Six parenchymal phenotypes were established that may be associated with a higher risk of developing breast cancer. Studies of these phenotypes identified by radiomics on mammograms demonstrated that these patterns were associated with an increased risk of invasive breast cancer, according to findings published in Radiology.
“We hypothesized that some patterns or phenotypes would be associated with a high risk of future breast cancer and suggest which women may benefit from supplemental screening or prevention strategies,” Celine M. Vachon, PhD, Professor of Epidemiology at the Mayo Clinic in Rochester, Minnesota, and one of the study’s senior authors, stated. “Other phenotypes could be associated with low risk, ultimately, suggesting less frequent screening.”
Study Methods and Results
The study investigators conducted a retrospective cross-sectional study of 30,000 randomly selected women with four-view mammograms as well as a nested case-control study of 1,055 women with invasive breast cancer who were matched to 2,764 women without breast cancer from three diverse breast screening practices.
Radiomics extracted and standardized quantitative features from the mammograms to identify patterns and characteristics in the breast tissue. These were then adjusted for age and practice.
Six parenchymal phenotypes were defined and associated with a higher risk of developing invasive breast cancer (P < .001).
Similar associations for increased breast cancer risk were found between both Black and White women (P = .23)
“We were surprised to find that these radiomic phenotypes showed suggestion of a stronger risk among Black vs White women,” stated co-senior author Despina Kontos, PhD, the Herbert and Florence Irving Professor of Radiological Sciences and Chief Research Information Officer at Columbia University Irving Medical Center. “This is particularly important as breast cancer tends to be more aggressive in Black women, highlighting the need for novel risk factors in this population.”
The radiomic findings also showed a positive association for the parenchymal phenotypes and false-negative findings (P = .004) as well as for symptomatic interval cancers (P = .006).
These findings can be used to better determine assessments of breast cancer risk and identify women who could benefit from additional screenings.
“Understanding who is at greatest risk of invasive breast cancer, especially the most aggressive types, is crucial for preventing cancer and diagnosing it early for potentially the choice of less intensive treatments,” stated co-senior author Karla M. Kerlikowske, MD, Professor of Medicine and Epidemiology and Biostatistics at University of California San Francisco.
“Our next steps include extending our investigations to larger groups of women in the U.S. population, especially examining 3D mammograms, and combining these radiomic risk factors with genetic and other lifestyle factors to improve our ability to define who is (and who is not) at increased risk of invasive breast cancer,” Dr. Vachon concluded.
Disclosure: For full disclosures of the study authors, visit pubs.rsna.org.
