentiating the breast densities in mammographic images. From this paper, it was possible to automate the feature selection and the classification with acceptable error rates since the extraction of the features is suitable to the characteristics of the images involving the problem.

Abstract P2-13-02: Risk Factors for high risk breast density patterns in Hispanic/Latinas living in the Northeast, US

Abstract Introduction: Breast densities are the non-fat (epithelial and stromal) breast tissue observable on screening mammograms. Known to be associated with a 4 to 6 fold increase in breast cancer risk, dense breast patterns complicate the reading of screening mammograms resulting in lowered sensitivity. Little is currently known about the prevalence and/or predictors of breast density in Hispanic/Latino women living in the Northeast, US. Objective: The goal of this prospective study is to identify risk factors for high risk breast density patterns among a large cohort of Hispanic/Latino women with ancestral ties primarily to the Eastern Caribbean (Puerto Rico and the Dominican Republic) as well as Central and South America. Because the hormonal milieu is somewhat different in Hispanic/Latinas compared with White women, and likely also differs from that of Hispanic/Latinas living in other parts of the US, we explored the role of reproductive and physiological factors in high risk breast density patterns. Methods: We analyzed breast density predictors in an established cohort of 1,600 Hispanic/Latino women recruited from primary care clinics in 4 cities with the largest enclaves of Hispanic/Latinos in Connecticut. Hour-long telephone interviews provided baseline data on biological, medical care, and sociodemographic factors. We retrieved radiology records on 1570 (98.7%) consenting women. For this analysis, we report predictors of breast density among the 1,040 (65.4%) women who received at least one screening mammogram during 2 to 4 years of follow-up. Breast density classification was based on radiologist assigned BI-RADS classification. Associations between predictors and high risk breast density patterns were examined using chi square tests. Multivariate analyses were conducted using logistic regression; odds ratios (OR) and 95% confidence intervals (CI) are reported. Results: Of the 1,040 women who received at least one screening mammogram during the follow-up period, 280 (27%) women were identified as having high risk dense breasts (extremely or heterogeneously dense, i.e., greater than 50% of the breast composed of fibroglandular densities), while 760 women (73%) were classified as having nondense breasts (fatty or scattered fibroglandular densities), suggesting a lower prevalence of high risk breast density patterns in this population. In multivariate analysis, breast density predictors were similar to those reported for the general population (mostly White) women, and are similar to known risk factors for breast cancer. However, we found that Hispanic/Latinas with diabetes to be at significantly reduced odds of high risk breast density patterns. There was also evidence that the relationship between age at menarche and density was modified by BMI, with early age at menarche a risk factor among normal and underweight women only. Conclusion: Our findings suggest that Hispanic/Latino women may differ in breast density prevalence relative to the general population. However, we observed a protective effect of diabetes and a potential interaction between age at menarche and BMI. This investigation enhances our understanding of breast density in a subset of the Hispanic/Latino population and provides the basis for further research. Citation Format: Jones BA, Claye E, Philpotts L, Hooley R, Silber A, Epstein L. Risk Factors for high risk breast density patterns in Hispanic/Latinas living in the Northeast, US [abstract]. In: Proceedings of the 2016 San Antonio Breast Cancer Symposium; 2016 Dec 6-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2017;77(4 Suppl):Abstract nr P2-13-02.

A hybrid hierarchical framework for classification of breast density using digitized film screen mammograms

In the present work, a hybrid hierarchical framework for classification of breast density using digitized film screen mammograms has been proposed. For designing of an efficient classification framework 480 MLO view digitized screen film mammographic images are taken from DDSM dataset. The ROIs of fixed size i.e. 128 × 128 pixels are cropped from the center area of the breast (i.e. the area where glandular ducts are prominent). A total of 292 texture features based on statistical methods, signal processing based methods and transform domain based methods are computed for each ROI. The computed feature vector is subjected to PCA for dimensionality reduction. The reduced feature space is fed to the classification module. In this work 4-class breast density classification has been conducted using hierarchical framework where the first classifier is used to classify an unknown test ROI into B-I/other class. If the test ROI is predicted as other class, it is inputted to second classifier for the classification into B-II/dense class. If the test ROI is predicted as belonging to dense class, it is inputted to classifier for the classification into B-III/B-IV class. In this work five hierarchical classifiers designs consisting of 3 PCA-kNN, 3 PCA-PNN, 3 PCA-ANN, 3 PCA-NFC and 3 PCA-SVM classifiers has been proposed. The obtained maximum OCA value is 80.4% using PCA-NFC in hierarchical approach. Further, the best performing individual classifiers are clubbed together in a hierarchical framework to design hybrid hierarchical framework for classification of breast density using digitized screen film mammograms. The proposed hybrid hierarchical framework yields the OCA value of 84.1%. The result achieved by the proposed hybrid hierarchical framework is quite promising and can be used in clinical environment for differentiation between different breast density patterns.

A classification framework for prediction of breast density using an ensemble of neural network classifiers

The present work proposes a classification framework for the prediction of breast density using an ensemble of neural network classifiers. Expert radiologists, visualize the textural characteristics of center region of a breast to distinguish between different breast density classes. Accordingly, ROIs of fixed size are cropped from the center location of the breast tissue and GLCM mean features are computed for each ROI by varying inter-pixel distance ‘d’ from 1 to 15. The proposed classification framework consists of two stages, (a) first stage: this stage consists of a single 4-class neural network classifier NN0 (B-I/B-II/B-III/B-IV) which yields the output probability vector [PB-I PB-IIPB-IIIPB-IV] indicating the probability values with which a test ROI belongs to a particular breast density class. (b) second stage: this stage consists of an ensemble of six binary neural network classifiers NN1 (B-I/B-II), NN2 (B-I/B-III), NN3 (B-I/B-IV), NN4 (B-II/B-III), NN5 (B-II/B-IV) and NN6 (B-III/B-IV).The output of the first stage of the classification framework, i.e. output on NN0 is used to obtain the two most probable classes for a test ROI. In the second stage this test ROI is passed through one of the binary neural networks, i.e. NN1 to NN6 corresponding to the two most probable classes predicted by NN0. After passing the entire test ROIs through the second stage, the overall accuracy increases from 79.5% to 90.8%. The promising results achieved by the proposed classification framework indicate that it can be used in clinical environment for differentiation between breast density patterns.

Reproductive factors related to childbearing and mammographic breast density.

We investigated the associations of reproductive factors related to childbearing with percent breast density, absolute dense and nondense areas, by menopausal status. This study included 4110 cancer-free women within the Nurses' Health Study and Nurses' Health Study II cohorts. Percent breast density, absolute dense and nondense areas were measured from digitized mammography film images with computerized techniques. All density measures were square root-transformed in all the analyses to improve normality. The data on reproductive variables and other breast cancer risk factors were obtained from biennial questionnaires, at the time of the mammogram date. As compared to nulliparous women, parous postmenopausal women had lower percent density (β=-0.60, 95% CI -0.84; -0.37), smaller absolute dense area (β=-0.66, 95% CI -1.03; -0.29), and greater nondense area (β=0.72, 95% CI 0.27; 1.16). Among parous women, number of children was inversely associated with percent density in pre- (β per one child=-0.12, 95% CI -0.20; -0.05) and postmenopausal women (β per one child=-0.07, 95% CI -0.12; -0.02). The positive associations of breastfeeding with absolute dense and nondense areas were limited to premenopausal women, while the positive association of the age at first child's birth with percent density and the inverse association with nondense area were limited to postmenopausal women. Women with greater number of children and younger age at first child's birth have more favorable breast density patterns that could explain subsequent breast cancer risk reduction.

Abstract P4-01-02: Identification of histopathologic determinants of mammographic breast density as a cancer risk factor

Abstract Background: Mammographic density and texture, the amount and appearance of fibroglandular tissue respectively, are known to be strong predictors of a woman's risk to develop breast cancer. However, how differences in underlying tissue biology are associated with the wide range of breast density patterns seen among women is currently unknown. Understanding the biological mechanisms driving breast density can be critical for developing targeted interventions aimed at reducing a woman's risk for breast cancer. Methods: Digital mammograms and formalin-fixed paraffin-embedded biopsy tissue sections from 73 women who donated breast tissue to the Susan G. Komen for the Cure Tissue Bank at the Indiana University Simon Cancer Center were included in this analysis. Hematoxylin and eosin (H&amp;E) and AE1/AE3 cytokeratin stains were applied to the tissue sections, which were then visually characterized by an expert breast pathologist. H&amp;E stains were used to assess the presence (in ≥5% of the tissue section) or absence of non-proliferative fibrocystic changes, proliferative fibrocystic changes without atypia, inflammatory and reactive conditions, or benign tumors. AE1/AE3 stains were used to quantify the extent of epithelial and stromal content, as well as the number of lobules and ductal structures seen in the section. Quantitative breast percent density (PD%) and whole-breast texture analysis was performed on the digital mammograms using validated software. Parenchymal texture measures recently demonstrated to be associated with breast cancer risk were assessed, including the gray-level co-occurrence features Cluster-shade, Correlation, Energy, Entropy, Inertia and Inverse Difference Moment. Texture was characterized within a 2.5cm2 area of interest in the upper-outer quadrant of the mammograms corresponding to the approximate location of the biopsy. Partial-R2 (pR2) analysis was applied in order to assess the proportion of the variability in the mammographic texture which can be directly attributed to underlying histological properties after adjusting for race, menopausal status, body mass index, PD% and mammography unit manufacturer, utilizing a false-discovery-rate (FDR) multiple comparisons correction. Results: The presence of proliferative fibrocystic changes without atypia was found to have a significant association to Correlation (pR2=0.21), Energy (pR2=0.13), Entropy (pR2=0.16), and Inverse Difference Moment (pR2=0.14) at the FDR-corrected significance level of p&amp;lt;0.0042, even after adjusting for race, menopausal status, body mass index, PD% and the mammography unit manufacturer. These findings suggest that 13-21% of the variation in parenchymal texture patterns seen between women can be explained by the presence of proliferative fibrocystic changes without atypia, a common and well known risk factor for breast cancer. Conclusion: In this study, we identified proliferative fibrocystic changes without atypia as one potential driver of image-based biomarkers of breast cancer risk. Ultimately, identification of radiographic biomarkers of tissue microenvironment could aid in the development of targeted chemopreventative interventions for women with dense breast tissue while simultaneously providing image-based biomarkers to monitor their efficacy. Citation Format: Keller BM, Batiste RC, Chen J, McDonald ES, Conant EF, Kontos D, Feldman MD. Identification of histopathologic determinants of mammographic breast density as a cancer risk factor. [abstract]. In: Proceedings of the Thirty-Eighth Annual CTRC-AACR San Antonio Breast Cancer Symposium: 2015 Dec 8-12; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2016;76(4 Suppl):Abstract nr P4-01-02.

Mammographic Ellipse Modelling for Risk Estimation

It has been shown that breast density and parenchymal patterns are significant indicators in mammographic risk assessment. In addition, studies have shown that the sensitivity of computer aided tools decreases significantly with increase in breast density. As such, mammographic density estimation and classification plays an important role in CAD systems. In this paper, we present the classification of mammographic images according to breast parenchymal structures through a multi-scale ellipse blob detection technique. Our classification is based on classifying the mammographic images of the MIAS dataset into high/low risk mammograms based on features extracted from a blob detection technique which is based on breast tissue structure. In addition, it evaluates the relation between the BIRADS classes and low/high risk mammograms. Results demonstrate the probability of estimating breast density using computer vision techniques to improve classification of mammographic images as low/high risk.

Cáncer de mama en pacientes con patrón de densidad mamaria alta, diagnosticado por mamografía

Antecedentes: La densidad mamaria se asocia al riesgo de cáncer mamario. Existen estudios que estiman este riesgo, pero el rango varía ampliamente debido a los tipos de estudio y población. Objetivo: Determinar el riesgo de cáncer mamario en mujeres con mamas densas detectado mamográficamente. Diseño: Estudio retrospectivo, de casos y controles. Institución: Departamento de Radiología, Hospital Nacional Edgardo Rebagliati Martins, Lima, Perú. Materiales: Mamografías. Métodos: Entre el 1º de enero y el 31 de diciembre de 2008, se evaluó las placas mamográficas de 76 pacientes (casos) diagnosticadas de cáncer mamario en el Servicio de Anatomía Patológica. El grupo de 152 controles correspondió a estudios mamográficos realizados durante el mismo año, catalogados como BIRADS 1 y 2 y sin estudio anatomopatológico, información proporcionada por el Servicio de Radiología. Se usó la clasificación de Tabár para determinar el tipo de densidad mamaria. Principales medidas de resultados: Correlación de densidad mamaria y cáncer de mama. Resultados: El OR ajustado a la edad fue 4,33 (IC 95%: 1,79 a 10,48), con un p = 0,0006. La diferencia entre las frecuencias de mamas densas en el grupo casos y controles fue 21,1% y 7,2%, respectivamente (Z = 2.8262, p = 0.0047). Se encontró un 38% de cáncer mamario en pacientes ≥50 años y 19,3% en las de &lt;50 años. Hubo mayor porcentaje de mamas no densas en ambos grupos etarios de los casos y controles. Conclusiones: El patrón denso mamográfico aumentó el riesgo de padecer cáncer de mama, existiendo una asociación altamente significativa.

Inter-observer agreement according to three methods of evaluating mammographic density and parenchymal pattern in a case control study: impact on relative risk of breast cancer.

BackgroundMammographic breast density and parenchymal patterns are well-established risk factors for breast cancer. We aimed to report inter-observer agreement on three different subjective ways of assessing mammographic density and parenchymal pattern, and secondarily to examine what potential impact reproducibility has on relative risk estimates of breast cancer.MethodsThis retrospective case–control study included 122 cases and 262 age- and time matched controls (765 breasts) based on a 2007 screening cohort of 14,736 women with negative screening mammograms from Bispebjerg Hospital, Copenhagen. Digitised randomized film-based mammograms were classified independently by two readers according to two radiological visual classifications (BI-RADS and Tabár) and a computerized interactive threshold technique measuring area-based percent mammographic density (denoted PMD). Kappa statistics, Intraclass Correlation Coefficient (ICC) (equivalent to weighted kappa), Pearson’s linear correlation coefficient and limits-of-agreement analysis were used to evaluate inter-observer agreement. High/low-risk agreement was also determined by defining the following categories as high-risk: BI-RADS’s D3 and D4, Tabár’s PIV and PV and the upper two quartiles (within density range) of PMD. The relative risk of breast cancer was estimated using logistic regression to calculate odds ratios (ORs) adjusted for age, which were compared between the two readers.ResultsSubstantial inter-observer agreement was seen for BI-RADS and Tabár (κ=0.68 and 0.64) and agreement was almost perfect when ICC was calculated for the ordinal BI-RADS scale (ICC=0.88) and the continuous PMD measure (ICC=0.93). The two readers judged 5% (PMD), 10% (Tabár) and 13% (BI-RADS) of the women to different high/low-risk categories, respectively. Inter-reader variability showed different impact on the relative risk of breast cancer estimated by the two readers on a multiple-category scale, however, not on a high/low-risk scale. Tabár’s pattern IV demonstrated the highest ORs of all density patterns investigated.ConclusionsOur study shows the Tabár classification has comparable inter-observer reproducibility with well tested density methods, and confirms the association between Tabár’s PIV and breast cancer. In spite of comparable high inter-observer agreement for all three methods, impact on ORs for breast cancer seems to differ according to the density scale used. Automated computerized techniques are needed to fully overcome the impact of subjectivity.

Pilot study demonstrating potential association between breast cancer image‐based risk phenotypes and genomic biomarkers

In this pilot study, the authors examined associations between image-based phenotypes and genomic biomarkers. The potential genetic contribution of UGT2B genes to interindividual variation in breast density and mammographic parenchymal patterns is demonstrated by performing an association study between image-based phenotypes and genomic biomarkers [single-nucleotide polymorphism (SNP) genotypes]. This candidate-gene approach study included 179 subjects for whom both mammograms and blood DNA samples had been obtained. The full-field digital mammograms were acquired using a GE Senographe 2000D FFDM system (12-bit; 0.1 mm-pixel size). Regions-of-interest, 256 × 256 pixels in size, selected from the central breast region behind the nipple underwent computerized image analysis to yield image-based phenotypes of mammographic density and parenchymal texture patterns. SNP genotyping was performed using a Sequenom MassArray System. One hundred twenty three SNPs with minor allele frequency above 5% were genotyped for the UGT2B gene clusters, and used in the study. The association between the image-based phenotypes and genomic biomarkers was assessed with the Pearson correlation coefficient via thePLINK software, and included permutation and correction for multiple SNP comparisons. From the phenotype-genotype association analysis, a parenchyma texture coarseness feature was found to be correlated with SNP rs451632 after multiple test correction for the multiple SNPs (p = 0.022). The power law β, which is used to characterize the frequency component of texture patterns, was found to be correlated with SNP rs4148298 (p = 0.035). The authors' results indicate that UGT2B gene variation may contribute to interindividual variation in mammographic parenchymal patterns and breast density. Understanding the relationship between image-based phenotypes and genomic biomarkers may help understand the biologic mechanism for image-based biomarkers and yield a future role in personalized medicine.

Breast cancer risk analysis based on a novel segmentation framework for digital mammograms.

The radiographic appearance of breast tissue has been established as a strong risk factor for breast cancer. Here we present a complete machine learning framework for automatic estimation of mammographic density (MD) and robust feature extraction for breast cancer risk analysis. Our framework is able to simultaneously classify the breast region, fatty tissue, pectoral muscle, glandular tissue and nipple region. Integral to our method is the extraction of measures of breast density (as the fraction of the breast area occupied by glandular tissue) and mammographic pattern. A novel aspect of the segmentation framework is that a probability map associated with the label mask is provided, which indicates the level of confidence of each pixel being classified as the current label. The Pearson correlation coefficient between the estimated MD value and the ground truth is 0.8012 (p-value < 0.0001). We demonstrate the capability of our methods to discriminate between women with and without cancer by analyzing the contralateral mammograms of 50 women with unilateral breast cancer, and 50 controls. Using MD we obtained an area under the ROC curve (AUC) of 0.61; however our texture-based measure of mammographic pattern significantly outperforms the MD discrimination with an AUC of 0.70.