Abstract
Breast density, a breast cancer risk factor, is a radiologic feature that reflects fibroglandular tissue content relative to breast area or volume. Its histology is incompletely characterized. Here we use deep learning approaches to identify histologic correlates in radiologically-guided biopsies that may underlie breast density and distinguish cancer among women with elevated and low density. We evaluated hematoxylin and eosin (H&E)-stained digitized images from image-guided breast biopsies (n = 852 patients). Breast density was assessed as global and localized fibroglandular volume (%). A convolutional neural network characterized H&E composition. In total 37 features were extracted from the network output, describing tissue quantities and morphological structure. A random forest regression model was trained to identify correlates most predictive of fibroglandular volume (n = 588). Correlations between predicted and radiologically quantified fibroglandular volume were assessed in 264 independent patients. A second random forest classifier was trained to predict diagnosis (invasive vs. benign); performance was assessed using area under receiver-operating characteristics curves (AUC). Using extracted features, regression models predicted global (r = 0.94) and localized (r = 0.93) fibroglandular volume, with fat and non-fatty stromal content representing the strongest correlates, followed by epithelial organization rather than quantity. For predicting cancer among high and low fibroglandular volume, the classifier achieved AUCs of 0.92 and 0.84, respectively, with epithelial organizational features ranking most important. These results suggest non-fatty stroma, fat tissue quantities and epithelial region organization predict fibroglandular volume. The model holds promise for identifying histological correlates of cancer risk in patients with high and low density and warrants further evaluation.
Highlights
Among women, invasive breast cancer is the most commonly diagnosed female cancer in most countries worldwide.[1]
Exploratory investigation relating histologic features to biopsy diagnosis among patients with high and low fibroglandular volume As elevated breast density is common among women,[4] yet only a small proportion will develop invasive breast cancer, we aimed to identify histological correlates that could inform future breast cancer risk stratification among women undergoing diagnostic biopsy with either high or low breast density
We report that we can predict global and local mammographic fibroglandular volume by applying a deep convolutional neural network model to hematoxylin and eosin (H&E)-stained sections of image-guided breast biopsies prompted by an abnormal mammogram
Summary
Invasive breast cancer is the most commonly diagnosed female cancer in most countries worldwide.[1] Increased mammographic breast density, which describes the radiologically appearing white tissue on a mammogram, is one of the strongest breast cancer risk factors[2]. The few studies that have examined histological correlates of breast density have suggested that higher breast density is associated with greater epithelial cell content and non-fatty stroma.[7,8] While most studies to date have utilized quantitative microscopy to characterize breast tissue from women undergoing procedures for suspect lesions, one study of non-cancerous autopsy breast tissues showed positive relationships between epithelial and nonfatty stromal tissue, stromal collagen area, and percent density.[9]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
