Factors associated with mammographic breast density among women in Karachi Pakistan

Background There are no studies done to evaluate the distribution of mammographic breast density and factors associated with it among Pakistani women. Methods Participants included 477 women, who had received either diagnostic or screening mammography at two hospitals in Karachi Pakistan. Mammographic breast density was assessed using the Breast Imaging Reporting and Data System. In person interviews were conducted using a detailed questionnaire, to assess risk factors of interest, and venous blood was collected to measure serum vitamin D level at the end of the interview. To determine the association of potential factors with mammographic breast density, multivariable polytomous logistic regression was used. Results High-density mammographic breast density (heterogeneously and dense categories) was high and found in 62.4% of women. There was a significant association of both heterogeneously dense and dense breasts with women of a younger age group < 45 years (OR 2.68, 95% CI 1.60–4.49) and (OR 4.83, 95% CI 2.54–9.16) respectively. Women with heterogeneously dense and dense breasts versus fatty and fibroglandular breasts had a higher history of benign breast disease (OR 1.90, 95% CI 1.14–3.17) and (OR 3.61, 95% CI 1.90–6.86) respectively. There was an inverse relationship between breast density and body mass index. Women with dense breasts and heterogeneously dense breasts had lower body mass index (OR 0.94 95% CI 0.90–0.99) and (OR 0.81, 95% CI 0.76–0.87) respectively. There was no association of mammographic breast density with serum vitamin D levels, diet, and breast cancer. Conclusions The findings of a positive association of higher mammographic density with younger age and benign breast disease and a negative association between body mass index and breast density are important findings that need to be considered in developing screening guidelines for the Pakistani population.

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

This systematic review aimed to assess the methods used to classify mammographic breast parenchymal features in relation to prediction of future breast cancer including the time from mammogram to diagnosis of breast cancer, and methods for the identification of texture features and selection of features for inclusion in analysis. 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 risk of breast cancer. Twenty-eight articles published since 2016 were included in the final review. Of these, 7 assessed texture features from film mammograms images, 3 did not report details of the image used, and the others used full field mammograms from Hologic, GE and other manufacturers. The identification of parenchymal texture features varied from using a predefined list to machine-driven identification. Reduction in number of features chosen for 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 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. By following these recommendations, we expect to improve risk classification and risk prediction for women to tailor screening and prevention strategies to level of risk.

Addressing catastrophic forgetting for medical domain expansion

Model brittleness is a key concern when deploying deep learning models in real-world medical settings. A model that has high performance at one dataset may suffer a significant decline in performance when tested at on different datasets. While pooling datasets from multiple hospitals and re-training may provide a straightforward solution, it is often infeasible and may compromise patient privacy. An alternative approach is to fine-tune the model on subsequent datasets after training on the original dataset. Notably,this approach degrades model performance at the original datasets, a phenomenon known as catastrophic forgetting. In this paper, we develop an approach to address catastrophic forgetting based on elastic weight consolidation combined with modulation of batch normalization statistics under three scenarios: 1) for expanding the domain from one imaging system’s data to another imaging system’s 2) for expanding the domain from a large multi-hospital dataset to another single hospital dataset 3) for expanding the domain from dataset from one geographic region to a dataset from another geographic region. Focusing on the clinical uses cases of mammographic breast density detection and retinopathy of prematurity stage diagnosis, we show that our approach outperforms several other state-of-the-art approaches and provide theoretical justification for the efficacy of batch normalization modulation. The results of this study are generally applicable to the deployment of any clinical deep learning model which requires domain expansion.

Mammary collagen architecture and its association with mammographic density and lesion severity among women undergoing image-guided breast biopsy

Background Elevated mammographic breast density is a strong breast cancer risk factor with poorly understood etiology. Increased deposition of collagen, one of the main fibrous proteins present in breast stroma, has been associated with increased mammographic density. Collagen fiber architecture has been linked to poor outcomes in breast cancer. However, relationships of quantitative collagen fiber features assessed in diagnostic biopsies with mammographic density and lesion severity are not well-established. Methods Clinically indicated breast biopsies from 65 in situ or invasive breast cancer cases and 73 frequency matched-controls with a benign biopsy result were used to measure collagen fiber features (length, straightness, width, alignment, orientation and density (fibers/µm2)) using second harmonic generation microscopy in up to three regions of interest (ROIs) per biopsy: normal, benign breast disease, and cancer. Local and global mammographic density volumes were quantified in the ipsilateral breast in pre-biopsy full-field digital mammograms. Associations of fibrillar collagen features with mammographic density and severity of biopsy diagnosis were evaluated using generalized estimating equation models with an independent correlation structure to account for multiple ROIs within each biopsy section. Results Collagen fiber density was positively associated with the proportion of stroma on the biopsy slide (p < 0.001) and with local percent mammographic density volume at both the biopsy target (p = 0.035) and within a 2 mm perilesional ring (p = 0.02), but not with global mammographic density measures. As severity of the breast biopsy diagnosis increased at the ROI level, collagen fibers tended to be less dense, shorter, straighter, thinner, and more aligned with one another (p < 0.05). Conclusions Collagen fiber density was positively associated with local, but not global, mammographic density, suggesting that collagen microarchitecture may not translate into macroscopic mammographic features. However, collagen fiber features may be markers of cancer risk and/or progression among women referred for biopsy based on abnormal breast imaging.

Does circulating progesterone mediate the associations of single nucleotide polymorphisms in progesterone receptor (PGR)-related genes with mammographic breast density in premenopausal women?

Progesterone is a proliferative hormone in the breast but the associations of genetic variations in progesterone-regulated pathways with mammographic breast density (MD) in premenopausal women and whether these associations are mediated through circulating progesterone are not clearly defined. We, therefore, investigated these associations in 364 premenopausal women with a median age of 44 years. We sequenced 179 progesterone receptor (PGR)-related single nucleotide polymorphisms (SNPs). We measured volumetric percent density (VPD) and non-dense volume (NDV) using Volpara. Linear regression models were fit on circulating progesterone or VPD/NDV separately. We performed mediation analysis to evaluate whether the effect of a SNP on VPD/NDV is mediated through circulating progesterone. All analyses were adjusted for confounders, phase of menstrual cycle and the Benjamini–Hochberg false discovery (FDR) adjusted p-value was applied to correct for multiple testing. In multivariable analyses, only PGR rs657516 had a direct effect on VPD (averaged direct effect estimate = − 0.20, 95%CI = − 0.38 ~ − 0.04, p-value = 0.02) but this was not statistically significant after FDR correction and the effect was not mediated by circulating progesterone (mediation effect averaged across the two genotypes = 0.01, 95%CI = − 0.02 ~ 0.03, p-value = 0.70). Five SNPs (PGR rs11571241, rs11571239, rs1824128, rs11571150, PGRMC1 rs41294894) were associated with circulating progesterone but these were not statistically significant after FDR correction. SNPs in PGR-related genes were not associated with VPD, NDV and circulating progesterone did not mediate the associations, suggesting that the effects, if any, of these SNPs on MD are independent of circulating progesterone.