Mammographic Breast Density Assessment Using Deep Learning: Clinical Implementation

Abstract

ammographic breast density can mask cancers at mammography and is an independent risk factor for breast cancer (1-3). Legislation mandating patients be notified of mammographic breast density has passed in more than 30 states, and a federal bill is under consideration. Details of state legislation vary, but most states require direct reporting to the patient that breast density can mask cancers at mammography and that the patient may benefit from additional testing. Qualitative assessment of mammographic breast density is subjective and varies widely between radiologists (4-10). In a study of 83 radiologists who assessed breast density, Sprague et al (4) found extreme variation in qualitative density assessment per the Breast Imaging Reporting and Data System (BI-RADS), with 6%-85% of mammograms assessed as either heterogeneously or extremely dense depending on radiologist interpretation. In a study of 34 radiologists, the intraradiologist agreement of density assessments among women who underwent two examinations varied from 62% to 87% (6). Commercially available methods for automated assessment of breast density do exist; however, they yield mixed results in agreement with expert qualitative density assessments, with k scores of 0.32-0.61 (11,12). These methods tend to result in over-or underreporting of breast density when compared with qualitative assessment by radiologists (11,13). A recent study found significant differences in density assessments in the same 4170 women with two software programs (Volpara, Volpara Solutions, Wellington, New Zealand; Quantra, Hologic, Bedford, Mass), with the software programs showing 37% and 51%, respectively, of women had dense breast tissue. In the same set of mammograms, radiologists determined 43% of the women had dense breast tissue (13). Deep learning (DL) has been gaining traction in radiology (12,14-17). Specifically, there has been preliminary work with DL methods to assess breast density (12,18); however, none of these techniques have been implemented in clinical practice, raising questions about clinical acceptance by practicing radiologists and the effect on patient care. In contrast, our purpose was to develop a DL algorithm we could use to reliably assess breast density and to measure the acceptance of its predictions in real-time clinical practice. We hypothesize that DL models can be applied to assess breast density at the same level as experienced breast imagers and that they can be accepted into routine clinical practice.

Prediction of reader estimates of mammographic density using convolutional neural networks

“…Kerlikowske et al 44 compared automatic BI-RADS with clinical BI-RADS and showed they similarly predicted both interval and screendetected cancer risk, which indicates that either measure may be used for density assessment. A deep learning method proposed by Lehman et al 45 for assessing BI-RADS density in a clinical setting, showed good agreement between the model's predictions and radiologists' assessments. Duffy et al 46 investigated the association of different density measures with breast cancer risk using digital breast tomosynthesis and compared automatic and visual measures.…”

A Deep Learning Mammography-based Model for Improved Breast Cancer Risk Prediction

“…It was compliant with the Health Insurance Portability and Accountability Act. Mammograms in 39 272 of the 60 886 women in our patient population were previously studied in our development of a breast density assessment algorithm (10).…”

“…Same-age patients who are assigned the same density score can have drastically different mammography with vastly different outcomes. Whereas previous studies (10)(11)(12) explored automated methods to assess breast density, these efforts reduced the mammographic input into a few statistics largely related to volume of glandular tissue that are not sufficient to distinguish patients who will and will not develop breast cancer.…”

Volumetric breast density measurement for personalized screening: accuracy, reproducibility, consistency, and agreement with visual assessment

“…7 Recently, also, deep machine learning techniques have been applied for breast density classification. 13 For using an automated breast density assessment software for clinical decision support, it should be validated comprehensively. Ng and Lau 7 have identified six requirements (denoted in their paper as "sanity checks") that should be fulfilled by an automated breast density measurement software: Some studies exist that validate existing software applications for automated breast density assessment.…”