Machine Learning Reveals Breast Cancer Risk Indicator in Women with Dense Breasts
A recent study published in Radiology, a journal of the Radiological Society of North America (RSNA), has found that background parenchymal enhancement (BPE) on breast MRI can serve as an indicator of breast cancer risk in women with extremely dense breasts. This discovery could have significant implications for women with dense breasts who are at a higher risk of developing breast cancer.
Women with extremely dense breasts are three to six times more likely to develop breast cancer compared to those with fatty breasts. However, mammography, the standard screening method for breast cancer, is less effective in detecting early-stage breast cancer in women with dense breasts. To address this challenge, researchers have explored supplemental MRI screening for women between the ages of 50 and 75 with dense breasts.
One important breast cancer risk factor is BPE, which refers to the level of normal fibroglandular tissue enhancement on breast MRI. However, the association between BPE and breast cancer risk, as well as its comparison to other established clinical risk factors such as age, body mass index (BMI), family history, and breast density, remains relatively unknown.
In this groundbreaking study, researchers examined the relationship between BPE and breast cancer risk in women with extremely dense breasts. The study utilized data from the Dense Tissue and Early Breast Neoplasm Screening (DENSE) Trial, which included 4,553 participants from multiple institutions in the Netherlands. The participants underwent dynamic contrast-enhanced MRI exams every two years between December 2011 and January 2016.
Using a deep learning model, the researchers developed a method to automatically identify and quantify the fibroglandular tissue from the MRI exams. After adjusting for age, BMI, and BPE, the researchers discovered that women with higher volumes of enhancing parenchyma had a greater incidence of breast cancer compared to those with lower volumes.
Out of the 4,553 women in the study, 122 were diagnosed with breast cancer. Approximately 63% of these cases were detected after the first round of screening, with an average cancer detection time of 24 months for the remaining cases.
According to Dr. Kenneth G. A. Gilhuijs, the study’s co-author from the Department of Radiology at the University Medical Center Utrecht in the Netherlands, Parenchyma does not enhance uniformly on MRI. This method calculates all the different subvolumes at which the parenchyma enhances and sorts them from high to low.
While supplemental MRI screening for women with dense breasts may reduce the number of interval cancers (breast cancers diagnosed between routine mammography screenings), it may also increase the workload for radiologists. To address this concern, the researchers suggest developing more personalized strategies to handle the additional screenings, thereby alleviating the strain on the healthcare system.
Dr. Gilhuijs emphasizes that this study is a significant step towards tailoring the frequency of supplemental MRI screening for women with dense breasts. By considering not only breast density but also other characteristics identified from the first screening MRI, healthcare providers can develop more targeted and effective approaches to breast cancer screening.
This study highlights the potential of machine learning in identifying breast cancer risk indicators and improving the accuracy of breast cancer screening for women with dense breasts. Further research and development in this field could lead to significant advancements in early detection and personalized treatment options for breast cancer patients.
Reference: Wang, H., et al. (2023) Assessing Quantitative Parenchymal Features at Baseline Dynamic Contrast-enhanced MRI and Cancer Occurrence in Women with Extremely Dense Breasts. Radiology. doi.org/10.1148/radiol.222841.
